Agents on AI Knowledge Base

Building with the Claude API

Mon, 01 Jan 0001 00:00:00 +0000

The most comprehensive free course on building with Claude’s API — 21 lessons covering everything from basic API calls to tool use, structured outputs, and agent patterns. This is Anthropic’s flagship developer course and the definitive companion to the Claude API documentation in this knowledge base. If you’re building production applications with Claude, this course provides the hands-on practice that documentation alone cannot. Take this alongside the Claude API Essentials learning path.

Symphony Overview

Mon, 01 Jan 0001 00:00:00 +0000

Symphony turns project work into isolated, autonomous implementation runs. It polls issue trackers, spawns coding agents per issue in isolated workspaces, and manages the full lifecycle from ticket to merged PR.

What Is an AI Agent?

Mon, 01 Jan 0001 00:00:00 +0000

McKinsey’s explainer on AI agents — what they are, how they differ from chatbots, and how they will impact business operations and the workforce.

Symphony Service Specification

Mon, 01 Jan 0001 00:00:00 +0000

Complete technical specification for implementing Symphony: six architectural layers, orchestration state machine, workspace management, agent runner protocol, polling and scheduling, retry semantics, and observability.

Elixir Reference Implementation

Mon, 01 Jan 0001 00:00:00 +0000

Setup and usage guide for Symphony’s experimental Elixir/BEAM reference implementation, leveraging OTP supervision trees for fault-tolerant agent orchestration.

Introduction to Agent Skills

Mon, 01 Jan 0001 00:00:00 +0000

Learn to build structured, reusable capabilities for Claude-based agents using the Agent Skills framework. Covers skill design, packaging, tool orchestration, and deployment patterns. This is Anthropic’s bridge between basic API usage and production agent development — take it after the Claude API course and before diving into the Agent SDK Deep Dive learning path.

WORKFLOW.md Configuration

Mon, 01 Jan 0001 00:00:00 +0000

The WORKFLOW.md file format: YAML front matter configuring tracker integration, polling intervals, workspace hooks, and agent settings, followed by a markdown prompt template with issue-field substitution.

Claude Code Mastery

Mon, 01 Jan 0001 00:00:00 +0000

Master Claude Code from setup through advanced usage. Learn the configuration system, memory, hooks, MCP integration, and how to use it effectively for complex software engineering tasks.

Orchestration State Machine

Mon, 01 Jan 0001 00:00:00 +0000

Symphony’s state machine for issue lifecycle: polling, dispatch, active run tracking, retry queuing with exponential backoff, and reconciliation of running issues against tracker state changes.

LangChain for LLM Application Development

Mon, 01 Jan 0001 00:00:00 +0000

Harrison Chase (LangChain CEO) and Andrew Ng’s one-hour introduction to building LLM applications with LangChain. Covers chains, memory, prompts, and agents. The fastest way to understand what LangChain does and whether it’s the right framework for your use case. Pair with the RAG from Scratch learning path to go deeper into retrieval-augmented generation patterns.

SDD with Claude Code

Mon, 01 Jan 0001 00:00:00 +0000

Educational chapter on applying specification-driven development with Claude Code, covering spec authoring, agent interaction patterns, and iterative refinement.

The Agentic Protocol Stack

Mon, 01 Jan 0001 00:00:00 +0000

Understand the three open protocols forming the agentic AI communication stack:

MCP (agent-to-tool) — how agents use external tools and data
A2A (agent-to-agent) — how agents collaborate across platforms
AG-UI (agent-to-user) — how agents communicate with frontends

All three are converging under the Linux Foundation’s Agentic AI Foundation (AAIF). This path teaches you the architecture and practical usage of each layer.

Functions, Tools and Agents with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Deepens the LangChain introduction with focus on function calling, tool use, and agent patterns — the building blocks of agentic AI applications. Covers OpenAI’s function calling API, LangChain tool abstractions, and conversational agents. Take this after the LangChain intro to understand how agents actually work under the hood.

Build What You Mean, Not What You Guess

Mon, 01 Jan 0001 00:00:00 +0000

How SDD reduces ambiguity in AI-assisted development by replacing informal prompts with structured specifications, with focus on agentic workflows.

Building Agentic RAG with LlamaIndex

Mon, 01 Jan 0001 00:00:00 +0000

Combines RAG with agentic patterns using LlamaIndex — covering router queries, tool retrieval, and multi-document agents. This goes beyond basic RAG (query → retrieve → generate) to show how agents can dynamically choose retrieval strategies and combine multiple data sources. Take this after understanding basic RAG concepts from the RAG from Scratch learning path.

Agent SDK — Overview

Mon, 01 Jan 0001 00:00:00 +0000

Introduction to Anthropic’s Agent SDK for building custom AI agents with tool use, MCP, and sub-agents.

Multi AI Agent Systems with crewAI

Mon, 01 Jan 0001 00:00:00 +0000

Hands-on introduction to multi-agent systems using CrewAI — covers role-based agent design, task delegation, inter-agent communication, and workflow orchestration. Taught by Joao Moura (CrewAI founder). The practical companion to the Multi-Agent Systems learning path: the course teaches you to build crews, the path provides comprehensive documentation across 8+ frameworks.

Tool Use — Overview

Mon, 01 Jan 0001 00:00:00 +0000

How Claude calls external tools and functions — the foundation for building agentic systems.

Agent SDK Deep Dive

Mon, 01 Jan 0001 00:00:00 +0000

Build custom AI agents with the Anthropic Agent SDK. Covers both TypeScript and Python SDKs, custom tools, MCP integration, sub-agents, streaming, and production deployment.

Prerequisites: Familiarity with the Claude API (complete Claude API Essentials first).

Multi-Agent Systems

Mon, 01 Jan 0001 00:00:00 +0000

Explore how to build systems with multiple cooperating AI agents. Compare approaches across eight frameworks: Anthropic Agent SDK, OpenAI Agents SDK, CrewAI, LangGraph, Google ADK, Microsoft Agent Framework, AutoGen, and OpenAI Symphony — plus the A2A protocol for cross-platform agent communication.

Each framework embodies a different orchestration paradigm: delegation, handoffs, crews, state machines, workflow agents, enterprise graphs, group chat, and autonomous work management. Understanding the design space helps you pick the right tool for your architecture.

Agents Course

Mon, 01 Jan 0001 00:00:00 +0000

Hugging Face’s comprehensive agents course — covers agent fundamentals, tool use, ReAct pattern, multi-agent systems, and building production agents with open-source models. The open-source counterpart to Anthropic’s agent courses: where Anthropic teaches you to build agents with Claude, Hugging Face teaches you to build agents with any open model. Essential if you’re evaluating open vs. proprietary agent architectures.

Evaluation & Testing

Mon, 01 Jan 0001 00:00:00 +0000

Build a comprehensive evaluation practice for AI applications. This path spans 7 sources to cover the full evaluation landscape: foundational concepts, practical implementation, RAG-specific metrics, LLM-as-judge patterns, and agent evaluation challenges.

Evaluation is the most cross-cutting concern in AI development — every provider and framework has a different take. OpenAI provides hosted evals, RAGAS specializes in RAG metrics, DSPy uses metrics for optimization, LangSmith offers traceability, and W&B Weave treats evaluation as a core development primitive. This path helps you pick the right tools and combine them.

AI Safety & Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Master the techniques for building safe, responsible AI applications across providers. This path covers content moderation, jailbreak defense, hallucination reduction, and guardrail patterns — drawing from 6 different sources to show how each provider approaches safety differently.

Cross-provider comparison is central to this path: OpenAI uses a separate moderation endpoint, Anthropic leverages the main model with prompt design, Mistral has its own categorization, and Cohere offers declarative safety modes. Understanding all approaches lets you build defense-in-depth systems.

AI Use Cases & Business Applications

Mon, 01 Jan 0001 00:00:00 +0000

A practical guide to identifying, evaluating, and prioritizing AI use cases for your product or organization. See concrete examples of AI in production — from customer support to document processing — and learn frameworks for assessing ROI and choosing the right approach.

By the end of this path, you’ll be able to: identify high-value AI use cases in your organization, evaluate whether a use case needs simple AI or complex agents, build an ROI-backed business case for AI investment, and have informed conversations with engineering about implementation feasibility.

Understanding AI Agents & Protocols

Mon, 01 Jan 0001 00:00:00 +0000

A non-technical guide to AI agents and the emerging protocol standards for product leaders and executives. Learn what agents are, why they matter for your product, and how the industry is standardizing agent communication through protocols like MCP, A2A, and AG-UI.

By the end of this path, you’ll understand the difference between chatbots and agents, how agents connect to external tools and data, and what enterprise agent deployment looks like. You’ll be equipped to evaluate whether your product needs agent capabilities and what infrastructure choices your team should be making.

AI Architecture for Technical Leaders

Mon, 01 Jan 0001 00:00:00 +0000

A technically rigorous guide to AI system architecture for product managers and executives who can evaluate architecture diagrams. This path walks through the major architectural decisions in modern AI systems — from the LLM application stack to agent frameworks, communication protocols, and multi-model strategies.

By the end of this path, you’ll be able to: evaluate your engineering team’s architecture proposals with informed questions, understand the protocol landscape (MCP, AG-UI) for platform integration decisions, and assess whether your system architecture is ready for multi-model, multi-agent production workloads.

Implement Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Step-by-step guide to implementing the tool use loop: define tools, handle tool_use responses, send tool_result.

A Data Analyst Agent Built with Cohere and Langchain

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to build a data-analysis system out of Cohere’s models.

A2A endpoint in Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

A2A JSON-RPC

Mon, 01 Jan 0001 00:00:00 +0000

Communicate with an assistant using the Agent-to-Agent (A2A) Protocol over JSON-RPC 2.0.

AbstractAgent

Mon, 01 Jan 0001 00:00:00 +0000

Base agent implementation with core event handling

Access & oversight

Mon, 01 Jan 0001 00:00:00 +0000

Control who can access agents, how they authenticate, and audit everything they do.

Access the W&B MCP Server

Mon, 01 Jan 0001 00:00:00 +0000

Connect your IDE or LLM application to W&B’s Model Context Protocol (MCP) server to provide your agent with access to your W&B workspace, data, and W&B’s documentation.

Add Tools to Agents

Mon, 01 Jan 0001 00:00:00 +0000

Add tool calling capabilities to agents with automatic schema inference from Python functions.

ADK with Agent2Agent (A2A) Protocol

Mon, 01 Jan 0001 00:00:00 +0000

Advanced Document Parsing For Enterprises

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use Cohere’s models to build a document-parsing agent.

Advanced integrations with ChatKit

Mon, 01 Jan 0001 00:00:00 +0000

Use your own server with ChatKit to integrate agent workflows into your product with more customization.

Agent Builder webhooks

Mon, 01 Jan 0001 00:00:00 +0000

Integrate agent publishing with external systems, CI/CD pipelines, or custom deployment workflows.

Agent Capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Understand the five ways to extend CrewAI agents: Tools, MCPs, Apps, Skills, and Knowledge.

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Chat UI

Mon, 01 Jan 0001 00:00:00 +0000

Agent Client Protocol (ACP)

Mon, 01 Jan 0001 00:00:00 +0000

Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs.

Agent Client Protocol (ACP)

Mon, 01 Jan 0001 00:00:00 +0000

Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs.

Agent Config

Mon, 01 Jan 0001 00:00:00 +0000

Agent definitions

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to define an agent’s instructions, model, tools, and local context in the OpenAI Agents SDK.

Agent evals

Mon, 01 Jan 0001 00:00:00 +0000

Use agent evals to create datasets, configure graders, and track evaluation runs for your agents.

Agent Evaluation Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Agent Framework Overview

Mon, 01 Jan 0001 00:00:00 +0000

Introduction to Microsoft Agent Framework: combining AutoGen’s agent abstractions with Semantic Kernel’s enterprise features for production-grade multi-agent orchestration.

Agent Frameworks

Mon, 01 Jan 0001 00:00:00 +0000

Build production-ready AI agents with Fireworks and leading open-source frameworks

Agent identity

Mon, 01 Jan 0001 00:00:00 +0000

Choose whether your Fleet agent authenticates with its own credentials or with each user’s credentials.

Agent Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Using OSS agent frameworks with Together AI

Agent Loop

Mon, 01 Jan 0001 00:00:00 +0000

Agent Repositories

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use Agent Repositories to share and reuse your agents across teams and projects

Agent Runtime

Mon, 01 Jan 0001 00:00:00 +0000

Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

Agent Server API reference for LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Agent Server changelog

Mon, 01 Jan 0001 00:00:00 +0000

Agent Skills

Mon, 01 Jan 0001 00:00:00 +0000

Install Pinecone’s official Agent Skills library for Cursor, GitHub Copilot, Codex, and other agentic IDEs.

Agent Specs

Mon, 01 Jan 0001 00:00:00 +0000

Agent Starter Pack

Mon, 01 Jan 0001 00:00:00 +0000

Agent team

Mon, 01 Jan 0001 00:00:00 +0000

Agent Tracing

Mon, 01 Jan 0001 00:00:00 +0000

Understand where your agent runs and how tracing enables reinforcement fine-tuning

Agent User Interaction (AG-UI)

Mon, 01 Jan 0001 00:00:00 +0000

Agent Workflows

Mon, 01 Jan 0001 00:00:00 +0000

Orchestrating together multiple language model calls to solve complex tasks.

agent-server-openapi

Mon, 01 Jan 0001 00:00:00 +0000

Agent2Agent (A2A)

Mon, 01 Jan 0001 00:00:00 +0000

Agentic IDEs and CLIs

Mon, 01 Jan 0001 00:00:00 +0000

Use Pinecone with agentic IDEs and CLIs like Claude Code, Gemini CLI, Cursor, and more.

Agentic Memory

Mon, 01 Jan 0001 00:00:00 +0000

Persist agent context across runs for better performance and personalization.

Agentic Multi-Stage RAG with Cohere Tools API

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to build a powerful, multi-stage agent with the Cohere platform.

Agentic or Tool use

Mon, 01 Jan 0001 00:00:00 +0000

Agentic RAG for PDFs with mixed data

Mon, 01 Jan 0001 00:00:00 +0000

This page describes building a powerful, multi-step chatbot with Cohere’s models.

Agentic Search

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that iteratively search and refine results to answer complex queries.

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn about agents in the Agent User Interaction Protocol

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Detailed guide on creating and managing agents within the CrewAI framework.

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Configure agent instructions, tools, guardrails, memory, and streaming behavior.

Agents

Mon, 01 Jan 0001 00:00:00 +0000

Agents & Conversations

Mon, 01 Jan 0001 00:00:00 +0000

Agents & Conversations API: Create, manage agents with tools, and handle interactive conversations with persistent history

Agents Function Calling

Mon, 01 Jan 0001 00:00:00 +0000

Agents use tools and function calling to perform tasks, with built-in and customizable options

Agents Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Agents Handoffs enable seamless task delegation and workflow automation between multiple agents with diverse tools and capabilities

Agents Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Introduction to Mistral’s agent system — autonomous task execution with tools, state persistence, connectors (code interpreter, web search), and multi-agent collaboration.

Agents Overview

Mon, 01 Jan 0001 00:00:00 +0000

Core agent abstraction in the Microsoft Agent Framework: agent types, providers, skills, and conversation management.

Agents SDK

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to build agents with the OpenAI Agents SDK.

AgentSubscriber

Mon, 01 Jan 0001 00:00:00 +0000

Event-driven subscriber system for agent lifecycle and event handling

Agno

Mon, 01 Jan 0001 00:00:00 +0000

Trace Agno multi-agent systems with Weave using OpenTelemetry, capturing agent interactions, tool calls, shared memory operations, and multi-modal workflows for comprehensive observability of your AI agent systems.

AI Mind Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘AIMindTool’ is designed to query data sources in natural language.

AI Models for ADK agents

Mon, 01 Jan 0001 00:00:00 +0000

Analysis of Form 10-K/10-Q Using Cohere and RAG

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use Cohere’s large language models to build an agent able to analyze financial forms like a 10-K or a 10-Q.

API Documentation

Mon, 01 Jan 0001 00:00:00 +0000

A local reference to the Agent Server API documentation.

Apify Actors

Mon, 01 Jan 0001 00:00:00 +0000

‘ApifyActorsTool’ lets you call Apify Actors to provide your CrewAI workflows with web scraping, crawling, data extraction, and web automation capabilities.

Apigee AI Gateway

Mon, 01 Jan 0001 00:00:00 +0000

Arize Phoenix

Mon, 01 Jan 0001 00:00:00 +0000

Arize Phoenix integration for CrewAI with OpenTelemetry and OpenInference

Arxiv Paper Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ArxivPaperTool’ searches arXiv for papers matching a query and optionally downloads PDFs.

Asana Integration

Mon, 01 Jan 0001 00:00:00 +0000

Team task and project coordination with Asana integration for CrewAI.

Async subagents

Mon, 01 Jan 0001 00:00:00 +0000

Launch background subagents that run concurrently while the supervisor continues interacting with the user

Async subagents

Mon, 01 Jan 0001 00:00:00 +0000

Launch background subagents that run concurrently while the supervisor continues interacting with the user

Auth-aware tool responses

Mon, 01 Jan 0001 00:00:00 +0000

Format tool responses to trigger OAuth flows and resume execution automatically.

AutoGen

Mon, 01 Jan 0001 00:00:00 +0000

Use Weave to track and monitor AutoGen agents and multi-agent systems

AutoGen Overview

Mon, 01 Jan 0001 00:00:00 +0000

AutoGen is a programming framework for building multi-agent AI systems through conversational agents that collaborate, use tools, and execute code. Now in maintenance mode — see Microsoft Agent Framework.

Automations

Mon, 01 Jan 0001 00:00:00 +0000

Manage, deploy, and monitor your live crews (automations) in one place.

Azure OpenAI Setup

Mon, 01 Jan 0001 00:00:00 +0000

Configure Azure OpenAI with Crew Studio for enterprise LLM connections

Backends

Mon, 01 Jan 0001 00:00:00 +0000

Choose and configure filesystem backends for deep agents. You can specify routes to different backends, implement virtual filesystems, and enforce policies.

Backends

Mon, 01 Jan 0001 00:00:00 +0000

Choose and configure filesystem backends for deep agents. You can specify routes to different backends, implement virtual filesystems, and enforce policies.

Bash Tool

Mon, 01 Jan 0001 00:00:00 +0000

The bash tool gives Claude direct shell access to execute commands, making it one of the most powerful and dangerous built-in tools available. It enables agents to run scripts, install packages, manage files, and interact with system utilities, forming the backbone of coding and DevOps automation workflows. Be deliberate about sandboxing: without proper isolation, Claude can execute arbitrary commands with the permissions of the host process. Start with a restrictive allowlist of commands and expand carefully, and always prefer higher-level tools like the text editor for file modifications where available rather than piping through sed or echo.

Basic usage of tool use (function calling)

Mon, 01 Jan 0001 00:00:00 +0000

Overview of Cohere’s tool use system for building agentic workflows — with native citation support that links tool results back to generated text.

Bedrock Invoke Agent Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows

Bedrock Knowledge Base Retriever

Mon, 01 Jan 0001 00:00:00 +0000

Retrieve information from Amazon Bedrock Knowledge Bases using natural language queries

Best Practices

Mon, 01 Jan 0001 00:00:00 +0000

This guide distills hard-won patterns for building reliable agent skills that perform well across diverse user inputs and edge cases. Pay particular attention to the guidance on error handling within skill execution and how to design tool descriptions that minimize misuse by the model. A common mistake is writing overly generic skill descriptions, which leads Claude to invoke skills in inappropriate contexts and degrades overall agent quality. Start here after completing the skills quickstart to refine your implementations before deploying to production.

Box Integration

Mon, 01 Jan 0001 00:00:00 +0000

File storage and document management with Box integration for CrewAI.

Braintrust

Mon, 01 Jan 0001 00:00:00 +0000

Braintrust integration for CrewAI with OpenTelemetry tracing and evaluation

Brave Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘BraveSearchTool’ is designed to search the internet using the Brave Search API.

Bright Data Tools

Mon, 01 Jan 0001 00:00:00 +0000

Bright Data integrations for SERP search, Web Unlocker scraping, and Dataset API.

Browserbase Web Loader

Mon, 01 Jan 0001 00:00:00 +0000

Browserbase is a developer platform to reliably run, manage, and monitor headless browsers.

Build a content builder agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a content writing agent with brand memory, skills, subagents, and image generation

Build a content builder agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a content writing agent with brand memory, skills, subagents, and image generation

Build a custom RAG agent with LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Build a custom RAG agent with LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

This guide shows how to build a RAG pipeline where the agent decides when and how to retrieve documents, rather than always retrieving on every query. Focus on the routing logic that lets the agent skip retrieval for questions it can answer directly — this is the key difference between naive RAG and agentic RAG. Compare this approach with Pinecone’s retrieval patterns and Cohere’s reranking strategies to see how different parts of the RAG stack complement each other. A common pitfall is over-retrieving: adding too many retrieval nodes or fetching too many documents degrades both latency and answer quality, so tune your retrieval thresholds carefully.

Build a custom SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a data analysis agent

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent that analyzes data files, generates visualizations, and shares results

Build a deep research agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-step web research agent with subagent delegation

Build a deep research agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-step web research agent with subagent delegation

Build a multi-source knowledge base with routing

Mon, 01 Jan 0001 00:00:00 +0000

Build a multi-source knowledge base with routing

Mon, 01 Jan 0001 00:00:00 +0000

This guide demonstrates a router pattern where a top-level agent dispatches queries to specialized sub-agents based on the knowledge domain, which is one of the most practical multi-agent architectures for production systems. The routing mechanism avoids the cost and latency of sending every query to every knowledge source by using an LLM to classify intent first. Focus on how the router prompt is structured and how fallback behavior works when no sub-agent matches, as these are the failure modes you will encounter most in real deployments. Compare this approach with CrewAI’s delegation model and LangGraph’s conditional edges to understand the tradeoffs between explicit routing and emergent coordination.

Build a personal assistant with subagents

Mon, 01 Jan 0001 00:00:00 +0000

Build a personal assistant with subagents

Mon, 01 Jan 0001 00:00:00 +0000

Build a Phone Voice Agent with Together AI

Mon, 01 Jan 0001 00:00:00 +0000

Build a real-time phone voice agent from scratch with Twilio Media Streams, Together AI realtime STT, chat completions, realtime TTS, and local voice activity detection.

Build a RAG agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a RAG agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

This guide assembles LangChain’s retrieval primitives into a complete RAG agent capable of querying external knowledge and synthesizing answers with citations. The key architectural decision covered here is when to use a simple retrieval chain versus a full agentic RAG loop where the model decides whether and how to retrieve. Pay attention to the prompt engineering patterns for grounding LLM responses in retrieved context, as poorly constructed prompts are the primary cause of hallucination in RAG systems. Read the retrieval guide first for the underlying abstractions, then use this guide to see how they combine in a production-oriented pattern.

Build a SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL Agent with Cohere's LLM Platform

Mon, 01 Jan 0001 00:00:00 +0000

This page contains a tutorial on how to build a SQL agent with Cohere’s LLM platform.

Build a SQL assistant with on-demand skills

Mon, 01 Jan 0001 00:00:00 +0000

Build a SQL assistant with on-demand skills

Mon, 01 Jan 0001 00:00:00 +0000

Build a streaming agent

Mon, 01 Jan 0001 00:00:00 +0000

Build A Tool Using Agent

Mon, 01 Jan 0001 00:00:00 +0000

Build a voice agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build a voice agent with LangChain

Mon, 01 Jan 0001 00:00:00 +0000

Build applications

Mon, 01 Jan 0001 00:00:00 +0000

Build agentic applications utilizing compatible event AG-UI event streams

Build clients

Mon, 01 Jan 0001 00:00:00 +0000

Showcase: build a conversational CLI agent from scratch using AG-UI and Mastra

Build Crew

Mon, 01 Jan 0001 00:00:00 +0000

A Crew is a group of agents that work together to complete a task.

Build customer support with handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Build customer support with handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Build with Agent Skills

Mon, 01 Jan 0001 00:00:00 +0000

Use agent skills to guide AI coding assistants through MCP server design and implementation

Build your agent with ADK

Mon, 01 Jan 0001 00:00:00 +0000

Build Your First Crew

Mon, 01 Jan 0001 00:00:00 +0000

Step-by-step tutorial to create a collaborative AI team that works together to solve complex problems.

Build Your First Flow

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to create structured, event-driven workflows with precise control over execution.

Building a Generative AI Agent with Cohere

Mon, 01 Jan 0001 00:00:00 +0000

This page describes building a generative-AI powered agent with Cohere.

Building Agentic RAG with Cohere

Mon, 01 Jan 0001 00:00:00 +0000

Hands-on tutorials on building agentic RAG applications with Cohere

Building AI Agents with DSPy

Mon, 01 Jan 0001 00:00:00 +0000

Building An AI Data Analyst

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use code interpreter to build an AI data analyst with E2B and Together AI.

Building an LLM Agent with the Cohere API

Mon, 01 Jan 0001 00:00:00 +0000

This page how to use Cohere’s API to build an LLM-based agent.

Building RAG as Agent

Mon, 01 Jan 0001 00:00:00 +0000

Calendar Agent with Native Multi Step Tool

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use cohere Chat API with list_calendar_events and create_calendar_event tools to book appointments.

Call agents from code

Mon, 01 Jan 0001 00:00:00 +0000

Invoke Agent Builder agents from Python, JavaScript, or any language through the REST API.

Call agents from code

Mon, 01 Jan 0001 00:00:00 +0000

Invoke Fleet agents from Python, JavaScript, or any language through the REST API.

Callbacks: Observe, Customize, and Control Agent Behavior

Mon, 01 Jan 0001 00:00:00 +0000

Cancel Run

Mon, 01 Jan 0001 00:00:00 +0000

Cancel Runs

Mon, 01 Jan 0001 00:00:00 +0000

Cancel one or more runs. Can cancel runs by thread ID and run IDs, or by status filter.

Capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Dynamic capability discovery for agents in the AG-UI protocol

Channels

Mon, 01 Jan 0001 00:00:00 +0000

Configure channels to trigger your Fleet agents automatically.

Citations and References

Mon, 01 Jan 0001 00:00:00 +0000

Citations and references enable models to ground responses with sources, ideal for RAG and agentic applications

Claude

Mon, 01 Jan 0001 00:00:00 +0000

Claude Agent SDK

Mon, 01 Jan 0001 00:00:00 +0000

Use W&B Weave with the Claude Agent SDK to trace your agent’s queries, tool calls, and multi-turn conversations.

Claude Api Skill

Mon, 01 Jan 0001 00:00:00 +0000

Claude Code Features

Mon, 01 Jan 0001 00:00:00 +0000

Claude Code overview

Mon, 01 Jan 0001 00:00:00 +0000

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.

CLI

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use the CrewAI CLI to interact with CrewAI.

ClickUp Integration

Mon, 01 Jan 0001 00:00:00 +0000

Task and productivity management with ClickUp integration for CrewAI.

Cline with W&B Inference

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure the Cline coding agent to use W&B Inference.

Code Docs RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CodeDocsSearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within code documentation.

Code Execution

Mon, 01 Jan 0001 00:00:00 +0000

Sandboxed code execution in AutoGen: Docker-based and local executors for running agent-generated code safely.

Code Execution Tool

Mon, 01 Jan 0001 00:00:00 +0000

The code execution tool lets Claude run Python code in a sandboxed environment during a conversation, enabling data analysis, mathematical computation, and rapid prototyping without requiring external infrastructure. This is particularly valuable for tasks where Claude needs to verify its own reasoning through computation rather than relying on mental arithmetic or approximation. Note that the sandbox has limited package availability and no network access, so complex data science workflows may hit dependency walls. Use this tool when you need deterministic computation results embedded directly in Claude’s response rather than asking the user to run code separately.

Code generation

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use OpenAI Codex models to generate code and build coding agents.

Code Interpreter

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CodeInterpreterTool’ is a powerful tool designed for executing Python 3 code within a secure, isolated environment.

Code Interpreter

Mon, 01 Jan 0001 00:00:00 +0000

Code Interpreter enables safe, on-demand code execution for data analysis, graphing, and more in isolated containers

Code Review

Mon, 01 Jan 0001 00:00:00 +0000

Set up automated PR reviews that catch logic errors, security vulnerabilities, and regressions using multi-agent analysis of your full codebase

Coding

Mon, 01 Jan 0001 00:00:00 +0000

Mistral AI offers Codestral for code generation & FIM, and Devstral for agentic tool use in software development, with integrations for IDEs and frameworks

Coding Agent Skills

Mon, 01 Jan 0001 00:00:00 +0000

Coding Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to enable your CrewAI Agents to write and execute code, and explore advanced features for enhanced functionality.

Coding Tools

Mon, 01 Jan 0001 00:00:00 +0000

Use AGENTS.md to guide coding agents and IDEs across your CrewAI projects.

Cohere Cookbooks: Build AI Agents and Solutions

Mon, 01 Jan 0001 00:00:00 +0000

Get started with Cohere’s cookbooks to build agents, QA bots, perform searches, and more, all organized by category.

Cohere's Command A Reasoning Model

Mon, 01 Jan 0001 00:00:00 +0000

Command A Reasoning excels in tool use, agentic workflows, and complex problem-solving. It has 111 billion parameters and a 256k context length.

Cohere's Command R7B Model

Mon, 01 Jan 0001 00:00:00 +0000

Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused large language models. It excels at RAG, tool use, and agents.

Collaboration

Mon, 01 Jan 0001 00:00:00 +0000

How to enable agents to work together, delegate tasks, and communicate effectively within CrewAI teams.

Collaborative agents

Mon, 01 Jan 0001 00:00:00 +0000

Command A

Mon, 01 Jan 0001 00:00:00 +0000

Command A is a performant mode good at tool use, RAG, agents, and multilingual use cases. It has 111 billion parameters and a 256k context length.

Comparison with OpenCode and Claude Agent SDK

Mon, 01 Jan 0001 00:00:00 +0000

Compare LangChain Deep Agents with OpenCode and Claude Agent SDK to choose the right tool for your use case

Comparison with OpenCode and Claude Agent SDK

Mon, 01 Jan 0001 00:00:00 +0000

Compare LangChain Deep Agents with OpenCode and Claude Agent SDK to choose the right tool for your use case

Composio Tool

Mon, 01 Jan 0001 00:00:00 +0000

Composio provides 250+ production-ready tools for AI agents with flexible authentication management.

Computer use

Mon, 01 Jan 0001 00:00:00 +0000

Enable models to interact with computer interfaces — clicking, typing, and navigating applications via screenshots, creating agents that can operate any software.

Computer Use Tool

Mon, 01 Jan 0001 00:00:00 +0000

Computer use enables Claude to interact with desktop environments through screenshots, mouse clicks, and keyboard input, effectively giving it the ability to operate any GUI application. This opens up automation for legacy software, web applications behind authentication, and workflows that lack APIs. Be aware that computer use is significantly slower and less reliable than API-based tool calling – treat it as a last resort for tasks that genuinely have no programmatic interface. Start with constrained screen regions and simple click-type sequences before attempting complex multi-window workflows, and always implement human-in-the-loop checkpoints for destructive actions.

Conditional Tasks

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use conditional tasks in a crewAI kickoff

Configuration

Mon, 01 Jan 0001 00:00:00 +0000

Configure the Deep Agents CLI with config.toml, hooks, and MCP servers

Configuration

Mon, 01 Jan 0001 00:00:00 +0000

Tune model selection, retry logic, rate limits, and runner policies for production workloads.

Configure checkpointer backend

Mon, 01 Jan 0001 00:00:00 +0000

Configure Agent Server to use PostgreSQL, MongoDB, or a custom implementation for checkpoint storage.

Configure LangSmith Agent Server for scale

Mon, 01 Jan 0001 00:00:00 +0000

Connect to any LLM

Mon, 01 Jan 0001 00:00:00 +0000

Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs) using LiteLLM, including supported providers and configuration options.

Connecting to Multiple MCP Servers

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use MCPServerAdapter in CrewAI to connect to multiple MCP servers simultaneously and aggregate their tools.

Connectors Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connectors enable Agents and users to access tools like websearch, code interpreter, image generation, and document library on demand

Context engineering in agents

Mon, 01 Jan 0001 00:00:00 +0000

Context engineering in agents

Mon, 01 Jan 0001 00:00:00 +0000

Context engineering in Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Control what context your deep agent has access to and how it is managed across long-running tasks

Context engineering in Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Control what context your deep agent has access to and how it is managed across long-running tasks

Context strategies

Mon, 01 Jan 0001 00:00:00 +0000

Control what past messages, attachments, and tool runs are injected into prompts.

Contributing

Mon, 01 Jan 0001 00:00:00 +0000

How to participate in Agent User Interaction Protocol development

ConversableAgent

Mon, 01 Jan 0001 00:00:00 +0000

The ConversableAgent base class: configurable with system messages, LLM models, tool registrations, and code execution capabilities.

Copy Thread

Mon, 01 Jan 0001 00:00:00 +0000

Create a new thread with a copy of the state and checkpoints from an existing thread.

Core architecture

Mon, 01 Jan 0001 00:00:00 +0000

Understand how AG-UI connects front-end applications to AI agents

Core capabilities overview

Mon, 01 Jan 0001 00:00:00 +0000

Overview of Agent Server core capabilities including streaming, human-in-the-loop, MCP, A2A, distributed tracing, webhooks, and double-texting.

Cost Tracking

Mon, 01 Jan 0001 00:00:00 +0000

Cost tracking in agentic workflows is substantially more complex than single-call API usage because agents make multiple model calls, tool invocations, and potentially spawn sub-agents — all of which accumulate tokens. This guide shows how to instrument the Agent SDK to capture per-turn and per-agent cost breakdowns. Focus on the callback hooks that expose token counts at each step, as these are the foundation for building budget limits and alerting. Without proactive cost tracking, a single runaway agent loop can consume your entire API budget in minutes, making this essential reading before any production deployment.

Count Assistants

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of assistants matching the specified criteria.

Count Crons

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of crons matching the specified criteria.

Count Threads

Mon, 01 Jan 0001 00:00:00 +0000

Get the count of threads matching the specified criteria.

Crafting Effective Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn best practices for designing powerful, specialized AI agents that collaborate effectively to solve complex problems.

Create Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Create an assistant.

Create Background Run

Mon, 01 Jan 0001 00:00:00 +0000

Create a run and return the run ID immediately. Don’t wait for the final run output.

Create Background Run

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread, return the run ID immediately. Don’t wait for the final run output.

Create Cron

Mon, 01 Jan 0001 00:00:00 +0000

Create a cron to schedule runs on new threads.

Create custom subagents

Mon, 01 Jan 0001 00:00:00 +0000

Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.

Create Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

Comprehensive guide on crafting, using, and managing custom tools within the CrewAI framework, including new functionalities and error handling.

Create plugins

Mon, 01 Jan 0001 00:00:00 +0000

Create custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers.

Create Run Batch

Mon, 01 Jan 0001 00:00:00 +0000

Create a batch of runs and return immediately.

Create Run, Stream Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run and stream the output.

Create Run, Stream Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread. Stream the output.

Create Run, Wait for Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run, wait for the final output and then return it.

Create Run, Wait for Output

Mon, 01 Jan 0001 00:00:00 +0000

Create a run in existing thread. Wait for the final output and then return it.

Create Thread

Mon, 01 Jan 0001 00:00:00 +0000

Create a thread.

Create Thread Cron

Mon, 01 Jan 0001 00:00:00 +0000

Create a cron to schedule runs on a thread.

Crew Studio

Mon, 01 Jan 0001 00:00:00 +0000

Build new automations with AI assistance, a visual editor, and integrated testing.

CrewAI

Mon, 01 Jan 0001 00:00:00 +0000

Using CrewAI with Together

CrewAI

Mon, 01 Jan 0001 00:00:00 +0000

Integrate CrewAI with Weave for monitoring and tracing multi-agent applications

CrewAI AMP

Mon, 01 Jan 0001 00:00:00 +0000

Deploy, monitor, and scale your AI agent workflows

CrewAI Cookbooks

Mon, 01 Jan 0001 00:00:00 +0000

Feature-focused quickstarts and notebooks for learning patterns fast.

CrewAI Documentation

Mon, 01 Jan 0001 00:00:00 +0000

Build collaborative AI agents, crews, and flows — production ready from day one.

CrewAI Examples

Mon, 01 Jan 0001 00:00:00 +0000

Explore curated examples organized by Crews, Flows, Integrations, and Notebooks.

CrewAI Run Automation Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to invoke CrewAI Platform automations and leverage external crew services within your workflows.

CrewAI Tracing

Mon, 01 Jan 0001 00:00:00 +0000

Built-in tracing for CrewAI Crews and Flows with the CrewAI AMP platform

CrewGPT

Mon, 01 Jan 0001 00:00:00 +0000

Crews

Mon, 01 Jan 0001 00:00:00 +0000

Understanding and utilizing crews in the crewAI framework with comprehensive attributes and functionalities.

CSV RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘CSVSearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a CSV file’s content.

Custom agents

Mon, 01 Jan 0001 00:00:00 +0000

Custom LLM Implementation

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to create custom LLM implementations in CrewAI.

Custom Manager Agent

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to set a custom agent as the manager in CrewAI, providing more control over task management and coordination.

Custom MCP Servers

Mon, 01 Jan 0001 00:00:00 +0000

Connect your own MCP servers to CrewAI AMP with public access, API key authentication, or OAuth 2.0

Custom model providers

Mon, 01 Jan 0001 00:00:00 +0000

Configure any LangChain-compatible model provider for the Deep Agents CLI

Custom model providers

Mon, 01 Jan 0001 00:00:00 +0000

Configure any LangChain-compatible model provider for the Deep Agents CLI

Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

Custom tools are how you give your agent the ability to take actions beyond conversation – calling APIs, querying databases, executing code, or interacting with any external system. Focus on how the tool’s JSON schema definition directly affects the model’s ability to invoke it correctly; poorly described parameters are the most common source of tool invocation failures. Pay special attention to error handling within tool implementations, since unhandled exceptions will surface as opaque failures in the agentic loop. If your tools need to call external MCP servers instead, read the MCP integration guide as an alternative approach.

Custom workflow

Mon, 01 Jan 0001 00:00:00 +0000

Custom workflow

Mon, 01 Jan 0001 00:00:00 +0000

Customer Support Chat

Mon, 01 Jan 0001 00:00:00 +0000

Building an AI-powered customer support chatbot with Claude, including architecture patterns and quality safeguards.

Customize Agents

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to tailoring agents for specific roles, tasks, and advanced customizations within the CrewAI framework.

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

Customize Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to customize deep agents with system prompts, tools, subagents, and more

Customizing Prompts

Mon, 01 Jan 0001 00:00:00 +0000

Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.

DALL-E Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DallETool’ is a powerful tool designed for generating images from textual descriptions.

Databricks SQL Query Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DatabricksQueryTool’ executes SQL queries against Databricks workspace tables.

Datadog Integration

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate Datadog with CrewAI to submit LLM Observability traces to Datadog.

Debugging

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to debugging Agent User Interaction Protocol (AG-UI) integrations

Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Deep Agents

Mon, 01 Jan 0001 00:00:00 +0000

Deep Agents CLI

Mon, 01 Jan 0001 00:00:00 +0000

Terminal coding agent built on the Deep Agents SDK

Deep Agents CLI

Mon, 01 Jan 0001 00:00:00 +0000

Terminal coding agent built on the Deep Agents SDK

Deep Agents overview

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that can plan, use subagents, and leverage file systems for complex tasks

Deep Agents overview

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that can plan, use subagents, and leverage file systems for complex tasks

Deep research

Mon, 01 Jan 0001 00:00:00 +0000

Use deep research models for autonomous multi-step research tasks — the model browses the web, synthesizes information, and produces comprehensive reports.

Define Tools

Mon, 01 Jan 0001 00:00:00 +0000

Delete an item.

Mon, 01 Jan 0001 00:00:00 +0000

Delete Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Delete an assistant by ID.

Delete Cron

Mon, 01 Jan 0001 00:00:00 +0000

Delete a cron by ID.

Delete Run

Mon, 01 Jan 0001 00:00:00 +0000

Delete a run by ID.

Delete Thread

Mon, 01 Jan 0001 00:00:00 +0000

Delete a thread by ID.

Deploy to AMP

Mon, 01 Jan 0001 00:00:00 +0000

Deploy your Crew or Flow to CrewAI AMP

Deploy to Vertex AI Agent Engine

Mon, 01 Jan 0001 00:00:00 +0000

Deploying Your Agent

Mon, 01 Jan 0001 00:00:00 +0000

Development

Mon, 01 Jan 0001 00:00:00 +0000

Development

Mon, 01 Jan 0001 00:00:00 +0000

Directory RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DirectorySearchTool’ is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within a directory’s content.

Directory Read

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DirectoryReadTool’ is a powerful utility designed to provide a comprehensive listing of directory contents.

Discover and install prebuilt plugins through marketplaces

Mon, 01 Jan 0001 00:00:00 +0000

Find and install plugins from marketplaces to extend Claude Code with new commands, agents, and capabilities.

Discover errors and usage patterns with the Insights Agent

Mon, 01 Jan 0001 00:00:00 +0000

Distributed tracing with Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

Unify traces when calling your deployed Agent Server from another service using RemoteGraph or the SDK.

Document Library

Mon, 01 Jan 0001 00:00:00 +0000

Document Library enhances agents with uploaded documents via Mistral Cloud’s built-in RAG tool

DOCX RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘DOCXSearchTool’ is a RAG tool designed for semantic searching within DOCX documents.

Enable Crew Studio

Mon, 01 Jan 0001 00:00:00 +0000

Enabling Crew Studio on CrewAI AMP

Enterprise

Mon, 01 Jan 0001 00:00:00 +0000

The enterprise skills guide addresses deployment concerns that only surface at organizational scale: access control, audit logging, skill versioning, and multi-tenant isolation. Focus on the permission model and how skill execution contexts are sandboxed — getting this wrong can expose one tenant’s data to another. A key pitfall is treating enterprise skill deployment as a simple extension of single-user patterns; the authentication and authorization layers add meaningful complexity to the skill lifecycle. Read this after the quickstart and best practices guides, as it assumes familiarity with core skill mechanics.

enterprise-api.base

Mon, 01 Jan 0001 00:00:00 +0000

enterprise-api.en

Mon, 01 Jan 0001 00:00:00 +0000

enterprise-api.ko

Mon, 01 Jan 0001 00:00:00 +0000

enterprise-api.pt-BR

Mon, 01 Jan 0001 00:00:00 +0000

Essentials

Mon, 01 Jan 0001 00:00:00 +0000

Agent Builder’s core features

Evals

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate agent trajectories using deterministic matching or LLM-as-judge evaluators with AgentEvals and LangSmith.

Evals

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate agent trajectories using deterministic matching or LLM-as-judge evaluators with AgentEvals and LangSmith.

Evals In Prod

Mon, 01 Jan 0001 00:00:00 +0000

Evals In Prod

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate a complex agent

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate a Text-to-SQL Agent

Mon, 01 Jan 0001 00:00:00 +0000

Evaluate an AI Agent

Mon, 01 Jan 0001 00:00:00 +0000

Evaluating Use Cases for CrewAI

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to assess your AI application needs and choose the right approach between Crews and Flows based on complexity and precision requirements.

Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

Event Listeners

Mon, 01 Jan 0001 00:00:00 +0000

Tap into CrewAI events to build custom integrations and monitoring

Events

Mon, 01 Jan 0001 00:00:00 +0000

Understanding events in the Agent User Interaction Protocol

Events

Mon, 01 Jan 0001 00:00:00 +0000

Documentation for the events used in the Agent User Interaction Protocol SDK

Events

Mon, 01 Jan 0001 00:00:00 +0000

Documentation for the events used in the Agent User Interaction Protocol Python SDK

EXA Search Web Loader

Mon, 01 Jan 0001 00:00:00 +0000

The ‘EXASearchTool’ is designed to perform a semantic search for a specified query from a text’s content across the internet.

Example Gallery

Mon, 01 Jan 0001 00:00:00 +0000

Task-oriented examples that demonstrate agent loops, tool usage, guardrails, and integration patterns.

Execution Hooks Overview

Mon, 01 Jan 0001 00:00:00 +0000

Understanding and using execution hooks in CrewAI for fine-grained control over agent operations

Explore the .claude directory

Mon, 01 Jan 0001 00:00:00 +0000

Where Claude Code reads CLAUDE.md, settings.json, hooks, skills, commands, subagents, rules, and auto memory. Explore the .claude directory in your project and ~/.claude in your home directory.

Extend Claude Code

Mon, 01 Jan 0001 00:00:00 +0000

Understand when to use CLAUDE.md, Skills, subagents, hooks, MCP, and plugins.

FAQs

Mon, 01 Jan 0001 00:00:00 +0000

Frequently asked questions about CrewAI AMP

File Checkpointing

Mon, 01 Jan 0001 00:00:00 +0000

File Read

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FileReadTool’ is designed to read files from the local file system.

File Write

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FileWriterTool’ is designed to write content to files.

Files

Mon, 01 Jan 0001 00:00:00 +0000

Pass images, PDFs, audio, video, and text files to your agents for multimodal processing.

Financial CSV Agent with Langchain

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use Cohere’s models to build an agent able to work with CSV data.

Financial CSV Agent with Native Multi-Step Cohere API

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to use Cohere’s models and its native API to build an agent able to work with CSV data.

Fine Grained Tool Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Fine-grained tool streaming gives you granular control over how tool call arguments and results are delivered incrementally, which is essential for building responsive UIs on top of agentic workflows. Focus on the event types and their ordering — understanding the difference between input_json delta events and tool_result blocks determines how you parse partial tool invocations. One subtle pitfall is assuming tool arguments arrive as valid JSON at each delta; you need to buffer and parse only after the tool use block is complete. Read this after the general streaming guide to layer tool-specific streaming behavior on top of basic SSE handling.

Finetuning Agents

Mon, 01 Jan 0001 00:00:00 +0000

Fingerprinting

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use CrewAI’s fingerprinting system to uniquely identify and track components throughout their lifecycle.

Fire Pass Setup

Mon, 01 Jan 0001 00:00:00 +0000

Kimi K2.6 Turbo for personal agentic coding — Fire Pass (Early Access), $49 / month

Firecrawl Crawl Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FirecrawlCrawlWebsiteTool’ is designed to crawl and convert websites into clean markdown or structured data.

Firecrawl Scrape Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘FirecrawlScrapeWebsiteTool’ is designed to scrape websites and convert them into clean markdown or structured data.

Fireworks Agent Overview

Mon, 01 Jan 0001 00:00:00 +0000

Describe what you want, approve the plan and cost, get a deployed fine-tuned model.

Fireworks Agent: Classification

Mon, 01 Jan 0001 00:00:00 +0000

Benchmark base models, fine-tune on labeled data, and pick the best classifier — automatically.

Fireworks Agent: Evaluator Authoring

Mon, 01 Jan 0001 00:00:00 +0000

Have Fireworks Agent generate a reusable evaluator from your dataset — for scoring candidates in an SFT sweep, or for use with Managed RFT.

Fireworks Agent: Preference Learning (DPO/ORPO)

Mon, 01 Jan 0001 00:00:00 +0000

Run preference fine-tuning end-to-end with optional base-model sweep, automatic pair generation, and pairwise evaluation.

Fireworks Agent: Supervised Fine-Tuning

Mon, 01 Jan 0001 00:00:00 +0000

Run end-to-end SFT with Fireworks Agent — dataset inspection, hyperparameter sweep, evaluator-guided selection, and a deployed winner.

Fleet webhooks

Mon, 01 Jan 0001 00:00:00 +0000

Integrate agent publishing with external systems, CI/CD pipelines, or custom deployment workflows.

Flow HITL Management

Mon, 01 Jan 0001 00:00:00 +0000

Enterprise-grade human review for Flows with email-first notifications, routing rules, and auto-response capabilities

Flows

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to create and manage AI workflows using CrewAI Flows.

Force Tool Output as Result

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to force tool output as the result in an Agent’s task in CrewAI.

Frameworks, runtimes, and harnesses

Mon, 01 Jan 0001 00:00:00 +0000

Understand the differences between LangChain, LangGraph, and Deep Agents and when to use each one

Frameworks, runtimes, and harnesses

Mon, 01 Jan 0001 00:00:00 +0000

Understand the differences between LangChain, LangGraph, and Deep Agents and when to use each one

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build React UIs that display real-time subagent streams from deep agents

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents, LangGraph graphs, and custom APIs

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build React UIs that display real-time subagent streams from deep agents

Frontend

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents, LangGraph graphs, and custom APIs

Function calling

Mon, 01 Jan 0001 00:00:00 +0000

Function calling with Mistral models — integrate external tools for dynamic, data-driven responses using JSON Schema tool definitions.

Galileo

Mon, 01 Jan 0001 00:00:00 +0000

Galileo integration for CrewAI tracing and evaluation

Gemini

Mon, 01 Jan 0001 00:00:00 +0000

Gemma

Mon, 01 Jan 0001 00:00:00 +0000

Generate Parallel Queries for Better RAG Retrieval

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that can expand a user query into a more optimized set of queries for retrieval.

Get Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Graph

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Schemas

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant by ID.

Get Assistant Subgraphs

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant’s subgraphs.

Get Assistant Subgraphs by Namespace

Mon, 01 Jan 0001 00:00:00 +0000

Get an assistant’s subgraphs filtered by namespace.

Get Assistant Versions

Mon, 01 Jan 0001 00:00:00 +0000

Get all versions of an assistant.

Get Run

Mon, 01 Jan 0001 00:00:00 +0000

Get a run by ID.

Get Thread

Mon, 01 Jan 0001 00:00:00 +0000

Get a thread by ID.

Get Thread History

Mon, 01 Jan 0001 00:00:00 +0000

Get all past states for a thread.

Get Thread History Post

Mon, 01 Jan 0001 00:00:00 +0000

Get all past states for a thread.

Get Thread State

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread.

Get Thread State At Checkpoint

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread at a specific checkpoint.

Get Thread State At Checkpoint

Mon, 01 Jan 0001 00:00:00 +0000

Get state for a thread at a specific checkpoint.

Getting Started Agents

Mon, 01 Jan 0001 00:00:00 +0000

GitHub Integration

Mon, 01 Jan 0001 00:00:00 +0000

Repository and issue management with GitHub integration for CrewAI.

Github Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘GithubSearchTool’ is designed to search websites and convert them into clean markdown or structured data.

GLM-5 Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

How to get the most out of GLM-5 for reasoning and agentic tasks.

Gmail Integration

Mon, 01 Jan 0001 00:00:00 +0000

Email and contact management with Gmail integration for CrewAI.

Gmail Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Trigger automations when Gmail events occur (e.g., new emails, labels).

Going to production

Mon, 01 Jan 0001 00:00:00 +0000

Take your Deep Agent to production with persistent memory, sandboxes, resilience middleware, and deployment options

Going to production

Mon, 01 Jan 0001 00:00:00 +0000

Take your Deep Agent to production with persistent memory, sandboxes, resilience middleware, and deployment options

Google Agent Development Kit (ADK)

Mon, 01 Jan 0001 00:00:00 +0000

Trace Google Agent Development Kit (ADK) agent and tool calls in Weave using OpenTelemetry

Google Calendar Integration

Mon, 01 Jan 0001 00:00:00 +0000

Event and schedule management with Google Calendar integration for CrewAI.

Google Calendar Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Kick off crews when Google Calendar events are created, updated, or cancelled

Google Contacts Integration

Mon, 01 Jan 0001 00:00:00 +0000

Contact and directory management with Google Contacts integration for CrewAI.

Google Docs Integration

Mon, 01 Jan 0001 00:00:00 +0000

Document creation and editing with Google Docs integration for CrewAI.

Google Drive Integration

Mon, 01 Jan 0001 00:00:00 +0000

File storage and management with Google Drive integration for CrewAI.

Google Drive Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Respond to Google Drive file events with automated crews

Google Serper Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerperDevTool’ is designed to search the internet and return the most relevant results.

Google Sheets Integration

Mon, 01 Jan 0001 00:00:00 +0000

Spreadsheet data synchronization with Google Sheets integration for CrewAI.

Google Slides Integration

Mon, 01 Jan 0001 00:00:00 +0000

Presentation creation and management with Google Slides integration for CrewAI.

Graph-based agent workflows

Mon, 01 Jan 0001 00:00:00 +0000

Grounding agents with data

Mon, 01 Jan 0001 00:00:00 +0000

GroupChat Pattern

Mon, 01 Jan 0001 00:00:00 +0000

AutoGen’s GroupChat coordinates multiple agents through managed conversation turns with configurable speaker selection strategies (round-robin, LLM-driven, or custom).

Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Implement safety checks and content filtering for your agents

Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Implement safety checks and content filtering for your agents

Guardrails

Mon, 01 Jan 0001 00:00:00 +0000

Define validators that run alongside the agent loop to enforce business and safety rules.

Guardrails and human review

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use guardrails and human review in the OpenAI Agents SDK for safer, more controlled workflows.

Guides Ai Agent Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

Guides Ai Agent Evaluation Metrics

Mon, 01 Jan 0001 00:00:00 +0000

Guides Tracing Ai Agents

Mon, 01 Jan 0001 00:00:00 +0000

Hallucination Guardrail

Mon, 01 Jan 0001 00:00:00 +0000

Prevent and detect AI hallucinations in your CrewAI tasks

Handle Tool Calls

Mon, 01 Jan 0001 00:00:00 +0000

Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

LangChain’s handoff mechanism lets you transfer execution between agents in a multi-agent graph, and it is worth comparing directly with OpenAI’s Agents SDK handoffs, which use explicit handoff objects rather than graph edges. Focus on how handoffs in LangChain are implemented as special tool calls that the framework intercepts to reroute execution — understanding this internal mechanism helps you debug cases where handoffs silently fail. Read the “Thinking in LangGraph” doc first, because handoffs only make sense once you understand LangGraph’s state machine model. Be mindful that handoff state serialization can be a source of subtle bugs when agents pass complex objects between each other.

Handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Delegate tasks between agents with intent classification, argument passing, and return values.

Harness capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Harness capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Health Check

Mon, 01 Jan 0001 00:00:00 +0000

Check the health status of the server. Optionally check database connectivity.

Hierarchical Process

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to understanding and applying the hierarchical process within your CrewAI projects, updated to reflect the latest coding practices and functionalities.

HITL Workflows

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to implement Human-In-The-Loop workflows in CrewAI for enhanced decision-making

Hooks

Mon, 01 Jan 0001 00:00:00 +0000

Hooks function similarly to middleware in web frameworks, giving you interception points at key stages of the agent’s lifecycle such as before and after tool calls, at the start and end of turns, and during error handling. This is where you implement cross-cutting concerns like logging, metrics, guardrails, and input/output validation without cluttering your core agent logic. A common pitfall is adding too much latency in hook functions, especially in before-tool hooks, which compounds across multi-step agent runs. Read this after you are comfortable with the basic agent loop and custom tools, as hooks are most useful once you understand what you need to observe or control.

Host Your Agent

Mon, 01 Jan 0001 00:00:00 +0000

Deploy agents to Azure Functions, custom hosts, or local environments.

Hosting

Mon, 01 Jan 0001 00:00:00 +0000

This guide covers the infrastructure considerations for running agents in production, including containerization, scaling, and managing long-running agent sessions. A key challenge with hosting agents compared to traditional APIs is that agent runs can take tens of seconds or even minutes due to multi-step tool use, which affects timeout configuration, connection pooling, and load balancer settings. Focus on the recommendations for stateless vs. stateful deployments, as this choice impacts how you handle conversation persistence and recovery from failures. Read this after the secure deployment guide, since security constraints will inform your hosting architecture decisions.

How Claude Code works

Mon, 01 Jan 0001 00:00:00 +0000

Understand the agentic loop, built-in tools, and how Claude Code interacts with your project.

How to add semantic search to your agent deployment

Mon, 01 Jan 0001 00:00:00 +0000

How to Build Coding Agents

Mon, 01 Jan 0001 00:00:00 +0000

How to build your own simple code editing agent from scratch in 400 lines of code!

How to collect user feedback for Agent Server runs

Mon, 01 Jan 0001 00:00:00 +0000

How to evaluate your agent with trajectory evaluations

Mon, 01 Jan 0001 00:00:00 +0000

How to run multiple agents on the same thread

Mon, 01 Jan 0001 00:00:00 +0000

How to use a custom checkpointer

Mon, 01 Jan 0001 00:00:00 +0000

Replace the built-in Postgres checkpointer with a custom BaseCheckpointSaver implementation in your agent deployment.

How to use a custom store

Mon, 01 Jan 0001 00:00:00 +0000

Replace the built-in Postgres store with a custom BaseStore implementation in your agent deployment.

How to use Cline with DeepSeek V3 to build faster

Mon, 01 Jan 0001 00:00:00 +0000

Use Cline (an AI coding agent) with DeepSeek V3 (a powerful open source model) to code faster.

How to use OpenCode with Together AI to build faster

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to combine OpenCode, a powerful terminal-based AI coding agent, with Together AI models like DeepSeek V3 to supercharge your development workflow.

How Tool Use Works

Mon, 01 Jan 0001 00:00:00 +0000

HttpAgent

Mon, 01 Jan 0001 00:00:00 +0000

HTTP-based agent for connecting to remote AI agents

HubSpot Integration

Mon, 01 Jan 0001 00:00:00 +0000

Manage companies and contacts in HubSpot with CrewAI.

HubSpot Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Trigger CrewAI crews directly from HubSpot Workflows

Human Feedback in Flows

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate human feedback directly into your CrewAI Flows using the @human_feedback decorator

Human Input on Execution

Mon, 01 Jan 0001 00:00:00 +0000

Integrating CrewAI with human input during execution in complex decision-making processes and leveraging the full capabilities of the agent’s attributes and tools.

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure human approval for sensitive tool operations

Human-in-the-loop

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to configure human approval for sensitive tool operations

Human-in-the-Loop (HITL) Workflows

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to implement Human-in-the-Loop workflows in CrewAI for enhanced decision-making

Hyperbrowser Load Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘HyperbrowserLoadTool’ enables web scraping and crawling using Hyperbrowser.

Image Generation

Mon, 01 Jan 0001 00:00:00 +0000

Built-in tool for agents to generate images on demand with detailed output handling and download options

Image Generation with DALL-E

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use DALL-E for AI-powered image generation in your CrewAI projects

Improvement

Mon, 01 Jan 0001 00:00:00 +0000

Improvement

Mon, 01 Jan 0001 00:00:00 +0000

Installation

Mon, 01 Jan 0001 00:00:00 +0000

Get started with CrewAI - Install, configure, and build your first AI crew

Integrate Slack with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect the LangSmith Agent Builder to your Slack workspace to let your agents communicate with users in Slack.

Integrate Slack with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect LangSmith Fleet to your Slack workspace to let your agents communicate with users in Slack.

Integrate Teams with an agent

Mon, 01 Jan 0001 00:00:00 +0000

Connect LangSmith Fleet to Microsoft Teams by bringing your own Azure Bot to let agents communicate with users in Teams.

Integration testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agents with real LLM APIs by organizing tests, managing keys, handling flakiness, and controlling costs.

Integration testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agents with real LLM APIs by organizing tests, managing keys, handling flakiness, and controlling costs.

Integrations and observability

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate MCP into Agents SDK workflows and how to trace and debug runs.

Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Build AI agent teams that work together to tackle complex tasks

Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Introduction

Mon, 01 Jan 0001 00:00:00 +0000

Japanese documentation

Mon, 01 Jan 0001 00:00:00 +0000

Localized overview and quickstart for Japanese-speaking developers.

Jira Integration

Mon, 01 Jan 0001 00:00:00 +0000

Issue tracking and project management with Jira integration for CrewAI.

Join & rejoin streams

Mon, 01 Jan 0001 00:00:00 +0000

Disconnect from and reconnect to running agent streams

Join & rejoin streams

Mon, 01 Jan 0001 00:00:00 +0000

Disconnect from and reconnect to running agent streams

Join Run

Mon, 01 Jan 0001 00:00:00 +0000

Wait for a run to finish.

Join Run Stream

Mon, 01 Jan 0001 00:00:00 +0000

Join a run stream. This endpoint streams output in real-time from a run similar to the /threads/THREAD_ID/runs/stream endpoint. If the run has been created with ‘stream_resumable=true’, the stream can be resumed from the last seen event ID.

Join Thread Stream

Mon, 01 Jan 0001 00:00:00 +0000

This endpoint streams output in real-time from a thread. The stream will include the output of each run executed sequentially on the thread and will remain open indefinitely. It is the responsibility of the calling client to close the connection.

JSON RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘JSONSearchTool’ is designed to search JSON files and return the most relevant results.

Kickoff Crew

Mon, 01 Jan 0001 00:00:00 +0000

Kickoff a Crew on CrewAI AMP

Kickoff Crew Asynchronously

Mon, 01 Jan 0001 00:00:00 +0000

Kickoff a Crew Asynchronously

Kickoff Crew for Each

Mon, 01 Jan 0001 00:00:00 +0000

Kickoff Crew for Each Item in a List

Kimi K2 family

Mon, 01 Jan 0001 00:00:00 +0000

Using Kimi K2 family models in agentic and tool-calling workflows on Fireworks.

Knowledge

Mon, 01 Jan 0001 00:00:00 +0000

What is knowledge in CrewAI and how to use it.

Koog

Mon, 01 Jan 0001 00:00:00 +0000

Trace Kotlin-based Koog agents with Weave’s built-in OpenTelemetry support, capturing single-run and complex workflow executions, tool calls, prompts, and completions for full observability of your Kotlin AI applications.

LangChain overview

Mon, 01 Jan 0001 00:00:00 +0000

LangChain is an open source framework with a pre-built agent architecture and integrations for any model or tool — so you can build agents that adapt as fast as the ecosystem evolves

LangChain overview

Mon, 01 Jan 0001 00:00:00 +0000

LangChain is an open source framework with a pre-built agent architecture and integrations for any model or tool — so you can build agents that adapt as fast as the ecosystem evolves

LangChain Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LangChainTool’ is a wrapper for LangChain tools and query engines.

LangDB Integration

Mon, 01 Jan 0001 00:00:00 +0000

Govern, secure, and optimize your CrewAI workflows with LangDB AI Gateway—access 350+ models, automatic routing, cost optimization, and full observability.

Langfuse Integration

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit

LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

LangGraph overview

Mon, 01 Jan 0001 00:00:00 +0000

Gain control with LangGraph to design agents that reliably handle complex tasks

LangGraph overview

Mon, 01 Jan 0001 00:00:00 +0000

Gain control with LangGraph to design agents that reliably handle complex tasks

LangSmith Agent Builder

Mon, 01 Jan 0001 00:00:00 +0000

Create helpful AI agents without code. Start from a template, connect your accounts, and let the agent handle routine work while you stay in control.

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

LangSmith Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

LangSmith Fleet

Mon, 01 Jan 0001 00:00:00 +0000

Create helpful AI agents without code. Start from a template, connect your accounts, and let the agent handle routine work while you stay in control.

LangSmith skills

Mon, 01 Jan 0001 00:00:00 +0000

Use Agent Skills to work with LangSmith traces, datasets, and evaluators from your coding agent.

LangSmith Tool Server

Mon, 01 Jan 0001 00:00:00 +0000

Langtrace Integration

Mon, 01 Jan 0001 00:00:00 +0000

How to monitor cost, latency, and performance of CrewAI Agents using Langtrace, an external observability tool.

Legal Summarization

Mon, 01 Jan 0001 00:00:00 +0000

Using Claude to extract key information from legal documents and generate structured summaries.

Linear Integration

Mon, 01 Jan 0001 00:00:00 +0000

Software project and bug tracking with Linear integration for CrewAI.

Linkup Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LinkupSearchTool’ enables querying the Linkup API for contextual information.

List namespaces with optional match conditions.

Mon, 01 Jan 0001 00:00:00 +0000

List Runs

Mon, 01 Jan 0001 00:00:00 +0000

List runs for a thread.

LiteLLM

Mon, 01 Jan 0001 00:00:00 +0000

LiteLLM integration

Mon, 01 Jan 0001 00:00:00 +0000

Configure LiteLLM as a provider to fan out across multiple model backends.

LiteRT-LM

Mon, 01 Jan 0001 00:00:00 +0000

LlamaIndex

Mon, 01 Jan 0001 00:00:00 +0000

Automatically trace and debug LlamaIndex applications with Weave, capturing all LLM calls, RAG pipelines, agent steps, and evaluations for comprehensive observability of your data-connected AI workflows.

LlamaIndex Agent Evaluation Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

LlamaIndex Agents

Mon, 01 Jan 0001 00:00:00 +0000

LlamaIndex Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘LlamaIndexTool’ is a wrapper for LlamaIndex tools and query engines.

LLM agents

Mon, 01 Jan 0001 00:00:00 +0000

LLM Call Hooks

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use LLM call hooks to intercept, modify, and control language model interactions in CrewAI

LLMs

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to configuring and using Large Language Models (LLMs) in your CrewAI projects

Local shell

Mon, 01 Jan 0001 00:00:00 +0000

Enable agents to run commands in a local shell.

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend deep agents with persistent memory across threads

Long-term memory

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend deep agents with persistent memory across threads

Loop agents

Mon, 01 Jan 0001 00:00:00 +0000

Manage Agent Builder

Mon, 01 Jan 0001 00:00:00 +0000

Manage agent settings

Mon, 01 Jan 0001 00:00:00 +0000

Manage your agents in Agent Builder.

Manage agent settings

Mon, 01 Jan 0001 00:00:00 +0000

Manage your agents in Fleet.

Manage Tool Context

Mon, 01 Jan 0001 00:00:00 +0000

Marketplace

Mon, 01 Jan 0001 00:00:00 +0000

Discover, install, and govern reusable assets for your enterprise crews.

Mastering Flow State Management

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to managing, persisting, and leveraging state in CrewAI Flows for building robust AI applications.

Maxim Integration

Mon, 01 Jan 0001 00:00:00 +0000

Start Agent monitoring, evaluation, and observability

Mcp

Mon, 01 Jan 0001 00:00:00 +0000

MCP integration is what makes the Agent SDK extensible beyond its built-in capabilities, letting your agents connect to any MCP-compatible tool server including databases, APIs, file systems, and custom services. Focus on how the SDK discovers and registers MCP tools at agent initialization, since this determines what capabilities your agent advertises during the agentic loop. A key gotcha is that MCP server connection lifecycle must be managed carefully – servers that fail to start will silently remove tools from your agent’s available set. If you are already familiar with MCP from the protocol specification, this guide shows the practical integration points within the SDK’s agent framework.

MCP

Mon, 01 Jan 0001 00:00:00 +0000

MCP is an open standard protocol for seamless AI model integration with data sources and tools

Mcp Connector

Mon, 01 Jan 0001 00:00:00 +0000

The MCP Connector is the primary mechanism for giving Claude direct access to external tools and data sources through the Model Context Protocol within API calls. Focus on how connector configuration differs from local MCP server setup — the connector handles transport, authentication, and tool discovery on Anthropic’s infrastructure rather than your own. A common pitfall is neglecting to scope tool permissions tightly, which can lead to unexpected token consumption when Claude explores available tools. Read this alongside the remote MCP servers guide to understand the full picture of hosted versus self-managed MCP integrations.

MCP DSL Integration

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use CrewAI’s simple DSL syntax to integrate MCP servers directly with your agents using the mcps field.

MCP endpoint in Agent Server

Mon, 01 Jan 0001 00:00:00 +0000

MCP Get

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

MCP Post

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

MCP Security Considerations

Mon, 01 Jan 0001 00:00:00 +0000

Learn about important security best practices when integrating MCP servers with your CrewAI agents.

MCP Servers as Tools in CrewAI

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to integrate MCP servers as tools in your CrewAI agents using the crewai-tools library.

MCP Tools

Mon, 01 Jan 0001 00:00:00 +0000

Load additional tools from MCP (Model Context Protocol) servers

MCP, A2A, and AG-UI

Mon, 01 Jan 0001 00:00:00 +0000

Understanding how AG-UI complements and works with MCP and A2A

MDX RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MDXSearchTool’ is designed to search MDX files and return the most relevant results.

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Leveraging the unified memory system in CrewAI to enhance agent capabilities.

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Add persistent memory to agents built with Deep Agents so they learn and improve across conversations

Memory

Mon, 01 Jan 0001 00:00:00 +0000

Add persistent memory to agents built with Deep Agents so they learn and improve across conversations

Memory Tool

Mon, 01 Jan 0001 00:00:00 +0000

The memory tool allows Claude to persist information across conversation sessions, enabling agents to maintain user preferences, project context, and learned patterns over time. This bridges the gap between stateless API calls and the continuity users expect from long-running assistant relationships. Focus on understanding what gets stored and how retrieval works, since overloading memory with low-value data degrades relevance of future recalls. Design your memory strategy around high-signal items like user corrections and workflow preferences rather than attempting to memorize entire conversation histories.

Memory-Enabled ReAct Agents

Mon, 01 Jan 0001 00:00:00 +0000

Merge Agent Handler Tool

Mon, 01 Jan 0001 00:00:00 +0000

Enables CrewAI agents to securely access third-party integrations like Linear, GitHub, Slack, and more through Merge’s Agent Handler platform

Message queues

Mon, 01 Jan 0001 00:00:00 +0000

Queue multiple messages and manage them while the agent processes sequentially

Message queues

Mon, 01 Jan 0001 00:00:00 +0000

Queue multiple messages and manage them while the agent processes sequentially

Meta Events

Mon, 01 Jan 0001 00:00:00 +0000

Annotations and signals independent of agent runs

Microsoft Excel Integration

Mon, 01 Jan 0001 00:00:00 +0000

Workbook and data management with Microsoft Excel integration for CrewAI.

Microsoft OneDrive Integration

Mon, 01 Jan 0001 00:00:00 +0000

File and folder management with Microsoft OneDrive integration for CrewAI.

Microsoft Outlook Integration

Mon, 01 Jan 0001 00:00:00 +0000

Email, calendar, and contact management with Microsoft Outlook integration for CrewAI.

Microsoft SharePoint Integration

Mon, 01 Jan 0001 00:00:00 +0000

Site, list, and document management with Microsoft SharePoint integration for CrewAI.

Microsoft Teams Integration

Mon, 01 Jan 0001 00:00:00 +0000

Team collaboration and communication with Microsoft Teams integration for CrewAI.

Microsoft Teams Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Kick off crews from Microsoft Teams chat activity

Microsoft Word Integration

Mon, 01 Jan 0001 00:00:00 +0000

Document creation and management with Microsoft Word integration for CrewAI.

Middleware

Mon, 01 Jan 0001 00:00:00 +0000

Transform and intercept events in AG-UI agents

Middleware

Mon, 01 Jan 0001 00:00:00 +0000

Connect to existing protocols, in process agents or custom solutions via AG-UI

Middleware

Mon, 01 Jan 0001 00:00:00 +0000

Event stream transformation and filtering for AG-UI agents

Migrate from Agent Builder

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to export an Agent Builder workflow and continue with ChatGPT Workspace Agents or the Agents SDK.

Migrating away from create_csv_agent in langchain-cohere

Mon, 01 Jan 0001 00:00:00 +0000

This page contains a tutorial on how to build a CSV agent without the deprecated create_csv_agent abstraction in langchain-cohere v0.3.5 and beyond.

Migration from AutoGen

Mon, 01 Jan 0001 00:00:00 +0000

Migration guide from AutoGen to Microsoft Agent Framework: mapping AgentChat concepts, workflow migration, and new enterprise features.

Migration Guide

Mon, 01 Jan 0001 00:00:00 +0000

This migration guide is critical reading if you have existing agent code built on earlier Anthropic SDK patterns or third-party frameworks and want to move to the official Agent SDK. Focus on the mapping between old abstractions and new ones — particularly how tool definitions, conversation state management, and multi-turn loops translate. A common pitfall is assuming one-to-one correspondence between concepts; the Agent SDK introduces opinionated patterns around agent lifecycle and handoffs that may require rethinking your architecture rather than just swapping imports. Work through the migration incrementally, validating behavior at each step rather than attempting a full rewrite.

Migration to Agent Framework

Mon, 01 Jan 0001 00:00:00 +0000

Migration guide from AutoGen to Microsoft Agent Framework: mapping AgentChat concepts to the unified framework.

MLflow Integration

Mon, 01 Jan 0001 00:00:00 +0000

Quickly start monitoring your Agents with MLflow.

Model Context Protocol

Mon, 01 Jan 0001 00:00:00 +0000

Connect MCP servers so agents can request external data or actions through standardized tool APIs.

Models

Mon, 01 Jan 0001 00:00:00 +0000

Models

Mon, 01 Jan 0001 00:00:00 +0000

Models and providers

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to choose models, set defaults, and think about providers and transport in the OpenAI Agents SDK.

Modifying System Prompts

Mon, 01 Jan 0001 00:00:00 +0000

System prompt modification in the Agent SDK controls how you customize agent behavior, persona, and constraints without forking the SDK’s default prompt scaffolding. Focus on the merge strategy — the SDK combines your custom instructions with its own internal prompts, and understanding this layering prevents conflicts where your instructions get overridden or diluted. A critical pitfall is inadvertently removing safety-relevant default instructions when overriding the system prompt wholesale rather than appending to it. Start with targeted modifications using the provided extension points before considering full prompt replacement.

MongoDB Vector Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MongoDBVectorSearchTool’ performs vector search on MongoDB Atlas with optional indexing helpers.

Moving from LangGraph to CrewAI: A Practical Guide for Engineers

Mon, 01 Jan 0001 00:00:00 +0000

If you already have built with LangGraph, learn how to quickly port your projects to CrewAI

Multi Agent Structured Output

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use multi agent structured output with W&B Weave

Multi-agent

Mon, 01 Jan 0001 00:00:00 +0000

Multi-agent

Mon, 01 Jan 0001 00:00:00 +0000

Multi-agent patterns

Mon, 01 Jan 0001 00:00:00 +0000

Architect teams of agents that collaborate, escalate, or specialize by capability.

Multi-Agent Patterns

Mon, 01 Jan 0001 00:00:00 +0000

Multi-agent systems

Mon, 01 Jan 0001 00:00:00 +0000

Build multi-agent systems in ADK by composing LLM agents and workflow agents into hierarchical teams with shared state and tool delegation.

Multi-Step Tool Use with Cohere

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to create a multi-step, tool-using AI agent with Cohere’s tool use functionality.

Multi-tool agent

Mon, 01 Jan 0001 00:00:00 +0000

Multi-Turn Conversations

Mon, 01 Jan 0001 00:00:00 +0000

Build agents that maintain conversation context across multiple turns with session-based state management.

MultiOn Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MultiOnTool’ empowers CrewAI agents with the capability to navigate and interact with the web through natural language instructions.

MySQL RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘MySQLSearchTool’ is designed to search MySQL databases and return the most relevant results.

Navigate the Weave Trace view

Mon, 01 Jan 0001 00:00:00 +0000

Use Weave’s Trace view to make sense of complex execution paths in your LLM and agentic apps.

Neatlogs Integration

Mon, 01 Jan 0001 00:00:00 +0000

Understand, debug, and share your CrewAI agent runs

NL2SQL Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘NL2SQLTool’ is designed to convert natural language to SQL queries.

Node reference

Mon, 01 Jan 0001 00:00:00 +0000

Explore all available nodes for composing workflows in Agent Builder.

Notion Integration

Mon, 01 Jan 0001 00:00:00 +0000

User management and commenting with Notion integration for CrewAI.

Observability for agents

Mon, 01 Jan 0001 00:00:00 +0000

OCR Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘OCRTool’ extracts text from local images or image URLs using an LLM with vision.

Ollama

Mon, 01 Jan 0001 00:00:00 +0000

OneDrive Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Automate responses to OneDrive file activity

Open Telemetry Logs

Mon, 01 Jan 0001 00:00:00 +0000

Understand how to capture telemetry logs from your CrewAI AMP deployments

OpenAI Agents SDK

Mon, 01 Jan 0001 00:00:00 +0000

Use W&B Weave with the OpenAI Agents SDK to track and monitor your agentic applications

OpenLIT Integration

Mon, 01 Jan 0001 00:00:00 +0000

Quickly start monitoring your Agents in just a single line of code with OpenTelemetry.

Opik Integration

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use Comet Opik to debug, evaluate, and monitor your CrewAI applications with comprehensive tracing, automated evaluations, and production-ready dashboards.

Orchestrate teams of Claude Code sessions

Mon, 01 Jan 0001 00:00:00 +0000

Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.

Orchestration and handoffs

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to orchestrate multiple agents with handoffs and agents-as-tools in the OpenAI Agents SDK.

Outlook Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Launch automations from Outlook emails and calendar updates

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Core concepts in the Agent User Interaction Protocol SDK

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Core concepts in the Agent User Interaction Protocol SDK

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Documentation for encoding Agent User Interaction Protocol events

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Anthropic’s taxonomy of proven AI use cases with implementation guidance for each.

Overview

Mon, 01 Jan 0001 00:00:00 +0000

This overview introduces the agent skills framework, which provides a structured way to package and distribute reusable capabilities that Claude-based agents can invoke. Skills sit between raw tool definitions and full agent architectures, giving you a composable middle layer for common tasks like code review, PR creation, or domain-specific analysis. Start here before reading the individual tool docs to understand how skills orchestrate multiple tools into cohesive workflows. The key architectural decision is which capabilities to implement as standalone tools versus packaged skills, and this doc provides the mental model for making that choice.

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to build, customize, and optimize your CrewAI applications with comprehensive guides and tutorials

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Monitor, evaluate, and optimize your CrewAI agents with comprehensive observability tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Leverage AI services, generate images, process vision, and build intelligent systems

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Automate workflows and integrate with external platforms and services

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Interact with cloud services, storage systems, and cloud-based AI platforms

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connect to databases, vector stores, and data warehouses for comprehensive data access

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Read, write, and search through various file formats with CrewAI’s document processing tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Connect CrewAI agents with external automations and managed AI services

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Perform web searches, find repositories, and research information across the internet

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Extract data from websites and automate browser interactions with powerful scraping tools

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build UIs that display real-time subagent streams, task progress, and sandbox for Deep Agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from deep agent runs and subagent execution

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Control and customize agent execution at every step

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from agent runs

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Render LangGraph agents to the frontend

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build UIs that display real-time subagent streams, task progress, and sandbox for Deep Agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from deep agent runs and subagent execution

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Build generative UIs with real-time streaming from LangChain agents

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Control and customize agent execution at every step

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Stream real-time updates from agent runs

Overview

Mon, 01 Jan 0001 00:00:00 +0000

Render LangGraph agents to the frontend

Oxylabs Scrapers

Mon, 01 Jan 0001 00:00:00 +0000

Oxylabs Scrapers allow to easily access the information from the respective sources. Please see the list of available sources below:

Parallel agents

Mon, 01 Jan 0001 00:00:00 +0000

Parallel Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Parallelize agents

Mon, 01 Jan 0001 00:00:00 +0000

Parallelize W&B Sweep agents on multi-core or multi-GPU machine.

Patch Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Update an assistant.

Patch Thread

Mon, 01 Jan 0001 00:00:00 +0000

Update a thread.

Patronus AI Evaluation

Mon, 01 Jan 0001 00:00:00 +0000

Monitor and evaluate CrewAI agent performance using Patronus AI’s comprehensive evaluation platform for LLM outputs and agent behaviors.

PDF Extractor with Native Multi Step Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to create an AI agent able to extract information from PDFs.

PDF RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PDFSearchTool’ is designed to search PDF files and return the most relevant results.

PDF Text Writing Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PDFTextWritingTool’ writes text to specific positions in a PDF, supporting custom fonts.

Performing Tasks Sequentially with Cohere's RAG

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that can handle user queries that require tasks to be performed in a sequence.

Permissions

Mon, 01 Jan 0001 00:00:00 +0000

Permissions are critical for production deployments where agents interact with external systems or sensitive data. Focus on the least-privilege principle: grant only the capabilities an agent actually needs, and be especially careful with tool permissions that allow file system access or network calls. A common pitfall is developing with permissive settings and forgetting to lock them down before deployment, which can expose your system to prompt injection attacks that leverage overly broad tool access. Read this alongside the secure deployment guide for a complete security posture.

PG RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘PGSearchTool’ is designed to search PostgreSQL databases and return the most relevant results.

PII Redaction for Traces

Mon, 01 Jan 0001 00:00:00 +0000

Automatically redact sensitive data from crew and flow execution traces

Pinecone Assistant

Mon, 01 Jan 0001 00:00:00 +0000

Pinecone Assistant is a service that allow you to build production-grade chat and agent-based applications quickly.

Planning

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to add planning to your CrewAI Crew and improve their performance.

Plugins

Mon, 01 Jan 0001 00:00:00 +0000

Plugins extend the Agent SDK’s core behavior by hooking into the agent lifecycle at well-defined extension points, enabling cross-cutting concerns like logging, rate limiting, and custom authentication without modifying agent logic directly. Focus on the plugin interface and the ordering guarantees for plugin execution — multiple plugins can compose, but execution order matters for plugins that modify requests or responses. A common mistake is putting business logic inside plugins rather than skills, which makes agents harder to test and reason about. Read this after understanding skills to appreciate the boundary between agent capabilities and infrastructure concerns.

Portkey Integration

Mon, 01 Jan 0001 00:00:00 +0000

How to use Portkey with CrewAI

Prebuilt middleware

Mon, 01 Jan 0001 00:00:00 +0000

Prebuilt middleware for common agent use cases

Prebuilt middleware

Mon, 01 Jan 0001 00:00:00 +0000

Prebuilt middleware for common agent use cases

Prepare for Deployment

Mon, 01 Jan 0001 00:00:00 +0000

Ensure your Crew or Flow is ready for deployment to CrewAI AMP

Price comparison vs Tinker

Mon, 01 Jan 0001 00:00:00 +0000

Estimate the cost of multi-turn agentic RL rollouts on Fireworks compared to Tinker’s per-token pricing

Pricing FAQ

Mon, 01 Jan 0001 00:00:00 +0000

Private Package Registries

Mon, 01 Jan 0001 00:00:00 +0000

Install private Python packages from authenticated PyPI registries in CrewAI AMP

Processes

Mon, 01 Jan 0001 00:00:00 +0000

Detailed guide on workflow management through processes in CrewAI, with updated implementation details.

Production Architecture

Mon, 01 Jan 0001 00:00:00 +0000

Best practices for building production-ready AI applications with CrewAI

Programmatic Tool Calling

Mon, 01 Jan 0001 00:00:00 +0000

Programmatic tool calling lets you force Claude to invoke a specific tool rather than deciding autonomously whether to use one, which is essential for deterministic agentic workflows where you need guaranteed structured output on every turn. This is particularly useful when building pipelines that must always extract data into a schema or always query an external system before responding. Be aware that forcing a tool call changes Claude’s behavior around the rest of the response – it will not produce any text content before the forced tool invocation. Read the general tool-use guide first to understand the baseline calling conventions, then use this doc to layer in the deterministic control patterns.

Prune Threads

Mon, 01 Jan 0001 00:00:00 +0000

Prune threads by ID. The ‘delete’ strategy removes threads entirely. The ‘keep_latest’ strategy prunes old checkpoints but keeps threads and their latest state.

Publish Custom Tools

Mon, 01 Jan 0001 00:00:00 +0000

How to build, package, and publish your own CrewAI-compatible tools to PyPI so any CrewAI user can install and use them.

PydanticAI

Mon, 01 Jan 0001 00:00:00 +0000

Trace PydanticAI agent and tool calls in Weave using OpenTelemetry

Python

Mon, 01 Jan 0001 00:00:00 +0000

The Python SDK is the more mature of the two language implementations and tends to receive new features first. Pay close attention to the async patterns used throughout – the SDK is built on asyncio, so understanding Python’s async/await model is a prerequisite for effective use. If you are coming from the raw Anthropic API client, note that the Agent SDK manages conversation state and tool execution loops for you, which is a significant shift in how you structure your code. Read the quickstart guide first if you have not already, then use this reference for Python-specific configuration details.

Qdrant Vector Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

Semantic search capabilities for CrewAI agents using Qdrant vector database

Querying Structured Data (SQL)

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that can query structured data (SQL).

Querying Structured Data (Tables)

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that can query structured data (tables).

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

This is the fastest path to a running agent and the best starting point before diving into advanced SDK features. Focus on the AgentConfig pattern, which is the central abstraction for defining agent behavior, tools, and instructions. Pay attention to how the SDK handles the agentic loop automatically – understanding what happens behind the scenes here will save you debugging time later. Read this before the Python or TypeScript language-specific guides so you have the conceptual model in place first.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

This quickstart walks you through building your first agent skill end-to-end, from definition to invocation within a Claude-powered agent. Focus on the skill registration pattern and how the runtime discovers and exposes skills to the model — getting this wiring right is foundational for everything else. Be aware that the quickstart uses simplified error handling; production skills need retry logic and graceful degradation as covered in the best practices guide. Work through this hands-on before reading the enterprise or best practices docs to build concrete intuition first.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first AI agent with CrewAI in under 5 minutes.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent from a template

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build an agent from a template

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first deep agent in minutes

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first deep agent in minutes

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Step-by-step setup for installing the package, configuring API keys, and running your first agent locally.

Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build your first agent with the OpenAI Agents SDK, add tools and handoffs, and understand where to go next.

Quickstart: How to Use OpenClaw with Together AI

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to pair OpenClaw, a powerful autonomous agent, with frontier OSS models on Together AI like Kimi K2.5 and GLM 4.7.

RAG Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘RagTool’ is a dynamic knowledge base tool for answering questions using Retrieval-Augmented Generation.

React Component Export

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to export and integrate CrewAI AMP React components into your applications

Realtime guide

Mon, 01 Jan 0001 00:00:00 +0000

Deep dive into session lifecycle, event formats, and concurrency patterns.

Realtime quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Stand up low-latency realtime agents with websocket transport (WebRTC is not available in the Python SDK).

Realtime transport

Mon, 01 Jan 0001 00:00:00 +0000

Decide between the default server-side WebSocket path and SIP attach flows, with the browser WebRTC boundary called out explicitly.

Reasoning

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to enable and use agent reasoning to improve task execution.

Reasoning Capabilities

Mon, 01 Jan 0001 00:00:00 +0000

Reasoning models excel at tool use, agentic workflows, and complex problem-solving. This page provides a general overview of Cohere’s reasoning capalities.

Release notes

Mon, 01 Jan 0001 00:00:00 +0000

Track SDK changes, migration notes, and deprecations.

Remote Agent Quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Train an SVG drawing agent running in a remote environment

Remote Mcp Servers

Mon, 01 Jan 0001 00:00:00 +0000

Remote MCP servers let you host tool endpoints that Claude connects to over the network, enabling shared infrastructure across teams and persistent service integrations. Pay close attention to the authentication and transport sections — remote servers use SSE or streamable HTTP rather than stdio, which changes how you handle connection lifecycle and error recovery. A frequent gotcha is failing to implement proper OAuth or token refresh flows, causing silent tool failures mid-conversation. This guide pairs well with the MCP Connector docs to compare Anthropic-hosted versus self-hosted approaches to serving tools.

Remote MCP servers

Mon, 01 Jan 0001 00:00:00 +0000

Connect Agent Builder to popular remote MCP servers

REPL

Mon, 01 Jan 0001 00:00:00 +0000

Use the interactive runner to prototype agents and inspect execution step by step.

Replay Tasks from Latest Crew Kickoff

Mon, 01 Jan 0001 00:00:00 +0000

Replay tasks from the latest crew.kickoff(…)

Repository on GitHub

Mon, 01 Jan 0001 00:00:00 +0000

Source code, issues, and contribution guidelines for the SDK.

Results

Mon, 01 Jan 0001 00:00:00 +0000

Inspect agent outputs, tool calls, follow-up actions, and metadata returned by the runner.

Results and state

Mon, 01 Jan 0001 00:00:00 +0000

Learn which result surfaces matter most in the OpenAI Agents SDK and how they connect to resumable workflow state.

Resume Agents

Mon, 01 Jan 0001 00:00:00 +0000

Retrieve a single item.

Mon, 01 Jan 0001 00:00:00 +0000

Roadmap

Mon, 01 Jan 0001 00:00:00 +0000

Our plans for evolving Agent User Interaction Protocol

Role-Based Access Control (RBAC)

Mon, 01 Jan 0001 00:00:00 +0000

Control access to crews, tools, and data with roles, scopes, and granular permissions.

Router

Mon, 01 Jan 0001 00:00:00 +0000

Router

Mon, 01 Jan 0001 00:00:00 +0000

Routing Queries to Data Sources

Mon, 01 Jan 0001 00:00:00 +0000

Build an agentic RAG system that routes queries to the most relevant tools based on the query’s nature.

Run backtests on a new version of an agent

Mon, 01 Jan 0001 00:00:00 +0000

Run Claude Code programmatically

Mon, 01 Jan 0001 00:00:00 +0000

Use the Agent SDK to run Claude Code programmatically from the CLI, Python, or TypeScript.

Running agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn synchronous, asynchronous, and batched execution, plus cancellation and error handling.

Running agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to run agents, stream output, and choose the right conversation-state strategy in the OpenAI Agents SDK.

Runs

Mon, 01 Jan 0001 00:00:00 +0000

An overview of runs in Agent Server, including how to kick off background runs, stateless runs, and cancel runs.

S3 Reader Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘S3ReaderTool’ enables CrewAI agents to read files from Amazon S3 buckets.

S3 Writer Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘S3WriterTool’ enables CrewAI agents to write content to files in Amazon S3 buckets.

Safety and Security for AI Agents

Mon, 01 Jan 0001 00:00:00 +0000

Safety in building agents

Mon, 01 Jan 0001 00:00:00 +0000

Minimize prompt injections and other risks in agent workflows — covering input validation, tool call authorization, and sandboxing strategies specific to agentic systems.

Salesforce Integration

Mon, 01 Jan 0001 00:00:00 +0000

CRM and sales automation with Salesforce integration for CrewAI.

Salesforce Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Trigger CrewAI crews from Salesforce workflows for CRM automation

Sandbox

Mon, 01 Jan 0001 00:00:00 +0000

Build an IDE-like UI for a coding agent backed by a sandbox environment

Sandbox

Mon, 01 Jan 0001 00:00:00 +0000

Build an IDE-like UI for a coding agent backed by a sandbox environment

Sandbox Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how sandboxes fit into Agents SDK workflows, when to use them, and how orchestration stays separate from execution.

Sandboxes

Mon, 01 Jan 0001 00:00:00 +0000

Execute code in isolated environments with sandbox backends

Sandboxes

Mon, 01 Jan 0001 00:00:00 +0000

Execute code in isolated environments with sandbox backends

Sandboxing

Mon, 01 Jan 0001 00:00:00 +0000

Learn how Claude Code’s sandboxed bash tool provides filesystem and network isolation for safer, more autonomous agent execution.

Schedules

Mon, 01 Jan 0001 00:00:00 +0000

Configure schedules to run your Fleet agents on a recurring basis.

Scrape Element From Website Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapeElementFromWebsiteTool’ enables CrewAI agents to extract specific elements from websites using CSS selectors.

Scrape Website

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapeWebsiteTool’ is designed to extract and read the content of a specified website.

Scrapegraph Scrape Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapegraphScrapeTool’ leverages Scrapegraph AI’s SmartScraper API to intelligently extract content from websites.

Scrapfly Scrape Website Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ScrapflyScrapeWebsiteTool’ leverages Scrapfly’s web scraping API to extract content from websites in various formats.

Search Assistants

Mon, 01 Jan 0001 00:00:00 +0000

Search for assistants.

Search Crons

Mon, 01 Jan 0001 00:00:00 +0000

Search all active crons

Search or list items within a namespace prefix.

Mon, 01 Jan 0001 00:00:00 +0000

Lists items ordered by last updated time. If a ‘query’ is provided, performs a natural language search instead. Supports pagination via ’limit’ and ‘offset’, and filtering via ‘filter’.

Search Threads

Mon, 01 Jan 0001 00:00:00 +0000

Search for threads.

Secure Deployment

Mon, 01 Jan 0001 00:00:00 +0000

This guide becomes essential the moment you move an agent from local development to any shared or production environment. Focus on the sections covering input sanitization and output validation, as prompt injection through user-supplied content is the most common attack vector for deployed agents. Be aware that securing an agent is different from securing a traditional API – you must account for the model’s ability to chain tool calls in unexpected ways, so defense-in-depth with both permission restrictions and monitoring is necessary. Read this in conjunction with the permissions guide, as the two together form a complete security strategy.

Selenium Scraper

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SeleniumScrapingTool’ is designed to extract and read the content of a specified website using Selenium.

Sequential agents

Mon, 01 Jan 0001 00:00:00 +0000

Sequential Processes

Mon, 01 Jan 0001 00:00:00 +0000

A comprehensive guide to utilizing the sequential processes for task execution in CrewAI projects.

Sequential Workflow

Mon, 01 Jan 0001 00:00:00 +0000

Coordinating a chain of LLM calls to solve a complex task.

SerpApi Google Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerpApiGoogleSearchTool’ performs Google searches using the SerpApi service.

SerpApi Google Shopping Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SerpApiGoogleShoppingTool’ searches Google Shopping results using SerpApi.

Server Information

Mon, 01 Jan 0001 00:00:00 +0000

Get server version information, feature flags, and metadata.

Server Tools

Mon, 01 Jan 0001 00:00:00 +0000

Sessions

Mon, 01 Jan 0001 00:00:00 +0000

Sessions

Mon, 01 Jan 0001 00:00:00 +0000

Manage stateful conversations with automatic history persistence and memory controls.

Set Latest Assistant Version

Mon, 01 Jan 0001 00:00:00 +0000

Set the latest version for an assistant.

Set up Agent Auth (Beta)

Mon, 01 Jan 0001 00:00:00 +0000

Enable secure access from agents to any system using OAuth 2.0 credentials with Agent Auth.

Shopify Integration

Mon, 01 Jan 0001 00:00:00 +0000

E-commerce and online store management with Shopify integration for CrewAI.

Short-Term Memory Handling for Agents

Mon, 01 Jan 0001 00:00:00 +0000

This page describes how to manage short-term memory in an agent built with Cohere models.

Single Sign-On (SSO)

Mon, 01 Jan 0001 00:00:00 +0000

Configure enterprise SSO authentication for CrewAI Platform — SaaS and Factory

SingleStore Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SingleStoreSearchTool’ safely executes SELECT/SHOW queries on SingleStore with pooling.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Skills in the Agent SDK are the primary abstraction for packaging reusable capabilities that agents can invoke — think of them as higher-level building blocks above raw tool definitions. Focus on how skill registration exposes capabilities to the agent runtime and how the SDK handles skill discovery, parameter validation, and result formatting. A subtle but important detail is how skill descriptions influence the model’s decision to invoke them; poorly written descriptions lead to unreliable skill selection. Read this reference alongside the agent-skills quickstart and best practices guides for the full picture from concept to production-ready implementation.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Filesystem-based skill packages that inject domain expertise and instructions into agent prompts.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Use skills to give your agents access to specific capabilities.

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend your deep agent’s capabilities with skills

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to extend your deep agent’s capabilities with skills

Skills

Mon, 01 Jan 0001 00:00:00 +0000

Skills for ADK agents

Mon, 01 Jan 0001 00:00:00 +0000

Slack Integration

Mon, 01 Jan 0001 00:00:00 +0000

Team communication and collaboration with Slack integration for CrewAI.

Slack Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Trigger CrewAI crews directly from Slack using slash commands

Slash Commands

Mon, 01 Jan 0001 00:00:00 +0000

Smolagents

Mon, 01 Jan 0001 00:00:00 +0000

Track and analyze Smolagents agentic applications with Weave’s automatic tracing, capturing tool calls, model inferences, and multi-step workflows across OpenAI, Hugging Face, and Anthropic LLM providers.

Snowflake Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SnowflakeSearchTool’ enables CrewAI agents to execute SQL queries and perform semantic search on Snowflake data warehouses.

Speaker Selection Strategies

Mon, 01 Jan 0001 00:00:00 +0000

Speaker selection determines which agent speaks next in a GroupChat: round-robin, random, manual, or auto-selection based on agent descriptions and conversation context.

Spider Scraper

Mon, 01 Jan 0001 00:00:00 +0000

The ‘SpiderTool’ is designed to extract and read the content of a specified website using Spider.

SQL Agent with Cohere and LangChain (i-5O Case Study)

Mon, 01 Jan 0001 00:00:00 +0000

This page contains a tutorial on how to build a SQL agent with Cohere and LangChain in the manufacturing industry.

SSE Transport

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to connect CrewAI to remote MCP servers using Server-Sent Events (SSE) for real-time communication.

Stagehand Tool

Mon, 01 Jan 0001 00:00:00 +0000

Web automation tool that integrates Stagehand with CrewAI for browser interaction and automation

Standard deployment

Mon, 01 Jan 0001 00:00:00 +0000

Start a sweep agent

Mon, 01 Jan 0001 00:00:00 +0000

Start or stop a W&B Sweep Agent on one or more machines.

State Management

Mon, 01 Jan 0001 00:00:00 +0000

Understanding state synchronization between agents and frontends in AG-UI

Stdio Transport

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to connect CrewAI to local MCP servers using the Stdio (Standard Input/Output) transport mechanism.

Stop Reasons

Mon, 01 Jan 0001 00:00:00 +0000

Store or update an item.

Mon, 01 Jan 0001 00:00:00 +0000

Strategic LLM Selection Guide

Mon, 01 Jan 0001 00:00:00 +0000

Strategic framework for choosing the right LLM for your CrewAI AI agents and writing effective task and agent definitions

Streamable HTTP Transport

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to connect CrewAI to remote MCP servers using the flexible Streamable HTTP transport.

Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Stream intermediate tool usage and LLM responses for responsive UIs.

Streaming Output

Mon, 01 Jan 0001 00:00:00 +0000

This guide dives into the practical implementation details of consuming streamed agent output, which is distinct from the higher-level decision of whether to use streaming at all (covered in the streaming vs. single mode guide). Focus on the event types emitted during a stream, particularly the distinction between text delta events and tool-use events, since your UI rendering logic needs to handle both gracefully. Watch out for the connection drop scenario – if a stream disconnects mid-response, you need a strategy for resuming or restarting the agent turn. Understanding the event structure here is also essential if you plan to build custom frontends or integrate with frameworks like AG-UI.

Streaming Vs Single Mode

Mon, 01 Jan 0001 00:00:00 +0000

This guide addresses a fundamental architectural decision you will face early in any agent project. Single-turn mode is simpler to implement and debug because you get a complete response at once, making error handling straightforward and retry logic clean. Streaming mode provides real-time token-by-token output that is essential for user-facing applications where perceived latency matters, but it introduces complexity around partial results and connection management. Start with single-turn mode during development and prototyping, then migrate to streaming when you need production-quality user experience.

Strict Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

Stripe Integration

Mon, 01 Jan 0001 00:00:00 +0000

Payment processing and subscription management with Stripe integration for CrewAI.

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Render structured agent responses with custom UI components instead of plain text

Structured output

Mon, 01 Jan 0001 00:00:00 +0000

Render structured agent responses with custom UI components instead of plain text

Structured Output

Mon, 01 Jan 0001 00:00:00 +0000

Learn to generate structured outputs like JSON for LLM agents and pipelines, with custom and flexible formatting options

Structured Outputs

Mon, 01 Jan 0001 00:00:00 +0000

Structured outputs let you constrain agent responses to conform to a specific schema, which is essential for building reliable pipelines where downstream code depends on predictable JSON shapes. Focus on how schema definitions interact with the agent loop — the SDK validates output at the framework level rather than relying on prompt engineering alone. A key gotcha is that overly complex schemas can increase latency and reduce output quality, so start with flat structures and add nesting only when needed. Compare this approach with OpenAI’s structured outputs to understand the tradeoffs in schema expressiveness and enforcement guarantees.

Subagent streaming

Mon, 01 Jan 0001 00:00:00 +0000

Display specialist subagents with streaming content, progress tracking, and collapsible cards

Subagent streaming

Mon, 01 Jan 0001 00:00:00 +0000

Display specialist subagents with streaming content, progress tracking, and collapsible cards

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Subagents enable multi-agent architectures where a parent agent delegates specialized tasks to child agents with their own instructions, tools, and models. Unlike the OpenAI Agents SDK handoffs pattern, which transfers control entirely to another agent, the Anthropic subagent model uses delegation semantics where the parent retains control and receives the subagent’s result. Focus on how context is passed between parent and child agents, since over-sharing context inflates token costs while under-sharing causes the subagent to lack necessary information. This is a key building block for complex workflows – read this after understanding single-agent patterns and before designing multi-agent systems.

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use subagents to delegate work and keep context clean

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use subagents to delegate work and keep context clean

Subagents

Mon, 01 Jan 0001 00:00:00 +0000

Swarm

Mon, 01 Jan 0001 00:00:00 +0000

System Metrics

Mon, 01 Jan 0001 00:00:00 +0000

Get system metrics in Prometheus or JSON format for monitoring and observability.

Tasks

Mon, 01 Jan 0001 00:00:00 +0000

Detailed guide on managing and creating tasks within the CrewAI framework.

Tavily Extractor Tool

Mon, 01 Jan 0001 00:00:00 +0000

Extract structured content from web pages using the Tavily API

Tavily Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

Perform comprehensive web searches using the Tavily Search API

Team Management

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to invite and manage team members in your CrewAI AMP organization

Telemetry

Mon, 01 Jan 0001 00:00:00 +0000

Understanding the telemetry data collected by CrewAI and how it contributes to the enhancement of the library.

Templates

Mon, 01 Jan 0001 00:00:00 +0000

Start faster with curated Agent Builder templates and customize tools, prompts, and triggers.

Terminate Session

Mon, 01 Jan 0001 00:00:00 +0000

Implemented according to the Streamable HTTP Transport specification.

Test

Mon, 01 Jan 0001 00:00:00 +0000

Strategies for testing LangChain agents, including unit tests, integration tests, and trajectory evaluations.

Test

Mon, 01 Jan 0001 00:00:00 +0000

Strategies for testing LangChain agents, including unit tests, integration tests, and trajectory evaluations.

Test a ReAct agent with Pytest/Vitest and LangSmith

Mon, 01 Jan 0001 00:00:00 +0000

Test Agent Card

Mon, 01 Jan 0001 00:00:00 +0000

Online tool to validate if a domain supports the A2A protocol and visualize agent card information. Enter any URL to check for A2A protocol support and parse the agent.json file.

Test deployed agents

Mon, 01 Jan 0001 00:00:00 +0000

Testing

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to test your CrewAI Crew and evaluate their performance.

Testset Generation for Agents or Tool use cases

Mon, 01 Jan 0001 00:00:00 +0000

Text Editor Tool

Mon, 01 Jan 0001 00:00:00 +0000

The text editor tool gives Claude the ability to view, create, and edit files through structured operations like insert, replace, and undo, making it central to coding agent implementations. Unlike having Claude output code in a message for you to copy, this tool enables autonomous multi-step file modifications within an agentic loop. Focus on understanding the exact replacement semantics, since the tool requires unique string matches for edits and will fail if the target string appears multiple times. This tool works best when combined with the bash tool for running tests after edits, forming the core edit-verify cycle that coding agents depend on.

Thinking in LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to think about building agents with LangGraph

Thinking in LangGraph

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to think about building agents with LangGraph

Ticket Routing

Mon, 01 Jan 0001 00:00:00 +0000

Using Claude to automatically classify and route support tickets to the right team based on content analysis.

Todo list

Mon, 01 Jan 0001 00:00:00 +0000

Track agent progress with a real-time todo list synced from agent state

Todo list

Mon, 01 Jan 0001 00:00:00 +0000

Track agent progress with a real-time todo list synced from agent state

Todo Tracking

Mon, 01 Jan 0001 00:00:00 +0000

Together AI Skills

Mon, 01 Jan 0001 00:00:00 +0000

Give your AI coding agent deep knowledge of the Together AI platform with ready-made skills for inference, training, images, video, audio, and infrastructure.

Together Mixture Of Agents (MoA)

Mon, 01 Jan 0001 00:00:00 +0000

Tool Call Hooks

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use tool call hooks to intercept, modify, and control tool execution in CrewAI

Tool calling

Mon, 01 Jan 0001 00:00:00 +0000

Display agent tool calls with rich, type-safe UI cards

Tool calling

Mon, 01 Jan 0001 00:00:00 +0000

Display agent tool calls with rich, type-safe UI cards

Tool Combinations

Mon, 01 Jan 0001 00:00:00 +0000

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tool integrations

Mon, 01 Jan 0001 00:00:00 +0000

Give your agents access to a wide range of tools and services.

Tool Reference

Mon, 01 Jan 0001 00:00:00 +0000

Tool Repository

Mon, 01 Jan 0001 00:00:00 +0000

Using the Tool Repository to manage your tools

Tool Runner

Mon, 01 Jan 0001 00:00:00 +0000

Tool Search

Mon, 01 Jan 0001 00:00:00 +0000

Tool Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The tool search tool enables deferred tool loading, allowing agents with large tool catalogs to discover and activate tools on demand rather than loading everything into context upfront. This is critical for agents that integrate many MCP servers or have hundreds of available tools, since stuffing all tool definitions into the system prompt degrades model performance and wastes tokens. Pay attention to the query semantics: keyword search returns ranked matches while direct selection loads a specific tool by name. Architect your agent so that commonly used tools are always loaded and niche tools are deferred behind search to keep context windows lean.

Tool use & agents - Cohere on Azure AI Foundry

Mon, 01 Jan 0001 00:00:00 +0000

A guide for using tool use and building agents with Cohere’s Command models on Azure AI Foundry (API v2).

Tool use & agents - quickstart

Mon, 01 Jan 0001 00:00:00 +0000

A quickstart guide for using tool use and building agents with Cohere’s Command models (v2 API).

Tool Use With Prompt Caching

Mon, 01 Jan 0001 00:00:00 +0000

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Understanding and leveraging tools within the CrewAI framework for agent collaboration and task execution.

Tools

Mon, 01 Jan 0001 00:00:00 +0000

Tools & Integrations

Mon, 01 Jan 0001 00:00:00 +0000

Connect external apps and manage internal tools your agents can use.

Tools Overview

Mon, 01 Jan 0001 00:00:00 +0000

Discover CrewAI’s extensive library of 40+ tools to supercharge your AI agents

Trace Claude Agent SDK applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace CrewAI applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Deep Agents applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace Microsoft Agent Framework applications

Mon, 01 Jan 0001 00:00:00 +0000

Trace OpenAI Agents SDK applications

Mon, 01 Jan 0001 00:00:00 +0000

Traces

Mon, 01 Jan 0001 00:00:00 +0000

Using Traces to monitor your Crews

Tracing

Mon, 01 Jan 0001 00:00:00 +0000

Capture spans for every agent step, emit data to OpenAI traces, and integrate third-party processors.

Training

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to train your CrewAI agents by giving them feedback early on and get consistent results.

Triggers

Mon, 01 Jan 0001 00:00:00 +0000

Configure triggers to start your Agent Builder agents automatically.

Triggers Overview

Mon, 01 Jan 0001 00:00:00 +0000

Understand how CrewAI AMP triggers work, how to manage them, and where to find integration-specific playbooks

Troubleshooting Tool Use

Mon, 01 Jan 0001 00:00:00 +0000

TrueFoundry Integration

Mon, 01 Jan 0001 00:00:00 +0000

TXT RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘TXTSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.

Types

Mon, 01 Jan 0001 00:00:00 +0000

Documentation for the core types used in the Agent User Interaction Protocol SDK

Types

Mon, 01 Jan 0001 00:00:00 +0000

Documentation for the core types used in the Agent User Interaction Protocol Python SDK

Typescript

Mon, 01 Jan 0001 00:00:00 +0000

The TypeScript SDK mirrors the Python SDK’s architecture but leverages TypeScript’s type system to provide compile-time safety for agent configurations, tool definitions, and event handlers. If you are choosing between the two language SDKs, note that the Python SDK generally receives feature updates first, but the TypeScript SDK offers stronger typing guarantees that catch configuration errors before runtime. Pay attention to how generics are used for tool input/output types, as properly typing your tools will give you autocompletion and validation throughout your agent code. Read the quickstart guide first for the conceptual model, then use this reference for TypeScript-specific patterns and idioms.

Typescript V2 Preview

Mon, 01 Jan 0001 00:00:00 +0000

Unit testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agent logic without API calls using fake chat models and in-memory persistence.

Unit testing

Mon, 01 Jan 0001 00:00:00 +0000

Test agent logic without API calls using fake chat models and in-memory persistence.

Update Crew

Mon, 01 Jan 0001 00:00:00 +0000

Updating a Crew on CrewAI AMP

Update Cron

Mon, 01 Jan 0001 00:00:00 +0000

Update a cron job by ID.

Update Thread State

Mon, 01 Jan 0001 00:00:00 +0000

Add state to a thread.

Usage and pricing

Mon, 01 Jan 0001 00:00:00 +0000

Understand token accounting, usage metrics, and cost estimation.

Use an Assistant MCP server

Mon, 01 Jan 0001 00:00:00 +0000

Connect AI agents to Pinecone Assistant via Model Context Protocol.

Use Fireworks Agent with Claude Code, Cursor, Codex, and other coding agents

Mon, 01 Jan 0001 00:00:00 +0000

Install the Fireworks Agent skill file once and drive end-to-end fine-tuning from your coding agent.

Use server-side caching

Mon, 01 Jan 0001 00:00:00 +0000

Cache values server-side in your agent deployment using stale-while-revalidate and key-value cache APIs.

Use the Pinecone MCP server

Mon, 01 Jan 0001 00:00:00 +0000

Use Pinecone MCP server for AI agent integration.

Use W&B Skills

Mon, 01 Jan 0001 00:00:00 +0000

Install W&B Skills to teach your coding agent how to train models, build agents, and analyze experiments using W&B’s AI development platform.

User Input

Mon, 01 Jan 0001 00:00:00 +0000

Using Annotations in crew.py

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use annotations to properly structure agents, tasks, and components in CrewAI

Using CrewAI Without LiteLLM

Mon, 01 Jan 0001 00:00:00 +0000

How to use CrewAI with native provider integrations and remove the LiteLLM dependency from your project.

Using Multimodal Agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to enable and use multimodal capabilities in your agents for processing images and other non-text content within the CrewAI framework.

Verifiers

Mon, 01 Jan 0001 00:00:00 +0000

Track and debug Verifiers RL environments and LLM agent training with Weave, capturing multi-round conversations, evaluation rollouts, and model performance metrics for comprehensive observability of reinforcement learning workflows.

Vertex AI hosted

Mon, 01 Jan 0001 00:00:00 +0000

Vision Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘VisionTool’ is designed to extract text from images.

Visualization

Mon, 01 Jan 0001 00:00:00 +0000

Embed tracing dashboards and visualize agent runs directly in notebooks and web apps.

vLLM

Mon, 01 Jan 0001 00:00:00 +0000

Voice agents

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to build agents that can work with audio and speech.

Voice pipeline

Mon, 01 Jan 0001 00:00:00 +0000

Customize audio ingestion, tool execution, and response rendering.

Voice quickstart

Mon, 01 Jan 0001 00:00:00 +0000

Build speech-enabled agents with streaming transcription and TTS.

VoltAgent

Mon, 01 Jan 0001 00:00:00 +0000

VoltAgent

Mon, 01 Jan 0001 00:00:00 +0000

Weather agent

Mon, 01 Jan 0001 00:00:00 +0000

Weave Integration

Mon, 01 Jan 0001 00:00:00 +0000

Learn how to use Weights & Biases (W&B) Weave to track, experiment with, evaluate, and improve your CrewAI applications.

Weaviate Vector Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘WeaviateVectorSearchTool’ is designed to search a Weaviate vector database for semantically similar documents using hybrid search.

Web Fetch Tool

Mon, 01 Jan 0001 00:00:00 +0000

The web fetch tool is an Anthropic-provided built-in tool that lets Claude retrieve content from URLs during a conversation, converting HTML to markdown for processing. This is a key building block for agents that need to access live web data, documentation, or API responses without requiring you to build custom tool infrastructure. Note that authenticated URLs will fail since the tool operates without session cookies or tokens, so you need alternative approaches for private resources. Compare this with the web search tool, which discovers URLs, whereas web fetch retrieves content from known URLs you or the model already have.

Web Search Tool

Mon, 01 Jan 0001 00:00:00 +0000

The web search tool gives Claude the ability to query search engines and incorporate up-to-date information into its responses, directly addressing the knowledge cutoff limitation inherent to all LLMs. This is essential for agents that need to answer questions about current events, recent software releases, or rapidly changing documentation. Be mindful that search results are summaries, not full page content – pair this tool with the web fetch tool when you need to deeply read a specific result. Search queries constructed by the model can sometimes be overly broad, so providing domain filtering constraints improves relevance significantly.

Webhook Automation

Mon, 01 Jan 0001 00:00:00 +0000

Automate CrewAI AMP workflows using webhooks with platforms like ActivePieces, Zapier, and Make.com

Webhook Streaming

Mon, 01 Jan 0001 00:00:00 +0000

Using Webhook Streaming to stream events to your webhook

Websearch

Mon, 01 Jan 0001 00:00:00 +0000

Websearch enables models to browse the web for real-time, up-to-date information and access specific websites

Website RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘WebsiteSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a website.

Why Evaluate Agents

Mon, 01 Jan 0001 00:00:00 +0000

Workflow Agents

Mon, 01 Jan 0001 00:00:00 +0000

Workflow agents provide deterministic orchestration without LLM overhead: sequential, parallel, and loop patterns for composing agent execution.

Workflow Edges

Mon, 01 Jan 0001 00:00:00 +0000

Edge types for controlling workflow transitions: conditional routing, parallel fan-out, and convergence patterns.

Workflows and agents

Mon, 01 Jan 0001 00:00:00 +0000

Workflows and agents

Mon, 01 Jan 0001 00:00:00 +0000

This guide draws the critical distinction between deterministic workflows and autonomous agents in LangGraph, which is the most important conceptual decision you make when designing a LangGraph application. Workflows use predefined edges and conditional branching, while agents use LLM-driven decisions to determine the next step. Understanding when to choose each pattern, and when to combine them, directly impacts the reliability, cost, and debuggability of your application. Start here before diving into specific LangGraph features like memory or streaming, as the workflow-vs-agent framing shapes every subsequent design choice.

Workflows Overview

Mon, 01 Jan 0001 00:00:00 +0000

Graph-based workflow orchestration: defining agents as nodes, transitions as edges, and execution strategies (sequential, parallel, conditional).

Workflows Tutorial

Mon, 01 Jan 0001 00:00:00 +0000

Tutorial on defining graph-based multi-agent workflows with executors and edges.

Workspace setup

Mon, 01 Jan 0001 00:00:00 +0000

Add required workspace secrets for models and tools used by Agent Builder.

XML RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘XMLSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a XML file.

Your First Agent

Mon, 01 Jan 0001 00:00:00 +0000

Step-by-step tutorial to build your first agent with the Microsoft Agent Framework.

YouTube Channel RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘YoutubeChannelSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube channel.

YouTube Video RAG Search

Mon, 01 Jan 0001 00:00:00 +0000

The ‘YoutubeVideoSearchTool’ is designed to perform a RAG (Retrieval-Augmented Generation) search within the content of a Youtube video.

Zapier Actions Tool

Mon, 01 Jan 0001 00:00:00 +0000

The ‘ZapierActionsAdapter’ exposes Zapier actions as CrewAI tools for automation.

Zapier Trigger

Mon, 01 Jan 0001 00:00:00 +0000

Trigger CrewAI crews from Zapier workflows to automate cross-app workflows

Zendesk Integration

Mon, 01 Jan 0001 00:00:00 +0000

Customer support and helpdesk management with Zendesk integration for CrewAI.