AI Knowledge Base

  • Catalog
  • Learning Paths
  • Courses
  • Search
  • Glossary
        • Understanding A2A
          • Build an MCP client
          • Build an MCP server
          • Connect to local MCP servers
          • Connect to remote MCP Servers
          • What is the Model Context Protocol (MCP)?
          • Architecture overview
          • Understanding MCP clients
          • Understanding MCP servers
          • MCP Inspector
            • Security Best Practices
            • Understanding Authorization in MCP
        • SDKs
          • Build an MCP App
        • Frequently Asked Questions
        • How to Authenticate When Publishing to the Official MCP Registry
        • How to Automate Publishing with GitHub Actions
        • MCP Registry Supported Package Types
        • Publishing Remote Servers
        • Quickstart: Publish an MCP Server to the MCP Registry
        • The MCP Registry
        • Versioning Published MCP Servers
              • Authorization
              • Lifecycle
              • Transports
              • Sampling
              • Prompts
              • Resources
              • Tools
        • Introduction to the Anthropic Platform
        • Get Started
            • Choosing A Model
            • Migration Guide
            • Overview
            • Content Moderation
            • Customer Support Chat
            • Legal Summarization
            • Overview
            • Ticket Routing
          • Pricing
          • Agent SDK — Overview
          • Cost Tracking
          • Custom Tools
          • Hooks
          • Hosting
          • Mcp
          • Migration Guide
          • Modifying System Prompts
          • Permissions
          • Plugins
          • Python
          • Quickstart
          • Secure Deployment
          • Skills
          • Streaming Output
          • Streaming Vs Single Mode
          • Structured Outputs
          • Subagents
          • Typescript
            • Best Practices
            • Enterprise
            • Overview
            • Quickstart
            • Tool Use — Overview
            • Implement Tool Use
            • Bash Tool
            • Code Execution Tool
            • Computer Use Tool
            • Fine Grained Tool Streaming
            • Memory Tool
            • Programmatic Tool Calling
            • Text Editor Tool
            • Tool Search Tool
            • Web Fetch Tool
            • Web Search Tool
          • Mcp Connector
          • Remote Mcp Servers
          • Build with Claude — Overview
          • Working With Messages
          • Streaming
          • Structured Outputs
          • Extended Thinking
            • Claude Prompting Best Practices
            • Overview
            • Prompting Tools
          • Vision
          • Prompt Caching
          • Batch Processing
          • Pdf Support
          • Skills Guide
          • Token Counting
            • Library
            • Handle Streaming Refusals
            • Increase Consistency
            • Mitigate Jailbreaks
            • Reduce Hallucinations
            • Reduce Latency
            • Reduce Prompt Leak
          • Best Practices for Claude Code
          • Claude Code overview
          • Claude Code settings
          • Common workflows
          • Configure permissions
          • Connect Claude Code to tools via MCP
          • Create custom subagents
          • Hooks reference
          • How Claude Code works
          • Manage Claude's memory
          • Quickstart
          • Run Claude Code programmatically
          • Core architecture
          • Events
          • Introduction
        • MCP, A2A, and AG-UI
                    • Agent definitions
                    • Guardrails and human review
                    • Integrations and observability
                    • Models and providers
                    • Orchestration and handoffs
                    • Quickstart
                    • Results and state
                    • Running agents
                    • Sandbox Agents
                      • Cybersecurity checks
                      • Under 18 API Guidance
                    • Agent evals
                    • API deployment checklist
                    • Audio and speech
                    • Batch API
                    • Computer use
                    • Connectors and MCP servers
                    • Conversation state
                    • Cost optimization
                    • Counting tokens
                    • Data controls in the OpenAI platform
                    • Deep research
                    • Evaluation best practices
                    • File search
                    • Fine-tuning best practices
                    • Function calling
                    • Getting started with datasets
                    • Image generation
                    • Image generation
                    • Images and vision
                    • Model selection
                    • Moderation
                    • Production best practices
                    • Prompt caching
                    • Prompt engineering
                    • Rate limits
                    • Reasoning best practices
                    • Reasoning models
                    • Red teaming
                    • Reinforcement fine-tuning
                    • Reinforcement fine-tuning use cases
                    • Retrieval
                    • Safety best practices
                    • Safety in building agents
                    • Streaming API responses
                    • Structured model outputs
                    • Supervised fine-tuning
                    • Text generation
                    • Trace grading
                    • Using realtime models
                    • Using tools
                    • Vector embeddings
                    • Web search
                    • Working with evals
                    • Developer quickstart
                    • Key concepts
                • Agents
                • Guardrails
                • Handoffs
                • Symphony Overview
                • Symphony Service Specification
                • Elixir Reference Implementation
                • WORKFLOW.md Configuration
                • Orchestration State Machine
                  • Agents Introduction
                    • Embeddings Overview
                  • Function calling
                  • Moderation
                  • Vision
                • A Guide to Streaming Responses
                • Basic usage of tool use (function calling)
                • Building Agentic RAG with Cohere
                • Deployment Options - Overview
                • How do Structured Outputs Work?
                • Introduction to Embeddings at Cohere
                • Master Reranking with Cohere Models
                • RAG Citations
                • Retrieval Augmented Generation (RAG)
                • Retrieval augmented generation (RAG) - quickstart
                • Safety Modes
                • Semantic search - quickstart
                • Semantic Search with Cohere Models
                • Tool use & agents - quickstart
                • Unlocking the Power of Multimodal Embeddings
                • Using Cohere's Models to Work with Image Inputs
                          • Build a multi-source knowledge base with routing
                          • Handoffs
                          • Build a RAG agent with LangChain
                          • Model Context Protocol (MCP)
                          • Retrieval
                            • Build a custom RAG agent with LangGraph
                            • LangSmith Deployment
                            • Memory
                            • Streaming
                            • Thinking in LangGraph
                            • Workflows and agents
                          • Agents
                          • Crews
                          • Production Architecture
                          • Tasks
                            • Programming Overview
                            • Multi-agent systems
                            • Workflow Agents
                    • DeepSeek
                      • Together AI
                            • Agent Framework Overview
                            • Workflows Overview
                            • GroupChat Pattern
                            • Spec-Driven Development
                            • SDD Tools: Kiro, Spec Kit, and Tessl
                            • SDD: Unpacking 2025's Key Engineering Practices
                            • SDD Overview
                            • Spec-Driven Development: When Architecture Becomes Executable
                            • The Rise of Spec-Driven Development
                            • SDD: From Code to Contract in the Age of AI Coding Assistants
                            • TDD vs BDD vs SDD
                            • Build What You Mean, Not What You Guess
                            • My LLM Coding Workflow Going into 2026
                            • How to Write a Good Spec for AI Agents
                            • Vibe Coding Is Not AI-Assisted Engineering
                            • Mastering SDD with AI Workflows
                            • SDD with AI: Open Source Toolkit
                            • Spec-Driven Development Guide
                            • SDD with Claude Code
                            • Getting Started with GitHub Spec Kit
                            • GitHub Spec Kit
                            • Tessl Spec-Driven Framework
                            • Awesome Spec-Driven Development
                            • What Product Managers Need to Know About LLMs
                            • 16 Changes to the Way Enterprises Are Building and Buying Generative AI
                            • Generative AI's Act Two
                            • The EU's AI Act and How Companies Can Achieve Compliance
                            • Designing a Responsible AI Program? Start with this Checklist
                            • Building LLM Applications for Production
                            • What Is an AI Agent?
                            • The Economic Potential of Generative AI: The Next Productivity Frontier
                            • Who Owns the Generative AI Platform?
                            • Generative AI Glossary for Business Leaders
                            • Emerging Architectures for LLM Applications
                            • How 100 Enterprise CIOs Are Building and Buying Gen AI in 2025
                            • The Rise of the AI Engineer
                              • Pinecone documentation
                        • Safetensors
                          • PEFT
                                    • LoRA
                                      • PEFT
                                  • TRL
                                      • SFT Trainer
                                      • TRL - Transformers Reinforcement Learning
                                  • Fireworks AI
                                                  • Training Overview
                                                  • Serverless Quickstart
                                                          • Pydantic AI
                                                                    • Instructor
                                                                        • Getting Started
                                                                        • Metrics Introduction
                                                                              • Chroma
                                                                                • RAGAS
                                                                                  • Weights & Biases
                                                                                    • Sources
                                                                                    • Topics
                                                                                    • Difficulty
                                                                                    • Content Types

                                                                                    Orchestration

                                                                                    Orchestration

                                                                                    Agent Framework Overview (0)

                                                                                    AutoGen Overview (0)

                                                                                    Elixir Reference Implementation (0)

                                                                                    GroupChat Pattern (0)

                                                                                    Migration from AutoGen (0)

                                                                                    Migration to Agent Framework (0)

                                                                                    Multi-agent systems (0)

                                                                                    Multi-Agent Systems (0)

                                                                                    Orchestration State Machine (0)

                                                                                    Symphony Overview (0)

                                                                                    Symphony Service Specification (0)

                                                                                    Workflow Agents (0)

                                                                                    Workflow Edges (0)

                                                                                    WORKFLOW.md Configuration (0)

                                                                                    Workflows Overview (0)

                                                                                    Workflows Tutorial (0)

                                                                                    Sign out