Prompt Engineering Across Providers

Master prompt engineering by studying best practices from Anthropic, OpenAI, and Mistral. Then see how DSPy challenges the entire paradigm by replacing prompts with programs.

Comparing approaches across providers gives you deeper intuition than studying any single provider’s guide.

OpenAI API Essentials

Learn the OpenAI API from first request to advanced features. Covers Chat Completions, function calling, structured outputs, streaming, vision, reasoning models, and embeddings.

Claude API Essentials

Learn the Anthropic API from first principles. Covers the Messages API, tool use, streaming, structured outputs, extended thinking, and cost optimization.

MCP Fundamentals

Go from zero to a solid understanding of the Model Context Protocol. This path covers the core architecture, primitives (tools, resources, prompts), transport mechanisms, and how clients and servers interact.

By the end you’ll understand the MCP mental model well enough to evaluate MCP servers, build simple integrations, and read the specification confidently.

Claude Code Mastery

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.

Spec-Driven Development Fundamentals

Learn the specification-driven development methodology from concept through practice. Understand why SDD emerged alongside AI coding tools, how to write effective specifications, and how to use tools like GitHub Spec Kit to formalize the workflow.

Prerequisites: Familiarity with Claude Code (complete Claude Code Mastery first) helps you apply SDD concepts immediately, but is not strictly required.

The Agentic Protocol Stack

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.

Building MCP Servers

Learn to build production-quality MCP servers. This path takes you from a basic server implementation through transport selection, security, and publishing to the registry.

Prerequisites: Complete the MCP Fundamentals path first to understand the protocol architecture.

RAG from Scratch

Build a complete Retrieval-Augmented Generation pipeline from the ground up. Learn embeddings, vector search, reranking, and how to wire retrieval into LLM generation with citations.

This path draws on Cohere (strong RAG docs), Pinecone (vector DB), and LangChain (orchestration).

Vision & Multimodal AI

Build applications that understand and generate images, documents, and audio. This path covers vision capabilities across 5 providers, document processing, image generation, multimodal embeddings, and audio — the complete multimodal toolkit.

The key cross-provider insight: each provider has different vision strengths. OpenAI offers the broadest multimodal coverage (vision + generation + audio), Anthropic excels at document understanding, Cohere provides multimodal embeddings for search, and Mistral/Together AI offer cost-effective open-source alternatives. Choosing the right provider per modality can dramatically improve both quality and cost.

Agent SDK Deep Dive

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

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.

Evaluation & Testing

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

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.

Deployment to Production

Take AI applications from prototype to production. This path covers the full deployment journey across providers: production checklists, rate limit management, batch processing for cost reduction, and agent-specific deployment patterns.

The key cross-provider insight: every provider has rate limits, batch APIs, and deployment recommendations, but the specifics differ meaningfully. Learning both OpenAI and Anthropic patterns helps you design resilient systems, and understanding framework deployment (LangGraph, CrewAI) is essential for agent-based applications.

Cost Optimization

Minimize AI application costs without sacrificing quality. This path covers the complete cost optimization toolkit: model selection, token counting, prompt caching, and batch processing — comparing approaches across Anthropic and OpenAI.

The key insight: cost optimization is not about using cheaper models everywhere. It’s about matching the right model to each task, caching repeated content, batching non-urgent work, and measuring token usage to eliminate waste. A well-optimized pipeline using GPT-4o-mini + caching can cost less than a naive GPT-3.5 implementation.

Fine-Tuning Across Providers

Master fine-tuning across multiple providers — from data preparation to training to deployment. This advanced path covers OpenAI, Mistral, and Together AI’s fine-tuning workflows, with W&B for experiment tracking.

Fine-tuning is a powerful but expensive technique. This path emphasizes the decision framework (when to fine-tune vs alternatives), practical data preparation, and cross-provider comparison of capabilities, costs, and workflows. LoRA and reinforcement fine-tuning expand the toolkit beyond basic supervised fine-tuning.

AI Architecture for Technical Leaders

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.

AI Vendor & Platform Evaluation

A systematic framework for evaluating AI providers, platforms, and build-vs-buy decisions. This path equips technical leaders with the analytical tools to compare vendors across capability, cost, deployment, and strategic dimensions — going beyond feature matrices to assess lock-in risk, deployment flexibility, and long-term platform strategy.

By the end of this path, you’ll be able to: build comparative cost models across providers, structure vendor evaluation around the accuracy-latency-cost tradeoff triangle, assess deployment topology requirements, and frame build-vs-buy recommendations with supporting market data.

AI Cost Modeling & Unit Economics

A practical guide to AI cost modeling and unit economics for technical leaders who need to build defensible financial projections. This path bridges the gap between per-token API pricing and board-level business cases, covering macro AI economics, provider pricing structures, token consumption drivers, optimization levers, and ROI frameworks.

By the end of this path, you’ll be able to: build per-query cost models for AI features, project AI infrastructure costs at scale, identify the highest-impact cost optimization levers (which are architecture decisions, not tuning exercises), and construct ROI analyses that connect engineering costs to business value.

AI Risk & Safety for Technical Leaders

A bridge between engineering safety practices and board-level risk governance for technical leaders who need to evaluate their team’s safety architecture and communicate residual risks to stakeholders. This path covers hallucination mitigation, data protection, enterprise guardrails, regulatory compliance, and production readiness assessment.

By the end of this path, you’ll be able to: evaluate whether your engineering team has implemented defense-in-depth safety, assess compliance requirements under the EU AI Act, conduct technical due diligence on AI projects before production deployment, and translate engineering risk into board-level governance language.

AI Landscape for Product Leaders

A non-technical introduction to the AI provider landscape for product managers, executives, and business leaders. This path builds your understanding of what AI models can do, how they’re priced, and how to think about provider selection — without requiring any coding knowledge.

By the end of this path, you’ll be able to: evaluate AI provider options, understand cost structures for budgeting, and frame build-vs-buy decisions for your organization. You’ll have the vocabulary and mental models to discuss AI capabilities with your engineering team and present AI strategy to leadership.

AI Use Cases & Business Applications

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

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 Safety & Risk for Decision-Makers

A concise path for executives, product leaders, and board members who need to understand AI risks and safety without technical depth. Covers data privacy, hallucination risk, safety engineering principles, regulatory compliance (EU AI Act), and responsible AI governance.

By the end of this 2-hour path, you’ll understand the key risks of deploying AI in production, what questions to ask your engineering team about safety measures, and how to establish an AI governance framework for your organization.