Guides & Tutorials
Practical, step-by-step tutorials that take you from beginner to production-ready. Follow the recommended order or jump to what you need.
Getting Started with Agents
Your first steps into the world of AI agent development. Understand what agents are, how they work, and build your first one.
Getting Started with Agents (Python)
Build your first AI agent with Python. Learn agent fundamentals, set up your environment, and write a working agent with tools.
Getting Started with Agents (TypeScript)
Build your first AI agent with TypeScript. Learn agent fundamentals, set up your environment, and write a working agent with tools.
Your First Agent in 5 Minutes
Build a working AI agent from scratch in under 5 minutes using the OpenAI Agents SDK or Anthropic SDK.
Choosing Your Stack
Pick the right framework and tools for your specific use case with a clear decision matrix.
Multi-Agent Architecture
Design and build systems with multiple collaborating agents using supervisor and peer patterns.
Building MCP Servers
Create Model Context Protocol servers that expose tools and resources to Claude and other MCP-compatible clients.
Prompt Engineering for Agents
Craft system prompts that make your agents more reliable, capable, and predictable.
Guardrails & Safety
Implement safety measures including input validation, output filtering, content moderation, and human-in-the-loop checkpoints.
Observability & Monitoring
Monitor agent behavior, trace execution, log tool calls, and set up alerting for production agent systems.
Evaluation & Testing
Test agent performance with unit tests, integration tests, benchmarks, and regression suites.
Production Deployment
Ship agents to production with proper architecture, containerization, scaling, cost optimization, and reliability.
Cost Engineering
Control GenAI and agent spend with model routing, caching, token budgets, attribution, and operational guardrails.
Governance & Compliance
Design GenAI systems with auditability, policy enforcement, approval controls, and compliance-aware operational boundaries.
Dataset & Prompt Versioning
Version prompts, evaluation datasets, and retrieval logic so GenAI behavior changes are reviewable, testable, and reproducible.
GenAI Product UX
Design user-facing GenAI experiences with streaming, partial results, uncertainty handling, evidence display, and human handoff.
Framework Cookbook: Support Copilot
See how the same support-copilot workflow maps across OpenAI Agents SDK, LangGraph, PydanticAI, and Vercel AI SDK.
Case Study: Support Agent
A production case study for a customer-support agent with retrieval, policy checks, drafts, and human escalation.
Case Study: Research Agent
A production case study for a research agent that searches, reads, synthesizes, and cites across large information sets.
Case Study: Coding Agent
A production case study for a coding agent that reads repos, plans edits, runs tools, and validates changes before handoff.
Case Study: Document Workflows
A production case study for document-heavy GenAI systems that extract, review, route, and transform files at scale.