Guides for engineers building AI agents in production.

Long reads with running code, each written from a lab or a client build. Pick a topic, read the guide, then build it live on Thursday.

Join Thursday's free lab

Every guide links the repo its code comes from.

    Every guide, by topic

    Agents and workflows

    1. AI agents vs workflowsAI agents vs workflows is the first call in any AI system.10 min
    2. Giving your LLM hands, a deep dive on tool callingLearn how to build agents that can interact with the real world using tool calling.6 min
    3. Prompt self critique and refinementLearn how to improve LLM output quality using Self-Critique and Refinement techniques.4 min

    Claude Code

    1. Safe shell execution for coding agentsBuild a bash tool for coding agents that is safe, scoped, and timeout-bounded.9 min

    MCP

    1. Build a production MCP serverHow to build an MCP server that holds up in production: transport, OAuth audience checks, typed small results, tool design and a person on every write.9 min

    RAG

    1. Fact checking and groundingFact-check RAG answers with a second LLM pass verifying every claim against retrieved context.7 min
    2. Tuning the retriever k valuePick the right top-k for your RAG retriever.6 min
    3. FAISS in productionUse FAISS for production RAG.6 min
    4. Chain types for summarisationStuff vs Map Reduce vs Refine in LangChain.9 min
    5. Multi hop RAG with query decompositionLearn how to build multi-hop RAG agents that can decompose complex queries into sub-questions and chain multiple retrieval steps.5 min
    6. Batteries included RAG platformsCompare batteries-included RAG platforms that bundle the entire pipeline into one application.8 min
    7. Choosing a RAG frameworkDemystify RAG frameworks by understanding their core philosophies.8 min

    Production and observability

    1. Retry patterns for LLM API errorsBuild retry logic that handles rate limits, timeouts, and transient failures without burning money.7 min
    2. Langfuse and Grafana monitoringCombine Langfuse traces with Grafana dashboards for production agent monitoring.6 min
    3. FastAPI with LangGraph for a chatbot APIWire LangGraph into a FastAPI chatbot API with streaming, per-user thread persistence, and the production patterns beyond the demo.6 min
    4. Prometheus metrics for agentsInstrument agentic AI with Prometheus.8 min
    5. LangGraph persistence and threadsHow LangGraph persistence and the postgres checkpointer keep agent state across restarts.10 min
    6. Separate development and production configWhy your agent needs .env.development and .env, not one file.9 min
    7. FastAPI and Uvicorn for agentic systemsFastAPI and Uvicorn for agentic AI: ASGI workers, streaming, lifespan, and the production gotchas tutorials skip.9 min
    8. System design for a production AI chatbotMaster end-to-end system design for production AI chatbots.20 min

    Read it, then build it live

    Join Thursday's free lab