Top 1% Engineers, one production AI lesson per issue.

For engineers building with agents. Each issue takes one decision you face at work, shows the code and names the trade off.

Read any past issue before you subscribe.

    Read a past issue

    Every past issue stays free to read, no sign-up needed. Each one takes a single question you hit when an agent goes to production, answers it with code you can run, and names the free Thursday lab where we build it live.

    1. Issue 5Test Prompt Injection in CIHow to test prompt injection in CI: cases by where the text comes in, assertions on tool calls and canaries, repeat runs, and why a pass is not a guarantee.Read it
    2. Issue 4Add LLM Guardrails at the Tool CallLLM guardrails by where they sit: code at the tool call for what must hold, classifiers as a measured signal, and an eval that counts both rates.Read it
    3. Issue 3Split Multi-Agent Systems by ContextMulti agent orchestration in practice: when one agent stops being enough, the patterns and what each one passes along, and why writes stay with one agent.Read it
    4. Issue 2Build 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.Read it
    5. Issue 1AI Agents vs WorkflowsAI agents vs workflows is the first call in any AI system. What each choice costs, how it fails, and the code for the safe default.Read it

    What every issue gives you

    1. One decision, made.

      A question like agent or workflow, answered with a rule you can use.

    2. Code you can run.

      Each issue links the repo.

    3. The next live lab.

      The Thursday lab that builds the topic.

    Get the next issue

    Subscribe