hello·ai

Phase 4 of 4

Systems

How do I run this in production?

Loops, tools, queues, budgets and the failure modes that only show up under load. Ordinary distributed systems work, with one unusual component in the middle.

Topics in this phase

  1. Agents & tool use

    7 minUnread

    A loop where the model picks a tool and your code decides whether to run it, and every interesting problem is in the loop rather than in the model.

    After Structured output, Evals

  2. Workflow patterns

    6 minUnread

    Four shapes for composing model calls, ordered by how much control flow you hand over — and the right default is the one that hands over the least.

    After Agents & tool use

  3. Serving & batching

    6 minUnread

    Decoding is bandwidth-bound, so one read of the weights can serve many requests at once — and that single fact is what makes the economics work.

    After Prefill & decode, KV cache

  4. Cost & latency levers

    6 minUnread

    Six levers, three of which need no infrastructure at all and are almost always tried last.

    After Prefill & decode, Context engineering

  5. Observability

    6 minUnread

    Aggregate metrics tell you something regressed; only a trace of the whole chain tells you which of six stages did it.

    After Agents & tool use, Evals

  6. Failure modes

    6 minUnread

    The failures that matter here do not raise exceptions — they return 200 with the wrong thing — so the defences are structural rather than reactive.

    After Observability, Agents & tool use

Examples that open after this phase

Problem statements that make sense once these topics are done. They unlock at the same 80% mark the next phase does.