hello·ai

Phase 3 of 4

Building with it

How do I compose a system around a non-deterministic component?

The model is one call in a larger system. This phase is the engineering around it: what you put in the context, what you get back, and how you know it works.

Topics in this phase

  1. Retrieval & RAG

    7 minUnread

    Fetch the relevant text at request time and put it in the prompt, because almost everything worth answering about is either private, recent, or needs a citation.

    After Embeddings, Vector space intuition

  2. Vector indexes

    6 minUnread

    An index that is allowed to be wrong, where the tuning dial is recall and correctness is something you measure rather than assume.

    After Vector space intuition, Retrieval & RAG

  3. Context engineering

    6 minUnread

    Deciding what occupies a finite window, in what order, on every call — and it is mostly a discipline of leaving things out.

    After Prefill & decode, Retrieval & RAG

  4. Structured output

    6 minUnread

    Getting a schema-valid object back instead of prose, so the boundary between the model and your code stops being a parsing problem.

    After Context engineering

  5. Evals

    6 minUnread

    Automated tests for a component whose output is not stable, where the assertion is a threshold on a score and the suite is the only thing making changes measurable.

    After Structured output

  6. The adaptation ladder

    6 minUnread

    Five ways to make a general model fit your task, ordered by cost and by how hard each is to undo — and the discipline is to stop climbing the moment the evals stop improving.

    After Training vs inference, Evals

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.