# The Model Spec

One screen for one run-time feature. Fill each field in a plain sentence. When it is full, paste it into the "Where AI fits" section of your Build Plan.

---

**The job.** _One feature, in one sentence, and the run-time role it plays (it generates content for the user, or it works behind the scenes)._

>

**The model.** _Which model and tier, and the one reason it fits: capability, cost, speed, context window, or privacy._

>

**The prompt.** _Where the prompt lives in your code, and its rules: what it must never do, and the format you need back._

>

**The output.** _The shape your code expects (the fields and their types), and the value checks you run before acting on it._

>

**The context.** _How the model gets your facts: stuffed into the prompt, retrieved, or none needed._

>

**The lever.** _Which rung of the customization ladder you stopped at (instructions, context, tools, fine-tuning), and why you did not climb higher._

>

**The fallback.** _The spend cap, and what the feature does when the model is slow, down, or clearly wrong._

>

---

A field you cannot fill is a decision still open. The chapter that settles each one:

- The job — Where AI fits in your product
- The model — Choose a model you can live with
- The prompt — Prompting is engineering, not wording
- The output — Get output you can build on
- The context — Give the model the facts it wasn't trained on
- The lever — The customization ladder
- The fallback — Wire the model into your build

Keep it to one screen. If it runs longer, the feature is doing more than one job.