Skip to content
AG-01Building AI agents9 checks · 8 min

What to get right before you build an AI agent

Work through this before anyone writes a prompt. The model is the part of this project least likely to be your problem.

  1. 01

    Name the one job it does.

    An agent that "helps customers" cannot be built or tested. An agent that "answers where-is-my-order and reschedules deliveries" can be. Scope is the single biggest predictor of whether an agent reaches production.

  2. 02

    Decide what it is allowed to do, not just what it can say.

    Reading an order is one risk profile. Issuing a refund is another. Write the list of actions before anything is built, because that list is the security boundary and it is much harder to narrow later.

  3. 03

    Find the source of truth for every fact it will state.

    in the PDF

  4. 04

    Write twenty real examples before you write a prompt.

    in the PDF

  5. 05

    Decide what a wrong answer costs.

    in the PDF

  6. 06

    Define the handoff before the happy path.

    in the PDF

  7. 07

    Decide what it must never do, in writing.

    in the PDF

  8. 08

    Plan how you will know it is getting worse.

    in the PDF

  9. 09

    Work out what it costs at ten times the volume.

    in the PDF

7 more checks in the PDF

The complete checklist — every check with the reasoning under it, the closing note, and the other 12 documents — comes as one PDF.

One email, one PDF, all 13 documents. We don't run a newsletter — unless a new one goes up, that's the only message you'll get.

Before you build

13 numbered documents on scoping software, building it, and taking delivery of it. Free, and free to copy — put them in your own wiki, take them into your own meetings, send them to whoever is about to sign something.

Free to use, share and adapt. No attribution required. © 2026 TechBuilds.