Idea and research · Cheatcode

What do you need to find out?

One line is enough. Step 1 asks the rest in your AI app, and nothing is done until you approve the brief it writes.

In the case folder's materials/: Optional: anything you already know, notes or a deck.

Parallel research, one writer, every claim checked. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well: Treat AI output as unvetted source material.
Keep a claims table: claim, source, quote, status; surface evidence, leave verdicts to the person.
Match claims on meaning and on the people, places and organizations they name.
Edit for the audience and the style guide, then fact check before publishing.
Ground it first: Ask for, or look in materials/ for: the style guide, the audience, and the sources the piece may rely on. If there is none, say plainly that the result rests on general defaults, and name them.
What stays with the person: What is worth checking, verdicts, and publication. Prepare these; never decide them.
The check that makes it trustworthy: A claims table where every claim has a source and a verbatim quote, and the verdicts are the person's.
The person's own data: If the person has connected Google Drive / Docs / Sheets, Notion, Microsoft 365 (Excel, SharePoint, Teams), read their data through that connector instead of asking for exports, and say which source each number or fact came from. Without one, work from materials/.

researcher: Researches one sub question of a Cheatcode case from public sources and records every claim with its exact quote and source.
citation-checker: Opens every source in a Cheatcode case's claims files, checks each claim against it, grades it and marks it kept or dropped.

On your computer: Your files in materials/, every result in outputs/, the work itself. It runs in your AI app, on the plan you already pay for.
With Cheatcode: The steps, the gates and how far each case has come, so a case survives closing the app. See your cases.