Watch trends and competitors

What do you report on?

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/: This period's data and the previous report.

The 3 steps

1. 01

   Set up the report

   Then you approve, before the next step starts.

2. 02

   Compare with last time

3. 03

   Explain and write

How it does this well

A fixed pipeline: change since last time in code, the agent explains. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well

• Run brief, draft, edit, then brand review; the brief states audience, goal and the one message.
• Make voice rules checkable: behaviors and banned phrases, not adjectives.
• Verify every statistic, quote and brand reference before publishing.
• Back attribution claims with an experiment, or label them as correlation.

Ground it first

Ask for, or look in materials/ for: the brand voice rules (positive rules and banned phrases), positioning, and past results. If there is none, say plainly that the result rests on general defaults, and name them.

What stays with the person

Positioning, claims approval, and the final publish decision. Prepare these; never decide them.

The check that makes it trustworthy

A lint pass against the voice rules and banned phrases, every factual claim linked, and attribution claims labeled.

The person's own data

If the person has connected HubSpot, Google Analytics 4, Google Drive / Docs / Sheets, Notion, Figma, 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/.

Where things stay

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.