Cheatcode_
Feedback

Front page / By role / Learn about users

Learn about users

Use interviews, analytics and feedback to see the problem from the user's side.

For Product designer · Parallel readers, one writer

What should be pulled out of your notes?

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

It never leaves this computer: not uploaded to Cheatcode, never used to train a model. Your AI app reads it from the case folder.

Add details (optional)
Start

Step 1 asks anything else it needs, in your AI app. Nothing you write here or put in the case folder comes to Cheatcode.

In the case folder's materials/: The transcripts, notes, tickets or documents to read.

The 4 steps

  1. 01

    Check the materials and schema

    Then you approve, before the next step starts.

  2. 02

    Extract per file

  3. 03

    Merge and verify

    Then you approve, before the next step starts.

  4. 04

    Write up

How it does this well

Map one extractor per file into a fixed schema, reduce in code, verify every quote. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well
  • Give synthesis the study context: goals, research questions and prior findings, or trivial findings crowd out useful ones.
  • Keep participant words apart from interpretation, and tie each finding to participant, session and timestamp.
  • Code with a small set of described tags.
  • Critique only against a named checklist the agent can detect reliably, and mark each item observed or inferred.
Ground it first

Ask for, or look in materials/ for: the study goals and research questions, participant details, and the design principles or checklist to judge against. If there is none, say plainly that the result rests on general defaults, and name them.

What stays with the person

Interpretation, prioritization against the study goals, and design decisions. Prepare these; never decide them.

The check that makes it trustworthy

Each finding links to participant, session and quote, and critique is limited to a named checklist.

The person's own data

If the person has connected Figma, Miro, Notion, Lucid, 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/.

The agents

extractor
Extracts structured items from one file of a Cheatcode case into a fixed schema, each with its exact quote and location.

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.