Cheatcode_
Feedback

Front page / By role / Understand the objectives

Understand the objectives

Learn what decision the work supports and how success is judged.

For Data scientist · Knowledge pack and an independent checker

What are you writing?

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 notes, documents or past examples it should rest on.

The 5 steps

  1. 01

    Gather and frame

    Then you approve, before the next step starts.

  2. 02

    Outline

    Then you approve, before the next step starts.

  3. 03

    Draft

  4. 04

    Independent check

  5. 05

    Finish

How it does this well

One writer from the person's material, checked by a fresh reader. Not found and out of scope are valid answers here: it says so instead of guessing.

How the field does this well
  • Use the person's governed definitions; when a question falls outside them, say it is not defined rather than improvising a join.
  • Compute every number with code that reruns from the raw files; never type a number.
  • Write the plan first, run it step by step, and keep known data quality facts and statistical guardrails in one rules file.
  • Check numbers deterministically: a judge accepts near misses that code rejects.
Ground it first

Ask for, or look in materials/ for: the metric definitions (a semantic layer, a definitions doc or a dbt project) and the known data quality issues. If there is none, say plainly that the result rests on general defaults, and name them.

What stays with the person

Choosing between competing definitions and deciding whether a result is decision grade. Prepare these; never decide them.

The check that makes it trustworthy

Every reported number traces to a named definition and a script that reruns, and out of scope questions are answered as not defined here.

The person's own data

If the person has connected BigQuery (managed remote), Snowflake, Databricks, Postgres, dbt, Amplitude, Mixpanel, PostHog, Google Analytics 4, Looker, Metabase, Hex, Tableau, Power BI, 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

checker
Checks a Cheatcode draft against its brief and its claims with fresh eyes, pass or fail per criterion.

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.