Find and assess partners

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.

The 4 steps

1. 01

   Plan the research

   Then you approve, before the next step starts.

2. 02

   Research in parallel

3. 03

   Check every claim

   Then you approve, before the next step starts.

4. 04

   Write it up

How it does this well

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

• Research in a waterfall: the cheapest source first, move on only when it returns nothing usable, validate before use.
• Specify for every lookup what to find, where, the format, and what to return when it is not found.
• Build briefs section by section from named sources, with the buyer's own words where they exist.
• A wrong fact is worse than a missing one: not found is an allowed answer.

Ground it first

Ask for, or look in materials/ for: the ideal customer profile, the offer, and the accounts or deals in question. If there is none, say plainly that the result rests on general defaults, and name them.

What stays with the person

Which accounts to pursue, the message actually sent, and relationship judgment. Prepare these; never decide them.

The check that makes it trustworthy

Every personalization fact carries its source and date, and a sample is spot checked before anything goes out.

The person's own data

If the person has connected Salesforce, HubSpot, Gong, Google Drive / Docs / Sheets, Slack, 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/.

Also from people

• Use structured instruments: the same questions, planned follow ups and a four level rubric with example answers.
• Remove names, photos and other proxies for protected traits in a script before any model reads a candidate's material. Keep the record IDs the person works with (employee, ticket or case numbers) so every finding names the row they will fix.
• Score only against the written rubric with evidence quoted.
• Draft instruments and plans; never rank people.
• What stays with the person here: every screening, hiring and people decision, and defining the role's attributes.
• The check here: proxies redacted before the model reads anything about a person, and every judgment quoted against the rubric.

The agents

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.

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.