Screen Amazon brand listings with Gemini Flash and Claude, but still read the P&L

PartialEvidence: Described by posterPosted Apr 16, 2026Last checked Nov 5, 2026

Alex Willen screens Amazon brand listings with Gemini Flash and Claude, but ChatGPT missed a P&L that put ad spend in revenue.

Source checked Nov 5, 2026
Results shared
Limitations noted

How to use this

Tap Copy prompt.
Open Gemini.
Paste it into the message box.
Send it, then read the answer before acting on it.

New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

Review this business-for-sale listing and its attached files against my acquisition criteria. If anything disqualifies it, lead with that. Otherwise give me pros and cons, where I could improve the business, and questions to ask the seller. Check the P&L for structural errors, such as expenses entered as revenue.

Try this in:

ChatGPT Used in source Gemini Used in source Grok Claude Used in source

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Screen business-for-sale listings quickly and get a first-pass evaluation of the ones worth a call.

Questions to ask me first:
- What are your hard disqualifiers (price, revenue, category, platform)?
- Which files come with a typical listing?
- How should ambiguous listings be handled?

Inputs (fill in or confirm):
- Listing text and files: [ATTACHMENTS]
- Acquisition criteria: [LIST]
- Disqualifiers: [LIST]

Rules:
- Lead with any disqualifier and quote the line that triggered it.
- When unsure, keep the listing and say why.
- Recompute margin from the P&L and flag sign or category errors.
- Never treat seller numbers as verified.

Checkpoint: Show the disqualifier check and recomputed margin before the full evaluation.

If you get stuck: If the P&L is too messy to read, say so and list what clean-up is needed.

Verify before you finish: Compare revenue and ad spend to the platform reports the seller provides.

Output: A one-page evaluation with disqualifiers, pros and cons, improvement ideas and seller questions.

Done when: I know whether to book a seller call and what to ask.

AI tools

Gemini Claude ChatGPT

Outcome

Alex Willen buys small Amazon brands, and most listing emails from Flippa and Empire Flippers aren't a fit. A Google Apps Script written by ChatGPT runs daily, sends relevant emails to Gemini Flash to check each listing against disqualifying reasons (erring toward keeping ambiguous ones), and emails Willen the survivors with good and bad buttons so rejected listings don't come back after price drops. Listings that pass get a long evaluation prompt in Claude (originally a custom GPT in ChatGPT) that returns disqualifiers or pros, cons, improvement ideas and questions for the seller. The weak spot is messy seller P&Ls: one seller listed ad spend as revenue, so margins were 0%, not 30%, and ChatGPT didn't catch it. Willen still reads every P&L and uses an Excel AI agent to clean up bad spreadsheets first.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Known limitations

PartialThe source says it only partly worked, or had a significant problem a person had to deal with.

What went wrong: Gemini Flash and Claude handle screening and first-pass evaluation, but ChatGPT missed a P&L that listed ad spend as revenue, so Willen still reviews every P&L.

Source

Posted: Apr 16, 2026 by Alex Willen
Last checked: Nov 5, 2026
Method:: How we verify

https://theautomatedoperator.substack.com/p/15-ways-im-using-ai-to-manage-my

Context: One of several workflows in the post; this case covers listing screening and evaluation only. The Excel agent mentioned is a separate product. Self-reported.