Real Agent Cases

Fact-check a viral research-paper claim with Claude in Chrome

Posted
by @seriesfusion
Last checked
Method:
How we verify

Evidence: Screenshots or logsThe source shows screenshots, a transcript or the agent's output.

Outcome

Asked to fact-check a post claiming Bitcoin would 'surge 500%' based on a study, Claude for Chrome reported in about 2 minutes that the paper wasn't in any academic database, the 500% maths was wrong, a commenter said it was AI-generated, and the paper itself said it wasn't a prediction.

Poster says:About 2 minutes

This is the source's own number. We haven't measured it.

Agent

Claude in Chrome

Prompt Recreated prompt

The source didn't share its exact prompt, so we wrote this from what it describes.

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: Check whether a viral claim that cites a study is true.

Quick-check questions: Which post, and what exactly is being claimed?

What I need from you:
- Link to the post ([URL])

Rules:
- Look for the cited paper in academic databases (e.g. Google Scholar) and on the publisher's site.
- Recheck any numbers in the claim yourself.
- Quote what the source actually says, with links.
- Check the date of the original post and the study.
- Find the original paper and quote the exact sentence or figure the claim relies on.
- Say whether the claim is supported, overstated or wrong, and explain in two sentences.

Output: A verdict (true / misleading / false), each finding with a link, and what the original source really says.

If my answers leave a gap, make a sensible choice, say what you assumed, and keep going.

You'll know it worked when: you can open every link and see the evidence for the verdict.

Source

https://x.com/seriesfusion/status/2005052460457754963

  • Working from the family's archive scans, Claude Code with memory and the Claude browser plugin cross-checked church books, ship manifests and naturalization records, built a 300-page family wiki, and found two more generations in a day; the family is now checking it for errors.

    Poster says:300-page family wiki

    Claude Code, Claude in Chrome, Perplexity Comet · Research · Source date:

  • Report global NAND market share with Gemini Deep ResearchImproved promptEvidence: Screenshots or logsFailure

    Asked for a simple report on global NAND market share, Gemini Deep Research returned figures the poster called an incredible failure when compared with Sandisk's investor-day slide and Claude's answer to the same query.

    Gemini Deep Research · Research · Source date:

  • Write a one-page sales brief on a target company with ManusRecreated promptEvidence: Article or interview

    Asked for a B2B sales brief on Google for a tl;dv pitch, Manus produced a one-page brief with revenue, tech stack, key decision makers, recent announcements and a sourced section mapping Google's pain points to tl;dv features; the reviewer says it took two minutes.

    Poster says:About two minutes

    Manus · Research · Source date: