Bullshit Detector – agent skills that fact-check videos and articles: SKIP, 42/100 | Ideas Lab

An AI agent that automatically fact-checks claims in videos and articles to identify false or misleading information.

The pain

People consume misinformation daily through videos and articles. Manual fact-checking is time-consuming. Platforms struggle to moderate at scale. Readers have no quick way to verify claims before sharing.

The gap

Existing fact-checking is done by humans (slow, expensive, limited coverage) or basic keyword matching (inaccurate). No seamless agent that integrates into reading/watching workflows and provides real-time verification with source citations.

Build angle

Start as a browser extension or embed for news sites that flags suspicious claims with confidence scores and source links. Focus on high-volume claim types (statistics, quotes, dates) rather than complex political narratives. Measure success by false positive rate and user trust metrics, not just detection volume.

Strengths

Clear user need, misinformation is a real problem people complain about
Technical feasibility, LLMs can cross-reference claims against knowledge bases
Multiple revenue paths, B2B (publishers, platforms), B2C (subscription), API licensing
Defensible if you build proprietary fact-checking data or source networks

Risks

Accuracy is binary, one wrong fact-check destroys credibility permanently
Liability exposure, flagging something as false could invite legal challenges
Competing against established fact-checkers (Snopes, FactCheck.org) with brand trust
LLMs hallucinate and confidently state false information, requires expensive human review loop
Vague MVP, 'agent skills' doesn't specify what claims it catches or how it integrates
Adoption friction, users must install extension or platforms must integrate API
False positive rate likely too high initially to be useful without heavy curation

Fly Labs Method

Is the pain real, is there a gap, is it the right time, can one person build it.

42

Value Equation

Dream outcome and how likely it feels, against the time and effort it costs.

35

One-Person Business

Curiosity pull, identity fit, and a path from free value to paid for a solo creator.

55

Viral Frameworks

Hook strength, shareability, and how cheaply it can be tested.

48

Builder Lens

Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.

52

Five lenses, one composite. How scoring works

The angle

Start as a browser extension or embed for news sites that flags suspicious claims with confidence scores and source links. Focus on high-volume claim types (statistics, quotes, dates) rather than complex political narratives. Measure success by false positive rate and user trust metrics, not just detection volume.

No market research recorded for this idea yet.

SaaS founders lack a platform for finding partners and organizing joint advertising campaigns with bloggers to reduce costs by 5 times while maintaining the same reach

Other

BUILD

85FL score

Founders waste hours daily on repetitive tasks that AI could automate instantly

Founders spend excessive time on routine tasks that AI could complete in minutes, but no simple, purpose-built tool exists to handle them automatically without complex setup.

Other

BUILD

82FL score

Owners of modern Macs can't launch old games due to complex instructions involving emulators and file conversion

Other

BUILD

79FL score

All Other ideas