three.dev
Notable signalFind out how your AI agent fails. Before your users do.
Launched 21h ago
Signal
59
Velocity
21
What this means
36%Mid-tier finish likely.
Projecting attention of 113 by end of day-1.
Prediction
Top-5 finish probability
36%
today
Projected end-of-day votes
113range 85–153
Trajectory
stable
Vote pace holding steady.
About
Almost every team now runs AI in production, but few know how it behaves once real users show up. The failures are quiet: a wrong refund policy, a made-up order status. Nothing crashes, so you hear about it from your users. three.dev finds those failures in your live traffic on its own and ranks them by severity. Setup is one prompt to Claude Code, Cursor, or Codex. Then your coding agent gets what it needs to write the fix.
AI Summary
three.dev is an analytics tool that identifies and ranks failures in AI systems based on live user interactions. It integrates with coding agents like Claude Code, Cursor, or Codex to facilitate prompt fixes.
Attention & discussion velocity
Performance
Velocity21
Vote pace vs average
Momentum37
Sustained over 6h
Virality21
Spread × engagement
Engagement22
Discussion per unit of attention
Editorial read
Scored deterministically. Only candidates that fire a story trigger are sent to a model, so this one has no written angle.
ThinLittle evidence and no strong angle. Nothing to build on yet.
125/8
Timeliness5%100
carried 7%
Trend20%31
carried 27%
Novelty15%26
carried 20%
Business15%12
carried 20%
Story20%0
carried 27%
Not measured · 3 of 8
Revenue10%—
Founder10%—
Cross-platform5%—
Gaps in our data, not findings about the product. Their weight is redistributed across the 5 we did measure.
measuredmeasured, zeronot measured
Full audit →Signal sources
3 of 6 active- Launch tracking4 readings since we picked it up
- AI analysisAI Agents
- Comment intelligencethread not yet analysed
- Outside discussionnot checked — domain is a storefront or shared
- Revenue signalsno match on this domain
- Editorial scoring28% evidence coverage
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.
