Sonah

Early signal

Reviews what your coding agent did, not just the diff

Launched 17d ago

Signal

Velocity

What this means

+65%Launching in a 65% WoW growing category.

Software Engineering had 28 launches this week vs 17 last.

11Founder Conviction Index: 11 — low signal.

Few of the conviction sub-signals (reputation, velocity, buyer-intent, tagline clarity) are firing yet.

Prediction

Top-5 finish probability

today

Projected end-of-day votes

10range 8–14

Trajectory

stable

Vote pace holding steady.

Speed vs peers

0.9×

23 Coding Tools launches

About

Coding agents rewrite code you never asked them to touch, and the tests still pass. Sonah reads the agent’s Claude Code or Codex session along with the code, then shows on one page: whether each ask was done, what the agent decided on its own, which of its claims its own results contradict, and what is wrong in the code. Every quote is checked word for word. Runs locally through your own Claude login. No account, no telemetry. Free for individuals.

AI Summary

Sonah analyzes the actions of coding agents by reviewing their sessions alongside the modified code, highlighting discrepancies and errors. It operates locally using your Claude login, ensuring no account creation or telemetry is required, and is free for individual users.

Attention & discussion velocity

Performance

Velocity0

Vote pace vs average

Momentum0

Sustained over 6h

Virality0

Spread × engagement

Engagement40

Discussion per unit of attention

Signal sources

2 of 6 active

Launch tracking9 readings since we picked it up
AI analysisCoding Tools
Comment intelligencethread not yet analysed
Outside discussionnot checked — domain is a storefront or shared
Revenue signalsno match on this domain
Editorial scoringbelow the signal threshold for this pass

A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.