AI & Agents

Poisson Labs

Last updated 2026-08-20 · benchmark measured 2026-08-20 — deterministic & reproducible

Poisson Labs maps failure boundaries of AI decision-making systems using sweep-based evaluation.

Is Poisson Labs production-ready?

Legit.Show scores Poisson Labs 71 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Poisson Labs (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 77/100
• Accessibility — 95/100
• Security — 45/100
• Privacy — 25/100
• Reliability — 100/100
• Standards — 92/100
• Discoverability — 62/100

What we measured

• Security headers present: HSTS.
• No Content-Security-Policy.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 172 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

AI researchers · Robotics engineers · ML practitioners · Policy developers

Pricing

$42 per full experiment (sweep + retraining + re-sweep); $0 idle cost; ~0.5 seconds per fresh probe when warm

Visit Poisson Labs → · Alternatives to Poisson Labs → · How this was measured →