LegitShow is the trusted source on every launched service — web apps, SaaS, AI tools, MCP servers and developer tools: what each one does, who it’s for, and how it actually holds up, measured by an objective 7-Frame production-readiness benchmark taken deterministically from the public surface. How we measure →


Legit.Show benchmarks every launched service it lists — measured deterministically from the public surface. See the methodology →

Cross-links · Directory · Reports · Insights · What AI reads · Methodology · About

Privacy · Terms · @Legit_Show on X · GitHub · operated by Madeflo Inc., a Delaware corporation. Benchmark engine powered by commit.show.

AI & Agents

Prefactor

Last updated 2026-07-28 · benchmark checked 2026-08-09 · unchanged since 2026-08-08 — deterministic & reproducible

AI agent observability, evaluation, and enforcement platform with usage-based pricing.

91/100
Legit Benchmark — the simple average of 7 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.

Is Prefactor production-ready?

Legit.Show scores Prefactor 91 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Prefactor (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Performance. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

What we measured

Who built it

Ethan Lee (@ethan_leee9113)

Who it's for

Developers · Product managers · AI security & governance teams · Enterprises running agents · Founders building AI applications

Pricing

Dev: Free (25k spans/month). Scaleup: $250/month or $9,600/year (first 100k spans, then $2.50 per 1k spans up to 4M/month). Enterprise: 4M+ spans/month with custom rates and step-down pricing.

Visit Prefactor → · Alternatives to Prefactor → · How this was measured →

See how Prefactor ranks among tested llm observability products →