Read quality

Every read-engine change runs the same filter.

Most poker tools eyeball the output of their AI and ship it. PokerReads doesn't. Every change to the read engine runs through the same set of gates: poker-correctness checks, frozen-champion comparison, founder review. Only then does it touch production. The bar only goes up because every update has to clear it cleanly.

Tested Every read change
Compared Against the live engine
Founder-approved No silent promotions
Regression tested Misses become permanent tests
Plain English: PokerReads does not claim every read is right. Read-engine changes run through poker-specific checks before production, and the founder compares candidate output with the shipped version on privacy-redacted evidence. Rejected cases can become regression fixtures, but tests reduce known mistakes rather than guaranteeing perfection.

Test before ship, every release.

PokerReads runs deterministic poker-correctness checks on every read-engine change: variant preservation, PLO exact-card discipline, mixed-game boundaries, citation safety, sample-size honesty. The check has to clear before a new prompt is even considered for production.

A new read must beat the shipped one.

Internal challengers compare against the engine that is currently live. If a candidate sounds sharper but breaks evidence discipline or poker correctness, it stays blocked. A change needs evidence of improvement, not a better-sounding paragraph.

The founder signs off on every promotion.

No read-engine change ships from internal scores alone. The founder reads candidate output side-by-side with the live engine on real, privacy-redacted evidence before any promotion. Fail-closed by design: the default when in doubt is to keep what's shipped.

Misses become permanent tests.

When a read change exposes a reproducible poker-correctness, evidence-safety, or sample-size failure, that case can become a fixture in the test suite. The fixture guards that known case; it does not prove that every future read is correct.

What we won't claim.

  • We don't say the engine is the best. We say it's been tested.
  • No production prompt change ships from internal scores alone: the founder reads every promotion candidate.
  • Reproducible misses become regression fixtures where a deterministic test can protect the behavior.
  • Public claims about new gates (cross-model judging, predictive lanes, observed-feedback fixtures) wait until those gates actually clear production. If we haven't done it yet, it doesn't go on this page.

Want to inspect the product instead? Start with the real Ronan sample read, then bring your own notes when you're ready.

Read the Ronan sample