Documentation
Understand every Aiscovery result.
Reference guides for reading your result, reviewing the evidence behind each fix and seeing how we decide a verdict without a single score.
3 min
Evidence and sessions
Review what our checker saw today. Coming later: what each AI agent saw and did, step by step, with sensitive fields masked.
3 min
Verdicts
A verdict is limited to what we tested. Critical fixes stay at the top, and gaps stay visible as Not tested yet or Couldn't check.
Documentation principles
These documents explain the public result contract. Parts about AI agent task tests are marked Coming later until they run for customers.
- 01Observed outcomes stay separate from claims about future agent behavior.
- 02Verdicts are limited to what we tested, without a single score.
- 03Every fix links to what we saw.
- 04Production runs stop before irreversible actions.