Skip to main content

Verification Manual

Insight LM's central claim is an Assistant that shows its work. This Verification Manual applies that standard to the product itself: a growing library of verification entries, each documenting a capability, the method used to verify it, concrete acceptance gates, and the result — including failures.

The model is the verification manual of a classical engineering tool: a numbered, versioned library of problems the tool is demonstrated to solve correctly, re-run as the tool evolves.

Entry format

Every entry carries:

FieldMeaning
VM-IDStable identifier (VM-NNN)
ObjectiveThe user-level capability under verification
MethodHow it was verified — always through the real application as a user would drive it
Acceptance gatesConcrete PASS/FAIL checks defined before the run
ResultPASS / FAIL per gate, with evidence
Authority classA: independently reproducible from the entry alone · B: reproducible with the described fixture setup · C: demonstrated, fixture not yet packaged for reproduction
BuildThe application version the run executed against

Principles

  • Real paths only. Verification drives the actual application; mocked or backend-only checks never count as acceptance.
  • Gates before runs. Acceptance criteria are written down before the run, not fitted to its outcome.
  • Failures are published. A failed run is a finding, and findings are part of the record.