Top 3 changes to implement first

1. Add a deterministic diligence fact ledger and domain checklist layer.
   Encode canonical facts and source-of-truth rules for ARR, runway/burn, parent-account concentration, unsupported metrics, and SOC 2 status so the agent cannot rely only on generic citation instructions.

2. Upgrade validators to audit the actual output artifacts, not just claimed evidence coverage.
   Current validation can pass while artifact-level citation or claim-audit issues still require later repair. Parse generated markdown/JSON/CSV artifacts, extract material claims, verify source support, and fail on unsupported or unaudited claims.

3. Persist the five generated evals into the checked-in regression suite.
   The generated evals all passed, but they should become durable regression tests so future prompt/runtime changes cannot regress on the specific human-feedback issues.