Evidence & verification reports
Proof per change instead of vague trust: what verification reports contain, how evidence accumulates into an audit trail, and how teams rebuild trust in AI pull requests.
How to use this collection
Use evidence & verification reports when you need a bounded answer rather than a generic promise about AI coding. The 3 articles separate observed evidence, working assumptions, product boundaries, and decisions that still belong to a human reviewer. Each guide is dated and keeps its source limitations visible.
Start with “Evidence Reports” for the broadest entry point, then use “Rebuilding Trust in AI Pull Requests” when you need the collection's more specific edge. The cards below state what each article covers, so you can choose by task instead of reading a manufactured sequence. Related links inside each guide connect methods, risks, evidence, and next actions without treating one check as universal proof.
Check each article's publication date, cited source, and stated scope before applying it to a live repository. Examples explain a method; they do not replace your project rules, threat model, tests, or accountable reviewer. If two guides appear to conflict, compare their assumptions and evidence rather than selecting the more confident wording.
Proof
Evidence Reports
What was intended, what changed, what was validated, what was skipped, what remains uncertain - recorded per run and stored with the code. Structure and a labeled sample.
Updated: October 19, 2026Read article →
Proof
Proof-Carrying Coding
Proof-carrying coding is an analogy for attaching task, checks, results, skips and provenance to a change, and the reason that evidence is not a formal proof.
Updated: November 4, 2026Read article →
Trust
Rebuilding Trust in AI Pull Requests
Gut feel fails on AI code - no author to model, plausibility decoupled from correctness, perception skewed. The five-question clear-conscience checklist, and why evidence makes trust transferable.
Updated: October 26, 2026Read article →
Want to see what your last agent run would have looked like?
Request access