Interactive demo · synthetic data · real cryptography

Your coding agent fixed the pipeline.
Can your customer prove why it was allowed to?

A AI code-assistant agent works a real SDLC task below — diagnosing and fixing a failing CI/CD pipeline on a compliance-bound repo. Flip between Without Summit (what the assessor sees today) and With Summit (every consequential action sealed in a signed, hash-chained Decision Receipt). Then try to tamper with the record.

Scenario

A defense-contractor customer (CMMC Level 2 track) runs AI code assistant Agent Platform. The release pipeline for acme-federal/telemetry-svc is red, and the coding agent is asked to fix it and ship. Six consequential actions follow.

Every step below emitted a Decision Receipt — click any receipt to open it.

The assessor's question

NIST 800-171 / CMMC Level 2, Audit & Accountability (AU) — the control family assessments fail most. Same six actions, two answers:

ControlAssessor asksWithout SummitWith Summit
3.3.1 System auditingAre agent actions captured as audit records at all?CI logs, 30-day retentionReceipt per action, permanent chain
3.3.2 User accountabilityCan you trace each action to a unique actor & authority?"ci-bot" commit authorActor + authorizing policy on every receipt
3.3.3 Reviewable eventsWere the right events selected for audit?Whatever the runner printedConsequential-action rule set, declared up front
3.3.7 Time stampsTrustworthy, ordered timestamps?Mutable log linesSigned, sequenced, hash-linked
3.3.8 Protect audit infoCould the record be altered after the fact?Anyone with runner accessTampering breaks the chain — try it below
3.3.9 Manage audit functionWho can change what gets audited?Repo maintainersGoverned policy, itself receipted
chain: 6 receipts · not yet verified