Skip to content

Governance and audit

Governance is the layer that judges actions, not just context. It is what has no analogue in a retrieval system.

Proposed actiontype · files · scope ·summaryRelevant memoryfor these files, this scopeReason evaluationpolicy · history · disputes ·checksVerdictallow · warn · block ·require_approvalAudit recordwhat was known, what wasdecided, by whom

You describe what you are about to do — the action type, the files, the scope, a summary. Vectadyne finds what the corpus knows about those specific things and evaluates it.

Every verdict carries reasons, each with a severity and citations:

ReasonFires when
regression_recurrencethis change resembles one that broke before
fragile_filethis file has a history of causing incidents
contradicts_decisionthis contradicts a recorded decision
violates_policya policy prohibits it
requires_approvalpolicy requires a human
stale_memory_conflictrelevant memory has aged past confidence
disputed_memorythe supporting memory is contested
missing_required_checka required check has not run
sensitivity_blockthe action touches memory above clearance
guide_prohibitiona topic guide prohibits it
low_confidence_advisoryweak signal, surfaced honestly

A bare block is not useful. block because violates_policy, citing the policy and the evidence behind it, is something an engineer can act on or argue with.

DecisionMeaningYour agent
allowNothing known against itproceeds
warnSomething worth knowing; not disqualifyingproceeds, with advisories in front of the model
blockRecorded knowledge says do notholds
require_approvalA human must sign offholds

warn proceeding is the advisory-first thesis in one row. If you treat warn as a stop, you have built the inline gate this is designed not to be.

Any decision a client does not recognise is treated as a hold. All three SDKs fail closed there.

Every governed call records what was known, what was decided, which principal asked, and when.

The value is reconstructive. After an incident, “the agent did the wrong thing” and “the agent did the wrong thing and here is exactly what it had been told” are different investigations. Combined with as_of time travel, you can replay what an agent would have been told at any past moment and distinguish:

  • the agent was never told — a corpus gap; fix the evidence
  • the agent was told and ignored it — an integration gap; fix the branch
  • the agent was told something wrong — a memory quality problem; fix the record

Those three have completely different fixes, and without the record you cannot tell them apart.

Anything running unattended should have its own identity, so the audit trail says which agent did what rather than which human’s token it borrowed. See Enrol a machine principal.

Three lanes, and only one of them is advisory:

CI / PR HARD, opt-inblock verdictmerge blockedServer-side HARDtenant · scope · clearance ·capabilityrequest refusedInline ADVISORYverdictyour branch decides

Read Advisory-first before you rely on any of them.

There is no attestation. The audit export is the artifact — a complete record you can pull and hand to whoever is asking. See What we do not claim.