Decisions and memory
A decision is something your organization settled that should still be true tomorrow. We do not log PII. Payments code needs a second reviewer. Enterprise contracts over $50k go to legal.
Most organizations have hundreds of these and can produce none of them on demand. They live in a Slack thread from March, in a meeting nobody recorded, and in the head of the person who is on holiday.
Memnox's job is to turn them into something machine-checkable without ever inventing one.
The pipeline
Events accumulate
Messages, pull requests, issues, transcripts and documents arrive as source events, each with a link back to itself.
Extraction proposes
An LLM reads a window of events and proposes candidate decisions, each one carrying the exact events it was drawn from. This is the only place in the entire product where a model runs.
A human reviews
Candidates land in the review queue. A reviewer reads the evidence and approves or rejects. Nothing skips this.
It becomes memory
An approved decision is recorded with its provenance, the source type, the source reference, and the name of the reviewer who approved it, and reaches the runtime, where it can escalate a decision that contradicts it.
Bring your own key
Extraction is BYOK: you supply the model credential, and it is your account the
call is billed to. Without one, the extraction routes answer 503 and the rest
of the product carries on working, ingestion, governance, audit and reporting
never needed a model.
That is worth stating plainly: an organization that never turns extraction on still gets the whole gate.
What a decision carries
Field
The statement
sourceType + sourceRef
The approver
Scope
Supersedes
How memory changes an agent's day
Recorded decisions are one of the runtime's advisors. When an agent attempts something that contradicts a recorded decision, the verdict is tightened, never loosened.
memnox memory add "No PII in application logs"
memnox memory search "logging"The search is keyword-based by default, with optional hybrid semantic search where a vector index is available. Same query, same results, which is what makes it safe for an advisor to consult.
Decisions go stale
An organization that never revisits a decision ends up governed by a rule from two reorganizations ago. Memnox runs a decay check: decisions whose evidence is old, whose owner has left, or which nothing has touched in a long time are surfaced for confirmation.
This never deletes anything. Ageing is a reason to ask, not a reason to act.
Drift
The mirror image: policy drift is when what the organization does has moved away from what it said. Memnox reports it rather than resolving it, because the resolution is a judgement call, either the practice is wrong, or the policy is out of date, and only a person knows which.
Console → Decisions, with the decay and drift indicators visible on the list
screenshot slot, save as public/screens/…png and set src
Patterns become proposals
The review queue has a second source. Extraction reads what the organization said; pattern detection reads what it did. An approval that keeps being granted, the same verb at the same size with the same person saying yes, is a rule nobody has written down yet, and it is surfaced as a proposed rule with the approval history as its evidence.
The proposal takes the same path as an extracted decision: it lands in the review queue, a named person accepts or rejects it, and until then nothing changes. The counting is deterministic, no model reads your approvals. Precedent is the same signal read from the other side: it tells an agent a question is settled, and this tells a reviewer the settlement is worth writing down.
The loop this closes is the point. An exception a person approves today becomes, with their approval a second time, the rule that is applied tomorrow. The organization becomes more machine-readable by being operated, not by being documented.