Architecture
From the outside Vectadyne is an endpoint and a token. Inside, everything runs through five stages, and each one is where a different kind of quality problem gets solved.
1. Evidence
Section titled “1. Evidence”Raw engineering activity: a merged PR, a failed CI run, an incident, a review comment, a correction from a human. Evidence is immutable and append-only — the record of what happened does not get edited later because someone disagreed with it.
Correction is expressed by adding, not by overwriting: a correction supersedes an earlier claim
and both stay in the record. That is what makes the audit trail worth having.
2. Derivation
Section titled “2. Derivation”Evidence becomes typed memory. A PR description is not a memory; the conclusion drawn from it is. Each memory carries:
- a kind —
fact,decision,lesson,policy,guide,evidence - a scope — where it applies
- a status —
active,disputed,stale,deprecated - a sensitivity — the clearance needed to see it
- links to the evidence that supports it
Kinds are not decoration; they carry precedence. A policy outranks a lesson when they conflict.
See The memory graph.
3. Guides
Section titled “3. Guides”A topic guide is the standing answer to “what should anyone touching this know?” — assembled from the memory that applies to a topic, and resolved fresh rather than stored as a stale digest.
This is the layer that makes retrieval feel like knowledge rather than search. Without it, every query starts from scratch and the same five facts are re-derived on every run.
4. Retrieval and admission
Section titled “4. Retrieval and admission”Two distinct steps, and conflating them is the mistake that makes a system leak:
Retrieval ranks candidates — hybrid lexical and dense, plus one hop of graph edges to pull in what the top hits are connected to.
Admission then filters by authority: tenant, scope, clearance, status. It runs at read time, on every request, against the calling principal.
Admission is not a re-ranking pass with a low weight for “probably shouldn’t see this”. It is a filter. What comes back is what this credential is allowed to see, which is why an empty result is a legitimate answer rather than an error.
5. Governance
Section titled “5. Governance”The action-facing layer. Given a proposed action, produce a verdict with reasons and citations, and record what was known at the moment of the decision.
The record is the part that outlives the run. “The agent did the wrong thing” is a very different conversation from “the agent did the wrong thing and here is what it had been told”.
See Governance and audit.
The loop
Section titled “The loop”The dotted line in the diagram is the whole point. An agent’s outcome — what it did, whether it worked — goes back in as evidence, so the corpus improves every run. A system without that line is a retrieval index that never learns.
What you touch
Section titled “What you touch”Only the endpoint. Seven verbs map onto these stages:
| Stage | Verbs |
|---|---|
| Evidence | evidence.ingest |
| Derivation | memory.remember |
| Guides | guide.resolve |
| Retrieval + admission | memory.search |
| Governance | preflight.action, context.assemble, context.report |
context.assemble spans stages 3 to 5 in one call, which is why it is the verb most integrations
end up centred on. Full schemas: MCP reference.