Knowledge and learning
Skills, playbooks, knowledge, wiki, and memory, plus the human-gated loop that turns a successful run into a reusable procedure.
UseAgent gives an agent an organization’s accumulated know-how at the start of a run, and captures what a run figures out at the end. Nothing is published without a human.
The knowledge substrate
| Term | What it is |
|---|---|
| Skill | Versioned, reusable instructions, selected semantically and activated by exact id for the current task. |
| Playbook | A skill whose content describes a repeatable end-to-end operating procedure. |
| Knowledge | Organization-scoped source material an agent can search and read. Reference data, not executable instructions. |
| Wiki | A published document generated from repository or organization knowledge and later retrievable by agents. |
| Memory | Optional scoped facts retained across sessions for a user or team. Reference material, and independently disablable. |
Skills and playbooks share one immutable substrate. The turn-prefill catalog is re-ranked by prompt relevance on every unpinned turn, so the procedures that match the current ask surface into the page the model sees, rather than a fixed top-N by usage.
Skill import
GitHub is the source of an organization’s procedures. UseAgent scans a repository
for SKILL.md files and imports selected paths as versioned skills:
- Discovery runs over a server-side shallow clone, resolving the head with
git ls-remote, because the REST git-data surface is not dependable for org installations. - Imports are pinned to a commit and idempotent by source, so re-running an import does not create duplicates.
- Resync is opt-in and operator-timed: a periodic sweep runs only when
SKILLS_RESYNC_INTERVAL_MINis set to a positive number of minutes, and unset means disabled. Each sweep is capped at 200 repositories with 2-second pacing between repositories (backend/src/skills/resync.ts).
The learning lane
The self-improvement loop runs on every completed run and is fully human-gated:
Recall at start
A run recalls organization memory when it begins.
Capture at finish
At the end, capture is salience-gated and enriched with structured evidence, including the ordered tool trace of what actually worked.
Propose knowledge drafts
High-value runs propose knowledge drafts, carrying the redacted procedure trace.
Propose skill revisions
Accepted drafts that cluster propose skill revisions whose procedure is assembled from the real traces.
A human reviews
An org admin accepts or dismisses each proposal at /learnings. Nothing
auto-publishes.