How Context Works¶
SecondBrain does not treat "context" as just prompt stuffing.
Mental Model¶
There are three layers:
- source material
- promoted knowledge and memory
- task-specific runtime context
Source Material¶
This is what you ingest:
- notes
- docs
- meeting transcripts
- example datasets
Promoted Knowledge And Memory¶
The repo then maintains more durable structures:
- promoted facts and assets
- decision records
- memory records
- context cards and registries
Runtime Context¶
When you ask a question or run a task, the runtime assembles a smaller bundle:
- the best matching evidence
- prior decisions
- relevant memory
- policy and routing hints
That bounded bundle is what the planner or chat loop sees.
Why This Is Different From Plain Chat¶
- evidence is retrieved and ranked, not pasted blindly
- memory and decisions can influence the turn
- policy and allowed actions can travel with the request
- the final answer can be traced back to local state and source material