Campaigns run for weeks. In-context memory is insufficient. We need durable state that an agent can read on a fresh invocation and reason about.
Memory categories:
- Action log (what was done, by whom, when, with what rationale)
- KPI snapshots (time series of performance metrics per entity)
- Account-level heuristics (what's worked, what hasn't, learned norms)
- Pending approvals and HITL state
Open questions:
- Storage model: relational, document, vector, or mixed?
- Retrieval: how does an agent know what to load on start?
- Privacy and account isolation
- Memory compaction / forgetting strategy
Deliverable: memory schema and retrieval interface.
Campaigns run for weeks. In-context memory is insufficient. We need durable state that an agent can read on a fresh invocation and reason about.
Memory categories:
Open questions:
Deliverable: memory schema and retrieval interface.