Evidence-linked trend hypothesis

Company memory needs write and correction loops

Retrieval is only one stage of memory; durable organizational knowledge also needs scoped writes, corrections, provenance, versioning, and invalidation.

Current thesis

  • Company memory becomes useful when real work continuously updates a governed knowledge layer, not when an agent merely searches a larger document pile.
  • Confidence: high.
  • Supported by 5 normalized raw signals.

Source ledger

Publishable sources attached to this record.

5 public sources
#SourceRolePublic status
1promptql.iosourceprimary receiptsource_urls
2aclanthology.orgsourcesupporting receiptsource_urls
3github.comreposupporting receiptsource_urls
4careersatdoordash.comsourcesupporting receiptsource_urls
5github.comreposupporting receiptsource_urls

What retrieval leaves unresolved

A relevant document can still be stale, unauthorized, contradicted, or scoped to another team. A long context window can expose more text without deciding which statement should change the next action. Those are memory lifecycle questions, not search-quality questions.

Supporting evidence

  • PromptQL captures a correction during work, proposes a reusable rule, and keeps citations, scope, revision history, and editorial control around the update.
  • DoorDash stores semantic memory as independently versioned components and a manifest, then refreshes different memory layers at different cadences.
  • MemoryData evaluates storage, retrieval, updating, and forgetting across a sequence rather than scoring only a final response.
  • OpenWiki turns repository understanding into a maintained artifact that can be inspected and refreshed outside an individual session.

Operational consequence

Every memory entry needs a write path, evidence, owner or authority, scope, timestamp, supersession behavior, and rollback. Human correction is a valuable write signal, but it should produce a reviewable proposal rather than an unbounded automatic truth update.