Agent Memory
Agent memory is saved information that an AI agent can use after the current message. Clear rules say what is saved, for how long, and how it can change.
Another example
A user lets an agent save a writing preference. A task note lasts only until that task ends. The preference can help in later sessions. The current context window alone is not lasting memory.
Main parts
- 01memory scope
- 02retention policy
- 03provenance and update
Use it when
Use this term when information is saved past one turn or found again for a later agent decision.
Do not use it when
Do not save private or guessed preferences without consent, a clear purpose, deletion controls, and a known source.
Name used in code
short-term state + durable store + retrieval policy Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate Agent Memory to make AI behavior measurable and tied to evidence. User context: A user lets an agent save a writing preference. A task note lasts only until that task ends. The preference can help in later sessions. The current context window alone is not lasting memory. AI method or concept: Agent Memory. Why it fits: Use this term when information is saved past one turn or found again for a later agent decision. Do not use it when: Do not save private or guessed preferences without consent, a clear purpose, deletion controls, and a known source. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): It is official for that source. Other platforms or teams may use the term in another way. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of Agent Memory. Definition: Agent memory is saved information that an AI agent can use after the current message. Clear rules say what is saved, for how long, and how it can change. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.