Learn the controls and knobs

Primary knobs for conversation memory: write policy, retention TTL, retrieval k, consent flags, memory scopes (user/session/org), forget API.

Write a sheet for the personal tutoring assistant with columns: control, current value, predicted benefit, predicted cost, rollback trigger. Fill it using this topic’s real tension: More durable memory feels personal and raises privacy/stale-advice risk. Aggressive forgetting is safer and more annoying. Automatic writes scale and can store falsehoods.

Change one conversation memory family at a time. If you move two knobs and the personal tutoring assistant improves, you learned a cocktail, not a cause—and you cannot roll back surgically.

End users of the personal tutoring assistant should see only safe dials related to conversation memory. Infrastructure limits, private prompts, and policy thresholds stay server-owned. A user-facing control that bypasses those limits is a vulnerability dressed as UX for conversation memory.

Publish the conversation memory control sheet next to the personal tutoring assistant runbook. On-call should see which knob moved in the last deploy without reading chat archaeology. Unknown conversation memory knobs are unowned knobs.

Also pin one numeric memory from this conversation memory chapter: If 40 memories are injected every turn but only 3 affect the hint, you spent tokens and risked contradictions—measure useful-memory rate, not memory count. That number is not decoration; it is a template for how claims about conversation memory on the personal tutoring assistant should look in design docs. Scoped specifically to conversation memory / personal tutoring assistant / controls-and-knobs.

People confuse conversation memory with neighboring buzzwords when debugging the personal tutoring assistant. Before changing prompts, ask whether the broken stage was evidence gathering, the conversation memory judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried conversation memory and it failed”) that blocks the next team on the personal tutoring assistant. Scoped specifically to conversation memory / personal tutoring assistant / controls-and-knobs.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to conversation memory rather than generic AI advice.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to conversation memory rather than generic AI advice.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to conversation memory rather than generic AI advice.