AI memory needs a way to change its mind

The appeal of AI memory is easy to understand. Explain the project once. Stop repeating the same preferences. Pick up the work tomorrow without another orientation session.

Then the project changes. A temporary workaround becomes unnecessary. A proposal gets rejected. The team changes its mind. The assistant still remembers the earlier conversation beautifully, which is now part of the problem.

Working on ATLAS, my project-memory system for AI tools, has made me think about remembering as a maintenance problem. Saving more context is useful only if there is also a way to tell what still applies.

Record what kind of statement you have

Consider three notes: we could use a queue for this task; we decided to use a queue; the queue is deployed. They share most of their vocabulary. They describe very different states of the work.

If a system retrieves them as interchangeable evidence, a suggestion can quietly become architecture. A future agent may start building on a decision nobody made. The original words can be accurately preserved while the resulting guidance is wrong.

ATLAS separates memories such as decisions, observations, blockers, preferences, and rejected alternatives. That structure gives the system something to reason about beyond similarity. It still depends on the quality of the record. Calling a guess a fact does not improve the guess.

Keep the reason and the limits

‘Use this service’ is less useful than a decision that explains why it was chosen and which project it applies to. A service selected for a prototype may be the wrong choice for a different workload. Without the original constraints, the memory turns a local decision into a universal preference.

I want a record to carry its source, its scope, and enough rationale to revisit it. Confidence can be helpful context, but a number does not replace evidence. A direct decision from the person responsible and an inference from an old conversation should remain distinguishable.

Rejected alternatives deserve space here as well. Knowing that a team considered an approach and why it declined it can prevent a lot of enthusiastic rediscovery. Sometimes the constraint has changed and the idea is worth another look. Preserve the reason so that judgment is possible.

Make replacement explicit

Adding a new note does not necessarily retire the old one. Both may keep appearing in search, and the longer or more frequently mentioned version may look more persuasive. The person asking the question should not have to settle that conflict from scratch every time.

ATLAS includes an explicit way to supersede a memory: keep the earlier record for history and create its replacement. It also supports validity windows for temporary facts and verification to mark a memory as still current. These are mechanisms for maintaining the record, not a guarantee that every stored statement is true.

The distinctions matter. Something old can remain correct. Something recent can be speculation. A temporary instruction may expire on a known date, while an architectural decision needs review only when its assumptions change. One blanket freshness score cannot express all of that.

Test a change of mind

A useful memory test starts with a decision, then changes it. Ask the system what applies now. Can it return the replacement, explain why the earlier choice changed, and keep an unrelated project’s preference out of the answer?

That exercise tests a more useful behavior than recalling an isolated fact. Repeat it with a rejected proposal, an expired workaround, and a note whose source is uncertain. Watch whether the system preserves those distinctions when it summarizes.

You can apply the same discipline to a plain Markdown project log. Mark decisions clearly, link replacements, and give temporary instructions an end condition. A small record that accurately describes the present can be more useful than a detailed archive that leaves every past direction in force.

The product goal I care about is continuity: enough history to understand the work, and enough maintenance to move it forward. Remembering why we changed our minds belongs in that goal.