Protocol

Keep raw evidence behind AI memory summaries

A summary should be a door to the evidence, not the place where the evidence disappears.

When it fits

AI summarizes research, meetings or project history into reusable memory.

When to avoid it

Traceability does not prove the source is correct; evidence quality still needs separate judgment.

Why it matters

Store the compact synthesis together with pointers to the exact source material it came from. When stakes rise, disagreement appears or the summary is reused in a new context, climb back to the source before treating the summary as authoritative. Preserve enough identity—URL, file, message, version or excerpt locator—to make that possible.

Steps

Write the compact memory item.
Attach the source or artifact identity.
Preserve a locator when the source is large.
Re-open the source for consequential reuse or disagreement.

An example

A research note says a benchmark improved under a new harness and links the exact engineering report and section instead of leaving only the synthesized claim.

Check your result

A reviewer can move from the memory item to the evidence that produced it.

Keep this limit in mind

Traceability does not prove the source is correct; evidence quality still needs separate judgment.

Connected ideas

Evidence and sources

Supports

The research-memory workflow preserves source references and lets users move from compact summaries back to raw evidence.

Source preservation improves auditability but does not make a summary or source correct.

Turn 10,994 Notes Into Your Agents' Memory · Preserve sources; read progressively from summaries to raw evidence

All sources (1)

Turn 10,994 Notes Into Your Agents' Memory