Protocol

Build a reusable research wiki when the topic keeps coming back

Deep research is expensive if every question starts by forgetting the last one.

When it fits

You repeatedly research the same domain, product, client or technical area across projects.

When to avoid it

A one-off topic may not justify maintenance overhead; persistent memory becomes useful only when reuse exceeds upkeep.

Why it matters

Create a maintained project knowledge layer with compact findings, source links, terminology, unresolved questions and dated decisions. Let new research update that layer rather than producing another isolated report. Start small with trusted seed sources, preserve raw references, and retire stale claims when the underlying source or product changes.

Steps

Seed the project with a few trusted sources.
Write compact source-linked findings.
Record open questions and decisions.
Reuse the wiki as input to later research.
Review freshness and supersede stale entries.

An example

For an SAP program, maintain a source-linked wiki of interface behavior, known notes, mappings and prior incident findings that the AI can search before starting another investigation.

Check your result

A later question reuses relevant prior evidence and can still reach the underlying sources.

Keep this limit in mind

A one-off topic may not justify maintenance overhead; persistent memory becomes useful only when reuse exceeds upkeep.

Connected ideas

Evidence and sources

Supports

The AI Engineer research-memory workflow turns repeated research into a maintained project wiki so later work can reuse sources and findings rather than restart from zero.

Persistent research only pays when the topic recurs and somebody maintains freshness and provenance.

Turn 10,994 Notes Into Your Agents' Memory · Reusable research workflow and growing project wiki

All sources (1)

Turn 10,994 Notes Into Your Agents' Memory