← The Memra Journal
Trust & Security

When Memra says "I don't know" — and why that's a feature

The most useful thing a memory can do is admit the edge of what it knows. A confident guess is worse than a clear refusal — it becomes tomorrow's misinformation.

There’s a strong temptation, in any answering system, to always produce something. Silence feels like failure. But a fabricated answer doesn’t just mislead the person who asked — it gets repeated, cited, and eventually treated as fact.

So we drew a bar. Below a confidence threshold, backed by too little evidence, Memra declines. It tells you the corpus can’t support an answer rather than inventing one.

The honest failure mode

The refusal isn’t a shrug — it’s specific. It names what it looked for and why the evidence fell short, so you know whether the gap is in the question or in the record.

  • Not enough sources — the topic isn’t covered in the connected corpus yet.
  • Conflicting sources — the evidence disagrees, and picking a winner would be guessing.
  • Stale sources — the only matches are too old to trust as current state.

A system that knows the shape of its own ignorance is one you can build on. One that always answers is one you eventually stop believing.

More from the Journal

Scroll for more →
SM

Swarad Mokal

Building Memra · Axelerant

Writes about organizational memory and evidence-first systems.

The Memra Journal

New thinking on organizational memory, twice a month.

Field notes and product thinking from the team. No noise, unsubscribe anytime.

Restricted to work email addresses.
When Memra says "I don't know" — and why that's a feature — The Memra Journal