Skip to main content
Most memory tools assert they improve your agent and back it with one flattering number. PMB takes the opposite stance: measure it conservatively, on your data, and say loudly when the signal isn’t trustworthy yet. A memory system you can’t measure is one you can’t trust. There are two different questions inside “does it help?”, and they need two different methods.

Retrieval quality

Does recall find the right memory? Measured with reproducible benchmarks - LoCoMo recall@10 ≈ 94.5%, multilingual top-10 ≈ 99.2%.

Outcome impact

Does using memory change outcomes? Measured by Earned Memory, joining each surfaced lesson to the outcome of the turn it was active in.

​
Earned Memory - three honest layers

PMB joins each surfaced lesson to the turn’s outcome (tests pass/fail, red→green, build, deploy - no LLM) and reports effectiveness at three levels of rigor, refusing to overclaim at each one.

Associational lift (weakest)

success_rate(lesson active) minus success_rate(no lesson). Useful first look, but confounded: lessons surface on harder turns, so a helpful lesson can show negative lift. A flag for review, never ground truth.

Statistical honesty

Each lesson carries a 95% Wilson confidence interval and a conservative verdict - useful/harmful only when the CI clears the baseline and n ≥ min_n; otherwise unverified or insufficient. An n=1 fluke can never read as a real effect.

Within-lesson causal read (strongest)

The cleanest control without randomization: compare the same lesson when followed vs ignored. Both arms share the same trigger population, so it holds the surfacing trigger fixed.

​
What PMB will not do

An untrustworthy metric never drives behaviour. Earned Memory is measurement-only: it does not feed ranking or decay until the outcome signal is dense enough to trust. PMB would rather show you insufficient than let a flattering-but-wrong number quietly re-weight your memory.

​
Run it on your own data

Seeing signal: insufficient early is the honest answer, not a bug - outcome turns are rare, so a young workspace simply hasn’t earned a verdict yet. A lesson only earns “useful”/“helps” once the statistics back it.