Every project starts from zero, even when it shouldn’t.
You solved a related problem eight months ago. You learned, the hard way, where the billing work tripped you up last time. But that knowledge lives in your head, or in a closed ticket no one will reopen, so the next brief in the same area starts blank — and the team rediscovers what it already knew, at full cost, again.
Circuit remembers. Every shipped, killed and deferred outcome is recorded, and when a new brief touches the same ground, the prior outcome surfaces before you start drafting.
From outcome to memory to the next brief.
Memory is written when work closes and read when new work begins.
When a spec ships or a priority is killed or deferred, Circuit writes a memory row — what shipped, what the outcome was, what corrections were made.
Each memory is embedded so it can be found by meaning, not by remembering it exists.
When a new brief touches an adjacent area, get_relevant_memory pulls the prior outcome before you start drafting.
Pick Conservative, Balanced or Aggressive for how strongly your corrections steer future briefs.
The system learns from what happened, not just what came in.
Most tools learn from inputs — more feedback, more tags. Circuit also learns from outcomes — what you shipped, what you killed, what you corrected. That’s the difference between a record and a memory.
When a new brief touches an area you’ve worked in, Circuit surfaces a reference to what you shipped there last. “You shipped ‘export polish’ previously” — before you start, not after.
The risk section of a brief is populated from past outcomes and signal patterns in adjacent areas, instead of invented caveats.
Pick Conservative, Balanced or Aggressive. The control sets how strongly your corrections — renamed themes, re-ranks, refinements — steer future briefs.
The rest of what compounds.
Three levels: Conservative, Balanced, Aggressive.
Rename a theme or re-rank a priority once and the change carries into future work.
An honest record of what shipped, what was killed and what was deferred, kept against each brief.
Relevant past outcomes appear before you start drafting, retrieved by embedding similarity.
Today the nudge appears at brief-draft time, not when the priority forms.
Compare how different kinds of briefs performed over time.
Surface what kinds of work succeed once enough briefs have shipped to compare.
Asked and answered.
Outcomes — what shipped, what was killed, what was deferred — along with the corrections you make and the themes you rename. The record of how your product decisions played out.
When you start a brief in an area you’ve worked in before, the relevant past outcome surfaces before you start drafting, retrieved by embedding similarity.
From past outcomes and signal patterns in adjacent areas — the risks you’ve encountered — rather than generic caveats.
Yes. Renaming a theme or re-ranking a priority is remembered and applied to future briefs through the memory aggressiveness control.
Yes. Memory aggressiveness is tunable — Conservative leans on your corrections lightly, Aggressive surfaces them strongly. You set how much weight your past corrections carry.
That’s the point. Every outcome adds to what Circuit knows. A team running it for a year is working with a system that has learned from everything they shipped.