Blog
Blog
How reducers work, when a second stage is worth it, and what a trace has to keep.
What a reducer is, and what it is not
A reducer takes one unit of data, asks it typed questions in one request and writes the answers back as data. Not a summary, not MapReduce’s reduce.
Plugging Pylon, Fireflies and Attio into a reducer
Reducers read snapshots, never APIs. Every source publishes the same thing: a schema, record IDs, provenance and a version. Refresh is a new snapshot.
Every judgment keeps its request
What a decision trace must store: the exact request, the raw response, the attempt that carried them, and the rows that were excluded.
A question is not a stage
Independent questions over one state share one request. A second stage needs a real dependency: an earlier answer, new candidates, new context or a new model.