Coding sessions
The step that repeats in every session.
Sessions' goals never repeat — but the exploration, triage and survey steps inside them do. Those are the ones worth learning.
Anatomy of the task · illustrative workflow
Locate files, symbols and call sites; report paths, not dumps.
Input
A codebase, a question about it, and the read-only tools an exploration step is allowed to use.
Required output
The relevant paths and symbols, reported precisely — not a dump of file contents into the context window.
Evaluation
- Names the right files and symbols
- Reports paths, not dumps
- Leaves the session cheaper than a frontier pass would
Understand the workflow.
On our own development estate, an Explore-style sub-agent thread recurred in 71% of coding sessions. The sessions' goals never repeat; the sub-agent's does. That is the shape Operant looks for.
Define the quality bar.
An exploration step has a checkable outcome: did it find the right call sites? The gate replays held-out runs and scores the cheaper model against the frontier model's answers.
Improve the route.
The recurring step becomes a named pattern. Operant writes the skill it takes — which tools, what to report, what to skip — and proposes routing that step to a cheaper model carrying it.
Keep frontier capability.
The main thread keeps the frontier model. Only the recurring sub-task moves down, and one click moves it back.
Published evidence
See the comparison. Keep the context.
The published gate result shows the discipline: exemplars held out before the learner ran, disjoint ids, and a judge scoring parity against the frontier baseline.
Read the results ->Who this fits
A task your team knows well.
A team running Claude Code, DeepSeek Harness or Codex sessions at volume, where the same exploration and triage steps recur across sessions.
Bring a workload ->Another place to start · Scheduled digests