Optimize
Optimize reads your sessions and surfaces where agent work is slow, expensive or failing — ranked by likely return. Findings are recomputed nightly and can be run on demand.
Finding types
Section titled “Finding types”| Finding | What it flags |
|---|---|
| Stall | a session whose tool calls went idle mid-run |
| High retry | a task retried three or more times |
| Cost overrun | a session costing well above the workspace median |
| Token bloat | a session using far more tokens than its peers |
| Parallel | tasks that could have run in parallel but didn’t |
| Context wide | a session that touched an unusually large number of files |
Each finding is scored for ROI so the highest-leverage ones sort to the top. Findings are recomputed on a nightly job (and whenever you press Run); the underlying statistics refresh hourly.
Data it needs
Section titled “Data it needs”Cost overrun, token bloat and context-wide findings need populated cost/token/files data — so they only appear once the hook is capturing real sessions. Stall, high-retry and parallel findings work from task and tool-call data alone.
What “Apply” does
Section titled “What “Apply” does”- For a finding tied to a task, Apply writes a fix hint onto the task and appends it to the
task description — so the next agent that claims it (via
get_next_task) sees the guidance. This is a real feedback loop back into the board. - For a session-scoped finding with no task, Apply just marks it handled. Use the Prompt action to generate a paste-ready prompt you can hand to an agent instead.