Check out the newest way to compare different models for a task/agent harness: AutoEvals

Command Reference

Agents

Inspect auto-discovered agents and their execution stats.

Inspect the agents auto-discovered from your spans and their execution stats. Agents are read-only — there are no agent mutations.

Commands

Run inf agent <verb> --help for each verb's options. The generated surface covers:

VerbDescription
listList a project's agents with rolled-up stats
summary-cardsList a project's agents as summary cards with sparklines
index-cardsList the paginated agent index with rolled-up stats
index-initial-dataThe first agent-index page plus its execution series
getGet an agent's identity by id
statsGet an agent's rolled-up stats over the read window
overviewGet an agent's overview: summary, series, model/tool profile
timeseriesGet an agent's per-day metric time series
index-execution-seriesPer-agent execution-count series for the index

On this page