AgentList / Field notes
How to evaluate AI agent features with evidence
Use agent directories to make a shortlist, distinguish documented capabilities from reproduced results, and keep unknown fields separate from unsupported features.
- Formats
- Landscape
- Runtime
- 55 seconds at 30 fps
- Delivery
- MP4 · H.264 · AAC · BT.709
- Source
- openscout.app
Transcript
An agent directory is a starting point for research. A feature listed on a page is not a test result.
Start with the job, the tool surface, and where the agent runs. Those requirements make the comparison meaningful.
Keep documented claims separate from capabilities reproduced in a test. Record the source and date for each claim.
A missing field means the catalog does not establish the answer. It does not prove the feature is unsupported.
Local execution and offline operation are different claims. Check model, service, and network dependencies before treating them as equivalent.
Test shortlisted tools on the same representative task. Record the version, environment, output, and any limits you observed.
Use AgentList to narrow the field and follow its source links. Verify important claims against the work you need done.
Educational diagrams with synthesized English narration. Captions are included in the picture; the optional caption track repeats the same text.
Try the explanation
Sources
Reviewed 2026-10-02. The diagrams illustrate the documented model; they are not a recording of a live agent run.