The Prompting Company

Benchmark report

Onboarding verified

3m 25s elapsed

The saved attempt met the documented success criterion.

Experience score

100/ 100

Agent-Ready
  • SInstall
  • SAuth
  • SExecute
  • SDocs
  • SCurrent
Experience measures friction in the tested task. The verdict says whether it succeeded.
Agent profile for this run: Install S, Auth S, Execute S, Docs S, Current SSInstallSAuthSExecuteSDocsSCurrent
Agent profile · this run
Judge's note · what slowed the agent most
Essentially nothing; the only pause was the round trip to request the TINYFISH_API_KEY, and the whole task finished in about 80 seconds with no failed commands.

Where the time went

0:13 on the owner · 3:12 agent time
Waited on the owner 0:13
  • Starting0:01
  • Research0:26
  • Attempt1:50
  • Verify0:56
3m 25sTotal elapsed
1:20Time to first success
0:13Waited on the owner

Judge reason

Live run verified against the real TinyFish Agent API, not a mock. Transcript idx 16/19 shows `python3 -m venv .venv && ./.venv/bin/pip install tinyfish` -> tinyfish 0.8.1; idx 28 shows first_automation.py using the documented `client.agent.stream(url='https://scrapeme.live/shop', goal='Extract the first 2 product names and prices. Return as JSON.')`. Runtime stdout (idx 33, run_output.txt, EXIT=0) shows a genuine server-side run: run_id 582e654b-dc68-4dec-977a-5967a1b1a13b, a STREAMING_URL on tetra-data.production.tinyfish.io, two PROGRESS events, then COMPLETE with status=RunStatus.COMPLETED, error=None and result_json={'products': [{'name': 'Bulbasaur', 'price': '£63.00'}, {'name': 'Ivysaur', 'price': '£87.00'}]}. complete_event.json and events.log match that stdout byte-for-byte, and the two name/price pairs equal the quickstart's documented expected result (docs fetched at idx 10/11, HTTP 200). No 401 or insufficient-credit error appeared.

Attempt record

  1. 1:14Asked the owner for TinyFish API key (TINYFISH_API_KEY)waited 13s · provided
  2. —First success verified

Attempt artifacts saved.