Benchmark: get slots on jameda with an AI agent
On jameda, Wield's recipe read free appointment slots in 9 of 9 runs, with a median of 0.2 seconds and one request per run. A browser agent (Browser Use driving Claude Sonnet 5.5) also passed 9 of 9, but its median run took 46 seconds and cost $0.13. Both sides used the same three doctor and date queries on 7 November 2026.
jameda Get free online appointment slots for a doctor on jameda
Read-only, no loginRuns in your browser only
Parameters (5)
| Metric | Wield recipe | Browser Use + Claude Sonnet 5.5 |
|---|---|---|
| Success | 100% | 100% |
| Median time | 211 ms | 46 s |
| Cost per run | $0 | $0.128 |
9 runs each, 7 November 2026. How we measure
The task
Each side ran the same three slot lookups. Each lookup names one practitioner, one practice address and one start date.
| Query | Parameters |
|---|---|
| q1 | doctor_id = 288098, address_id = 314278, start_date = 2026-11-09 |
| q2 | doctor_id = 368693, address_id = 405242, start_date = 2026-11-10 |
| q3 | doctor_id = 978, address_id = 1469, start_date = 2026-11-11 |
Pass check: at least one free slot, with a date and a time.
Results (7 November 2026)
| Wield recipe | Browser agent | |
|---|---|---|
| Runs passing the check | 9 of 9 | 9 of 9 |
| Median time per run | 211 ms | 46.0 s (46,005 ms) |
| Model cost per run | $0 | $0.13 |
| Requests per run (median) | 1 | 148 (to the site: 4) |
| Blocked by the site | 0 runs | 0 of 9 runs |
Why the results differ
Both sides passed every run, so this task compares speed and cost. The recipe makes one request per run to read the slot data. It runs from a jameda tab in your own browser and makes no model calls.
The browser agent got the same answer by reading pages. A median run took 6 steps, 148 requests (4 of them to the site), 42,788 input tokens and 1,561 output tokens. Its cost is the model cost of those steps.
The site did not block the browser agent. The log records no HTTP 401, 403 or 429 errors.
Caveats
- Small sample. Nine runs per side, on three lookups.
- Preliminary. The benchmark was still running on 7 November 2026.
- Paced. Runs are paced at about 30 site requests per hour, so counts are low on some sides.
- Slots change. A slot listed on 7 November 2026 may be gone when you read it.
Terms of jameda
jameda's terms forbid automated retrieval of profile data. The recipe makes one search request that you start, from your own browser. Searches about health are sensitive, so results stay on your device. Check jameda's terms before any automated use.
FAQ
Does jameda block browser agents?
Not in these runs. The browser agent recorded no HTTP 401, 403 or 429 errors from jameda, and it passed all nine runs.
How fast is the Wield recipe for get slots on jameda?
The median run took 211 ms across nine runs. The fastest took 204 ms and the slowest took 649 ms. The browser agent median was 46.0 s.
Can I rerun this benchmark?
The method, the task file and the raw logs are described on the benchmark page. The logs record destinations, timing, tokens and checks. They hold no page contents.