Leaderboard / api.agentweather.io / endpoint
GET https://api.agentweather.io/v1/pulse/storm
Scores measure reliability and honesty, not output quality.
- Quoted a price different from the listed price on 6 of 6 comparable probes.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Category
- Utility by llm, confidence 40%
- Latest quote
- $0.003 on Base to 0xA15c…F4Ec
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 8m ago
- Next probe
- 2026-11-17 23:03 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | xrpl:0 | 524C55…0000 | — | rnFHPG…jrZZ | default | yes | 4h ago |
| cdp | exact | Base | 0x8d58…8258 | $1000000000 | 0xA15c…F4Ec | permit2 | yes | 4h ago |
| cdp | exact | Base | 0x8335…2913 | $0.001 | 0xA15c…F4Ec | default | yes | 4h ago |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Delivery results do not affect scores yet.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 16h ago | Utility | 40% | llm | v1 | claude-haiku-5-5: The endpoint reports a current worst-level status across status pages and facilitator reachability, which is a live condition check rather than a fit for signal or web_audit. Nothing in the listing names a clearly matching category, so utility is the closest fit at moderate-low confidence. |
| 20h ago | x402 tooling | 60% | rules | v1 | rule x402_meta matched "facilitator" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 8m ago | free | 402 | 154 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 7h ago | free | 402 | 202 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 13h ago | free | 402 | 338 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 19h ago | free | 402 | 430 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 25h ago | free | 402 | 306 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 32h ago | free | 402 | 192 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |
| 38h ago | free | 402 | 190 ms | v2 | option ok | $0.003 | 0xA15c…F4Ec | malformed_challengeprice_above_listingprice_mismatch accepts[1].amount_not_uint_string |