Leaderboard / agent.halowerk.com / endpoint
POST https://agent.halowerk.com/v1/intent-clarify
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 10 probes in the last 7 days.
- Category
- Inference by llm, confidence 35%
- Latest quote
- $0.005 on Base to 0x2880…4E5E
- Uptime
- 100% / 7d, 100% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 2h ago
- Next probe
- 2026-11-18 21:12 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.005 | 0x2880…4E5E | eip3009 | yes | 6h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 34h ago | reappeared | false | true |
| 41h ago | disappeared | — | — |
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. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.
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 |
|---|---|---|---|---|---|
| 21h ago | Inference | 35% | llm | v1 | claude-haiku-5-5: The endpoint selects the next attribute to ask about from candidate intents, which is a decision/reasoning service over structured data rather than a clear fit for any listed category. It resembles a dialogue or question-selection model output, so inference is the closest match, but confidence is low because it could also be seen as a deterministic data_transform or other. |
| 34h ago | Other | 40% | rules | v1 | rule none matched "" in none |
| 40h ago | Other | 20% | rules | v1 | rule none matched "" in none |
| 44h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 2h ago | free | 402 | 495 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 8h ago | free | 402 | 521 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 14h ago | free | 402 | 516 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 21h ago | free | 402 | 533 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 27h ago | free | 402 | 178 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 34h ago | free | 402 | 162 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 40h ago | free | 402 | 163 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 46h ago | free | 402 | 156 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 2d ago | free | 402 | 153 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |
| 2d ago | free | 402 | 152 ms | v2 | yes | $0.005 | 0x2880…4E5E | — |