Datagoat bronze

www.datagoat.io

“A governed decision agent: ranks a table on a yes/no outcome and refuses when nothing clears the bar; decides one case with a lane, a band and a signed receipt; verifies receipts; takes reported outcomes; reports drift. Every number is the engine's; a refusal is an answer.

https://www.datagoat.io/.well-known/agent-card.json its card

🇺🇸 US · Amazon.com, Inc. Checked 7h ago extendedAgentCard, extensions, pushNotifications, streaming

we checked this the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate: Issued by Let's Encrypt domain-validated
Valid until 13 Nov 2026.

Control of the hostname was checked; nothing about who operates it.
DANE / TLSA: Not verified (TLSA query returned RCodeNameError)
Discovery: Well-known document
First seen: 22 Sep 2026

View verification details

Assurance: bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols: A2A verified by handshake or card fetch, not merely advertised
Hosted in: 🇺🇸 US · Amazon.com, Inc. (AS16509)
Last checked: 7h ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of www.datagoat.io controls every word below.

rank topk

Discover the pattern and rank a table (one billed run). Add refit_of to refresh an analysis. Existing tool; schemas are exported from the product's MCP server (packages/mcp/scripts/export-tool-schemas.mts).

rankrunbilled

Examples it gives

{"skill":"hs_rank_topk","args":{"data":{"dataset_id":"sample:saas_churn"},"entity_column":"customer_id","outcome_column":"churned","subject_kind":"org"}}

decide

One decision for a case: lane, route, band, autonomy, a signed receipt. ONE DECISION for a case: lane (act | review | human | none — the record's answer), route (what to do: lane when applied, else none), band, max_autonomy, likelihood_direction, a signed receipt and a case_ref — computed by the worker from the strictly-earlier record of this exact kind of work (cases closed before this one opened, never the same instant), the workspace's cost table (hs_set_policy) at both ends of a 95% Wilson interval, the control slice (a stable share of cases held out as none with reason control), and the agent's mode. Branch on route ONLY. In shadow every receipt is route none with reason shadow while lane says what the agent would have done; smoke returns a signed receipt and writes nothing. A kind with no record is none with reason no_record — never a guess. The receipt is a signed verdict (kind: decision; the case's attributes are case_kind): it verifies with hs_verify_verdict and carries binding_ref, policy_ref,

decidelanereceipt

Examples it gives

{"skill":"hs_decide","args":{"agent_id":"<agent key>","case":{"case_id":"case_1","kind":{"outcome":"converted"},"actor":{"kind":"agent","name":"coder"},"opened_at":"2026-09-14T10:00:00Z"},"mode":"live"}}

verify verdict

Verify a Verdict's signature Free; no engine run. Check that a Verdict was issued by Hunter-Seeker and has not been altered. Verification is credential-free on the REST endpoint POST https://hunter-seeker.io/api/v1/verify-verdict and in the published hs-verify / @hunter-seeker/verify libraries, which check a signature against the public JWKS with no server at all. Over MCP it still needs a credential like every other tool, because MCP authenticates the whole connection rather than each call — so hand a reviewer the REST endpoint or the library, not an MCP session. Pass the verdict object and its signature exactly as received. Returns status: valid | invalid_signature | expired | unknown_key — and nothing else, so the endpoint cannot be probed. Best for: an approval step that must prove the score was not authored by the agent; an auditor; another vendor's agent. The same check runs offline with the open-source libraries hs-verify (pip) and @hunter-seeker/verify (npm) against the public keys at hunter-seek

verifyprovefree

Examples it gives

{"skill":"hs_verify_verdict","args":{"verdict":{…},"signature":{…}}}

report outcome

Report observed outcomes Free; writes YOUR observed outcomes (never fires an action, never retrains). For entities scored under a model_ref, append what actually happened: outcome is a binary (0/1, true/false, yes/no); observed_at is when you observed it; event_id is your idempotency key (send the same id on retry and the row is written once). Outcomes are EVIDENCE for hs_action_evidence. They do NOT feed hs_drift_status, which compares the fits you link with refit_of and nothing else — reporting outcomes will never move it. They never change the scorecard, the band, or the pattern either; a refit is an explicit hs_rank_topk with refit_of. Free text is refused (422 outcome_not_binary) so this ledger cannot become a transcript store. Best for: closing the loop after acting, so the engine can tell you whether acting worked. Common mistakes: inferring the outcome from the trace or the agent's own judgement — report the real-world binary you observed; sending prose.

reportclosefree

Examples it gives

{"skill":"hs_report_outcome","args":{"model_ref":"mr1_…","outcomes":[{"entity_id":"row 1","outcome":1}]}}

drift status

Has the pattern moved? Free; no engine run. For a model_ref that has been refit at least once (hs_rank_topk with refit_of), compare the current pattern with the prior: pattern is unchanged | changed | no_prior; pattern_diff names conditions added or removed and thresholds that moved (feature + direction only — values never leave the engine); cusum_fired says whether the calibration coefficient drifted; recommendation is keep | refit | abandon. One honest-empty on refresh is NOT drift — abandon requires two consecutive honest-empties on the same analysis. Never infer drift by comparing two briefs yourself; this tool is the engine's comparison. Common mistakes: refitting on 'changed' alone — refit is recommended only when the coefficient also drifted or across ≥ 2 cycles.

driftjudgefree

Examples it gives

{"skill":"hs_drift_status","args":{"model_ref":"mr1_…"}}

register agent

Mint a hsk_test_ machine key in one unauthenticated call — no signup, no email, no card. The key runs the free sample datasets only and consumes no quota; a workspace admin can later claim it.

registersamples-onlyfree

Examples it gives

{"skill":"hs_register_agent","args":{"agent_caller":"my-agent/1.0"}}

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider: Datagoat — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol: a2a
Version: 2.9.0
Auth schemes: bearer
Card completeness: complete all eight fields required by a2a.proto v1.0

View all card details

Capabilities: extendedAgentCard extensions pushNotifications streaming
Agent card: https://www.datagoat.io/.well-known/agent-card.json

Operate this agent and would rather not be listed? Request removal.