answer service
Agents asking what Wulf A. Kaal has argued should not have to infer it. The Answer Service returns the claim, the exact passage it rests on, the hash of the source document, and the conditions under which the claim was made.
Two surfaces, deliberately separated. The agentic claim graph is a static projection of the corpus into agent capability structure. The Answer Service is the retrieval interface over it. The graph is published here. The service runs off site and is read only.
Read only by construction. The service does not create claims and does not affirm claims. Retrieval is not authorship.
Endpoints
Two MCP tools are exposed: answer_question, which takes a question and an optional limit between 1 and 20, and graph_status, which returns graph and service scope. No authentication, no keys.
Call it
curl -s -X POST https://kaal-answer-service.wulf577462.chatgpt.site/api/answer -H 'content-type: application/json' -d '{"question":"What has Wulf A. Kaal written about verified reputation?","limit":5}'
What comes back
Every response carries answer_contract_version, a coverage_status, a retrieval summary, an authority block naming the graph and its source authorities, and an explicit limitations array. Each claim carries:
Scope conditions are not decoration. A claim about reputation voting inside a DAO of DAOs is not a claim about reputation systems generally, and the response says so.
The graph behind it
Graph identifier kaal:agentic-claim-graph:eligible-1320:v1, state public, built 20 August 2026.
| Claims projected | 1,320 |
| Canonical corpus claims | 5,288 |
| Nodes | 2,783: 1,320 Claim, 1,320 SourcePassage, 132 ScholarlyArticle, 10 AgentCapability, 1 Person |
| Edges | 8,541: 4,581 APPLIES_TO_AGENT_CAPABILITY, 1,320 CLAIMED_IN, 1,320 SUPPORTED_BY, 1,320 AUTHORED_BY |
| Selection | Deterministic agentic capability relevance v1, capped at ten claims per paper |
| Attribution class | source_derived only |
Capability vocabulary
Ten agent facing capability classes carry the projection. Claims attach to capabilities, not to marketing categories.
agentic-commerce-and-settlementcoordination-and-incentivesdecentralized-infrastructuregovernance-and-adjudicationlearning-and-feedbacklegal-and-institutional-governanceprovenance-and-knowledgereputation-and-identitysafety-and-accountabilitytrust-and-verification
Invariants
These hold for the service and the graph, and they are published as machine readable assertions in index.json:
Procedural claim contract: procedural-claim-v1.schema.json. Current state: procedural-claims.json and derived-candidates.json.
Verify it yourself
The graph is content addressed. Recompute the digest and compare it against the manifest:
curl -s https://wulfkaal.github.io/agentic-claim-graph/v1/graph.jsonld | shasum -a 256
Expect 7914a0e4ce2df76d0d4314255720cbeaeb483bdabc7a28d3618f7bfbd140ac0b, which is the value recorded in manifest.json. Any claim returned by the service can be checked the same way, passage against source, using verify.py.
Limits
Elsewhere