✦ Feason

Christian evidence API · Claim evaluation

Theological Claim Checking API
Evidence before verdicts.

Feason’s theological claim checking API evaluates a Christian doctrinal claim against curated, passage-level evidence. It separates support, contradiction, qualification, context, and unclassified material so an AI product can show why a claim is contested.

Get an API keySee an API response
POST /evaluate-claim endpointhttps://www.feason.com/api/context/v1/evaluate-claim

How it works

A Christian context layer built for inspection.

Check Christian theological claims against curated Scripture and historical sources. Retrieve supporting, contradicting, qualifying, and contextual evidence with citations.

Deterministic normalization

Recognized wording maps to a curated claim registry. The API discloses when a claim does not match instead of pretending to understand it.

Passage-level stances

Human-curated annotations distinguish support, opposition, qualification, and context. Model-generated classification is not used.

Safe negative evidence

A missing result is not a denial. Only explicit opposing annotations can populate the contradiction bucket.

API example

Concrete JSON.
Traceable evidence.

The REST response mirrors the same versioned Christian source corpus available through Feason’s MCP server. Every evidence item retains its passage ID, canonical reference, source provenance, and verification status.

See all six API operations →
RequestPOST /evaluate-claim
curl https://www.feason.com/api/context/v1/evaluate-claim \
  -H "Authorization: Bearer $FEASON_CONTEXT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "claim": "Children of believers may be baptized.",
    "limitPerStance": 5
  }'
Response shapeapplication/json
{
  "normalizedClaim": "infants-may-be-baptized",
  "supportingEvidence": [{ "passageId": "..." }],
  "contradictingEvidence": [{ "passageId": "..." }],
  "qualifyingEvidence": [{ "passageId": "..." }],
  "contextualEvidence": [],
  "unclassifiedEvidence": [],
  "confidence": 0.92
}

How theological claim checking differs from ordinary fact checking

Many Christian questions involve interpretation, historical development, and tradition-specific language rather than a single database fact. Feason therefore returns an evidence map, not a confidence-shaped substitute for judgment. Applications can quote exact passages, name the source tradition, and explain where evidence qualifies a claim.

A response contract designed for explainable Christian AI

Each result includes the submitted claim, its normalized definition when available, five distinct evidence collections, methodology, confidence, caveats, and a negative-evidence policy. Evidence items carry stable source and passage identifiers, canonical references, full provenance, retrieval scores, and verification status.

Source attribution across disputed doctrine

When Christians disagree about baptism, salvation, Scripture, Christology, or the Trinity, Feason keeps each witness attached to its source. A confession remains a confession; a council remains a council; a patristic passage remains historical testimony. Retrieval does not flatten those categories into synthetic consensus.

Use cases

What developers can build.

Feason supplies the evidence layer. Your application remains responsible for presentation, pastoral boundaries, and the conclusions it draws.

AI answer review

Check doctrinal statements produced by a model and attach evidence users can open before publication.

Theology research tools

Give students and researchers a structured starting point for comparing evidence around a claim.

Editorial guardrails

Flag unsupported certainty, missing qualification, or claims that do not match the curated registry.

Questions

Frequently asked.

Short answers to the implementation and methodology questions teams usually ask first.
What is a theological claim checking API?

A theological claim checking API retrieves source-backed evidence relevant to a Christian doctrinal claim and groups that evidence by its documented relationship to the claim. Feason reports supporting, contradicting, qualifying, contextual, and unclassified passages instead of generating an unexplained true-or-false verdict.

Does Feason decide whether a theological claim is true?

No. Feason normalizes supported claims and returns inspectable evidence with curated stance annotations. It helps an application reason from sources while leaving interpretation and final conclusions to the application and its users.

How does Feason treat missing evidence?

Missing retrieval, silence in a source, and unclassified passages never count as contradiction. Only a passage explicitly annotated as opposing a normalized claim appears as contradicting evidence.

Which Christian traditions does the API represent?

The corpus includes Scripture, creeds, councils, patristic writings, historical works, and confessions from multiple Christian traditions. Every response identifies represented traditions and preserves gaps instead of inventing consensus.

Feason Context · REST API 1.2

Build with Christian sources your users can inspect.

Create a scoped keyConnect through MCP