본문으로 건너뛰기

AI와 이상 징후

모델은 프로젝트의 세 곳에서 일합니다: 이벤트가 기준선을 벗어난 때를 말하는 감지, 본 것에 대해 무엇을 할지 말하는 제안, 질문을 쿼리로 바꾸는 Ask. 어느 것도 홀로 행동하지 않습니다: 제안은 사람이 승인할 때만 현실이 됩니다.

At a glance

Detection
Daily counts against a fourteen-day baseline
Proposals
Origin, rationale, and a recorded human decision
Ask
Question to query, query kept on screen
Model
Chosen by the plan, per tier
Auth
Access token; nothing executes unapproved
  • 감지는 일일 수치를 14일 기준선과 비교합니다. 편차는 산술이지 의견이 아닙니다.
  • 모든 제안은 출처와 근거를 지니며, 그 결정은 누가 내렸는지와 함께 기록됩니다.
  • Ask의 번역된 쿼리는 화면에 남습니다. 어떤 모델이 답하는지는 플랜의 선택입니다.

작동 방식

Detection is arithmetic over the warehouse: a day whose count deviates from the fourteen-day baseline past the threshold is an insight, marked as a spike or a drop. A deviation worth acting on, or a pattern in support threads, becomes a proposal: a cohort to build, a flag to add, a message to send, or a dashboard to create, each carrying what it saw and why it suggests what it does. Proposals queue in the Inbox until a person approves, edits or rejects them, and the decision is stored with its decider. Ask is the third piece: the model emits only the validated query language, never free SQL, and its translation stays on screen beside the answer. The broader model story, entitlements and safety posture live on the AI pillar.

접근 위치

SurfaceOperation
RESTNone
GraphQLaiInsights, aiProposals, aiTranslateQuery, aiAnswer queries · approveProposal, editProposal, rejectProposal mutations
RealtimeaiProposals subscription: new proposals stream as they are raised
MCPNone

예시

Bash
curl "https://api.prodantix.com/graphql" \
  -H "Authorization: Bearer $ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "query ($p: String!, $e: String!, $f: String!, $t: String!) { aiInsights(projectId: $p, event: $e, from: $f, to: $t, threshold: 0.3) { bucket kind value baseline } }",
    "variables": { "p": "'$PROJECT_ID'", "e": "signup_completed", "f": "2026-08-01", "t": "2026-08-28" }
  }'