Ruka hadi maudhui makuu

AI na hitilafu

Modeli hufanya kazi kwa mradi sehemu tatu: ugunduzi unaosema tukio lilipoacha mstari wake wa msingi, mapendekezo yanayosema la kufanya kwa ilichokiona, na Ask, inayogeuza swali kuwa hoja. Hakuna kinachotenda peke yake: pendekezo huwa halisi tu mtu anapoliidhinisha.

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
  • Ugunduzi hulinganisha hesabu za kila siku na mstari wa siku kumi na nne; mkengeuko ni hesabu, si maoni.
  • Kila pendekezo hubeba asili yake na hoja yake, na uamuzi wake hurekodiwa pamoja na aliyeufanya.
  • Hoja iliyotafsiriwa ya Ask hubaki kwenye skrini; modeli ipi inajibu ni chaguo la mpango.

Jinsi inavyofanya kazi

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.

Wapi kuifikia

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

Mfano

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" }
  }'