Liigu põhisisu juurde

Tehisintellekt ja kõrvalekalded

Mudel töötab projekti heaks kolmes kohas: tuvastus, mis ütleb, millal sündmus baasjoonest lahkus, ettepanekud, mis ütlevad, mida nähtuga teha, ja Ask, mis muudab küsimuse päringuks. Ükski neist ei tegutse üksi: ettepanek saab teoks alles siis, kui inimene selle heaks kiidab.

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
  • Tuvastus võrdleb päevaseid loendeid neljateistpäevase joonega; kõrvalekalle on aritmeetika, mitte arvamus.
  • Iga ettepanek kannab oma päritolu ja põhjendust ning tema otsus salvestatakse koos otsustajaga.
  • Aski tõlgitud päring jääb ekraanile; milline mudel vastab, on plaani valik.

Kuidas see töötab

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.

Kust seda leida

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

Näide

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" }
  }'