IA et anomalies
Le modèle travaille pour le projet à trois endroits : la détection qui dit quand un événement a quitté sa ligne de base, les propositions qui disent quoi faire de ce qu'il a vu, et Ask, qui transforme une question en requête. Rien n'agit seul : une proposition ne devient réelle que lorsqu'une personne l'approuve.
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
- La détection compare les comptes quotidiens à une ligne de base de quatorze jours ; l'écart est de l'arithmétique, pas une opinion.
- Chaque proposition porte son origine et sa justification, et sa décision est enregistrée avec son auteur.
- La requête traduite d'Ask reste à l'écran ; quel modèle répond est le choix du plan.
Comment ça marche
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.
Où y accéder
| Surface | Operation |
|---|---|
| REST | None |
| GraphQL | aiInsights, aiProposals, aiTranslateQuery, aiAnswer queries · approveProposal, editProposal, rejectProposal mutations |
| Realtime | aiProposals subscription: new proposals stream as they are raised |
| MCP | None |
Exemple
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" }
}'