IA y anomalías
El modelo trabaja para el proyecto en tres lugares: la detección que dice cuándo un evento dejó su línea base, las propuestas que dicen qué hacer con lo que vio, y Ask, que convierte una pregunta en una consulta. Nada actúa solo: una propuesta solo se vuelve real cuando una persona la aprueba.
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 detección compara conteos diarios con una línea base de catorce días; la desviación es aritmética, no opinión.
- Cada propuesta lleva su origen y su razón, y su decisión queda registrada con quién la tomó.
- La consulta traducida de Ask queda en pantalla; qué modelo responde lo elige el plan.
Cómo funciona
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.
Dónde acceder
| 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 |
Ejemplo
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" }
}'