AI dan anomali
Model bekerja untuk proyek di tiga tempat: deteksi yang mengatakan kapan peristiwa meninggalkan garis dasarnya, proposal yang mengatakan apa yang harus dilakukan atas yang dilihatnya, dan Ask, yang mengubah pertanyaan menjadi query. Tidak ada yang bertindak sendiri: proposal menjadi nyata hanya saat seseorang menyetujuinya.
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
- Deteksi membandingkan hitungan harian dengan garis dasar empat belas hari; deviasinya aritmetika, bukan opini.
- Setiap proposal membawa asal dan alasannya, dan keputusannya dicatat beserta siapa yang membuatnya.
- Query terjemahan Ask tetap di layar; model mana yang menjawab adalah pilihan paket.
Cara kerjanya
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.
Di mana mengaksesnya
| 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 |
Contoh
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" }
}'