AI at mga anomalya
Nagtatrabaho ang modelo para sa proyekto sa tatlong lugar: deteksyon na nagsasabi kung kailan lumihis ang isang event sa baseline nito, mga panukala kung ano ang gagawin sa nakita nito, at ang Ask, na ginagawang query ang tanong. Walang kumikilos mag-isa: nagiging totoo lamang ang panukala kapag inaprubahan ng tao.
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
- Inihahambing ng deteksyon ang pang-araw-araw na bilang sa labing-apat na araw na baseline; aritmetika ang paglihis, hindi opinyon.
- Dala ng bawat panukala ang pinagmulan at katwiran nito, at naitatala ang desisyon kasama kung sino ang gumawa.
- Nananatili sa screen ang isinaling query ng Ask; pili ng plano kung aling modelo ang sasagot.
Paano ito gumagana
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.
Saan ito maaabot
| 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 |
Halimbawa
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" }
}'