Analytics confidence thresholds with Jev
On-call already drowns in threshold alerts. Warehouses and anomaly detectors still own the math. Jev judges whether the written incident is actionable given numbers you already computed. It does not detect spikes or query the warehouse.
This unofficial page is the confidence thresholds slice of the analytics alert triage pack. Intent: apply the Jev (TypeSafe System One) decision model to analytics alert triage confidence thresholds. Primary search language: Analytics Jev confidence thresholds. Confirm patterns on docs.typesafe.ai. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Independent angle (cover ≠ clone): Alert-class + actionability on narrative + precomputed bands — not a clone of a BI-alert product or anomaly-SaaS IA.
Analytics use-case context
Thresholds turn analytics alert triage answers into act / review / abstain. They are product policy, not a hyperparameter TypeSafe ships. Official 0.5 / 0.9 sketches are illustrations. This slice also carries the false-reject discussion: over-gating analytics alert triage hides calibration.
Hub: Use cases. Compare, when the other tool is the real job: analytics alerts.
Confidence Thresholds inputs
You need (1) pinned answers on a frozen contract and (2) labels for class gold from on-call, page-now gold, and whether the page was justified. State shape:
{
"alert": { "id": "a-991", "title": "Checkout p95 up", "body": "p95 2.1s vs 1.2s baseline; error rate flat." },
"bands": { "p95_ratio_band": "1.5-2x", "error_rate_delta_band": "flat" },
"runbook": { "page": "Page if latency ≥ 1.5× and user-facing checkout, unless error_rate also explains it." }
}Decision signals and actions
| Axis | Where it lives | Analytics use |
|---|---|---|
choice / score / noul |
answer payload | What to do with the alert narrative + metric bands |
confidence |
Choice & Score only | Whether to trust the argmax |
| Distance from 0.5 | Noul | Whether page_now is decided |
FLOORS = {
"tag_class_only": 0.55, # illustrations — replace
"page_oncall": 0.85,
}
NOUL_TAU = 0.75 # for page_now
def allow(ans, action):
return ans.confidence >= FLOORS[action]Do not treat a Noul of 0.5 as a “medium” analytics alert triage score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For analytics alert triage, treat page_oncall as the high bar (paging on-call or auto-suppressing a user-facing alert). Tune on labels — see offline evaluation.
Band around 0.5 on page_now always reviews. Do not copy 0.75 onto Choice confidence.
Evaluation and rollout notes
- Missed pages on planted checkout-down narratives
- False pages / suppress mistakes
- Handoff rate
Fit loop: pin jev-1.13.0 → replay → plot error vs confidence → pick floors where auto-act error ≤ your SLA. Pin jev-1.13.0 (the versioned id) after you fit thresholds. jev-latest and the marketing line jev-1.13 can move. Log the response model. TypeSafe’s published list price for jev-1.13 is $0.042 per million input tokens (vendor claim — confirm on the models page); output tokens are free on that same page. Unused distractors still bill as input.
Official Python and JavaScript SDKs read TYPESAFE_API_KEY and retry documented 429/529. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Pack map
| Slice | Page |
|---|---|
| Graph and primitives | decision workflow |
What may enter state |
input contracts |
| What to gather first | evidence collection |
| Atomic rules | policy checks |
| Act / review / abstain | you are here |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
Should page_oncall use 0.9 everywhere? No. Over-gating hides calibration and dumps the queue on humans. Fit per action.
Can I reuse a Noul τ as Choice confidence? No. Jaggedness: they are not interchangeable. See confidence.
Where is the rest of the Analytics pack? Start with Analytics decision workflow and Analytics human handoff. Cluster hub: Use cases.
Can Jev replace the anomaly detector? No. Detectors emit numbers. Jev reads the write-up and your runbook excerpt.
Should we send the whole timeseries?
No. Summarize to bands in code. Distractors hurt jev-1.13 and still bill as input (vendor claim).
What this page does not claim
- Not a warehouse, detector, or APM.
- No MTTA/MTTD benchmarks.
- Not official TypeSafe.
- Official TypeSafe status, or that jev.pro issues API keys.
- That a schema-constrained answer is automatically factually correct.
Disclaimer
This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.
Primary documentation: https://docs.typesafe.ai. Hub: Use cases.
Sources
Public TypeSafe or adjacent documentation only. No private claims.