Ads evidence collection with Jev
Launching spend is irreversible. Jev judges creative copy and claims against your brand/legal excerpts. Bidding, budgets, and auction math stay in the ad platform.
This unofficial page is the evidence collection slice of the ads creative and policy decisions pack. Intent: apply the Jev (TypeSafe System One) decision model to ads creative and policy decisions evidence collection. Primary search language: Ads Jev evidence collection. 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): Policy/compliance gates + spend irreversibility — not a clone of bidding-system IA or a rival ads recipe slug.
Ads use-case context
Evidence collection for ads creative and policy decisions happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the ad creative + claim facts, filter them, then ask snap questions. This slice is where fan-out cost math belongs: batch questions, do not re-send state.
Hub: Use cases. Compare, when the other tool is the real job: ad bidding systems.
Evidence Collection inputs
Collect:
- Headline + body as they will serve
- The landing claim that must match
- The policy paragraphs you actually enforce
Never send:
- Asking Jev which bid to set
- Pixel-level screenshots
- The entire brand book as unused tokens
Shape the payload like this once the gather step finishes:
{
"creative": { "id": "ad-441", "headline": "Lose 10kg this week", "body": "Guaranteed results." },
"landing": { "claim": "Results vary; no guarantee." },
"policy": { "health": "No absolute health outcome claims.", "superlatives": "No unsubstantiated #1 claims." }
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
policy_ok |
Noul | Does creative violate policy.* given landing.claim? |
claim_type |
Choice | performance / health / pricing / social_proof / other |
brand_risk |
Score | how embarrassing if this ships |
Policy + claim_type + brand_risk in one call per creative. Batch creatives as separate states, not one Choice over 200 headlines.
Do not treat a Noul of 0.5 as a “medium” ads creative and policy decisions score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty ad creative + claim, redaction stripped everything, retriever empty), fail closed on spending against a live campaign. Do not invent evidence so Jev has something to say. TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For ads creative and policy decisions, treat allow_launch as the high bar (spending against a live campaign). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy ad creative + claims. Label hold / allow gold from brand+legal, plus claim_type gold. 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 | you are here |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
Should evidence live in the question text?
Put facts in state and point instructions at creative.headline, creative.body, policy.health, landing.claim. Criteria stay stable so you can replay.
When do I split calls? Policy + claim_type + brand_risk in one call per creative. Batch creatives as separate states, not one Choice over 200 headlines.
Where is the rest of the Ads pack? Start with Ads input contracts and Ads decision workflow. Cluster hub: Use cases.
Will Jev pause campaigns when CPA spikes? No. That is the ad platform / your rules. Jev judges language and policy fit.
Can we send images of the creative? Not to System One. Transcribe or paste the copy. Images are not accepted.
What this page does not claim
- Not an ads manager or bidding engine.
- No performance numbers.
- 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.