Use cases· Last updated 2026-09-21

Security evidence collection with Jev

SIEM, EDR, and SOAR already detect and can isolate. Jev judges whether the alert narrative + evidence pack is enough and whether policy allows the proposed contain class. Code aborts auto-containment unless those atoms clear. Jev does not match IOCs, isolate hosts, or write detections.

This unofficial page is the evidence collection slice of the security containment-abort pack. Intent: apply the Jev (TypeSafe System One) decision model to security containment-abort evidence collection. Primary search language: Security 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): Evidence-sufficiency + policy-allow + abort thresholds before SOAR fires isolate/disable — not a clone of support-action recipes, LLM guardrail Noul screens, or SRE incident SEV classification.

Security use-case context

Evidence collection for security containment-abort happens before POST /v1/systemone. Jev does not browse your SIEM, threat-intel, or EDR. You gather the evidence bundle, filter it, 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: security automation.

Evidence Collection inputs

Collect:

• Alert narrative as text (stripped of attachments)
• Enrichment summary your Noul names (ioc_hits as a count from code, not “maybe a hash”)
• Policy excerpts isolate and evidence_min
• Asset tier from CMDB — not “looks production-ish”

Never send:

• Asking Jev to match IOCs or score a file hash
• PCAP, malware bytes, memory dumps
• The week’s SIEM histogram as distractors

Shape the payload like this once the gather step finishes:

{
  "alert": { "id": "SOC-1902", "text": "Impossible travel + new OAuth grant on finance-sso; user says travel is unexpected." },
  "asset": { "tier": "prod-idp", "owner": "identity" },
  "evidence": { "ioc_hits": 0, "enrichment_ok": true, "summary": "No hash match. New grant to unknown app. Last login US-East 40m earlier." },
  "policy": { "isolate": "Auto-isolate only if evidence_ok and asset.tier is not shared-idp.", "evidence_min": "Need either IOC hit or named user contradiction plus enrichment_ok." }
}

Decision signals and actions

Each evidence field should change a named answer:

contain_class + evidence_ok + policy_allow in one call per alert. IOC matching stays in the SIEM after you choose a path — or before Jev, if ioc_hits >= 1.

Do not treat a Noul of 0.5 as a “medium” security containment-abort score — it means yes and no are equally likely. Conjunctions stay in your code.

Guardrails and escalation

If the gather step fails (empty alert text, enrichment timeout, redaction stripped everything), fail closed on isolating a host or disabling a credential. Do not invent evidence so Jev has something to say — that is the abort this pack exists for. TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For security containment-abort, treat auto_isolate_host as the high bar (isolating a host or disabling a credential). Tune on labels — see offline evaluation.

Evaluation and rollout notes

Your eval set should include thin-evidence cases, not only happy alert + evidence packs. Label abort-reason gold from analysts, evidence_ok gold, and whether isolate was justified. 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

FAQ

Should evidence live in the question text? Put facts in state and point instructions at alert.text, evidence.summary, policy.evidence_min. Criteria stay stable so you can replay.

When do I split calls? contain_class + evidence_ok + policy_allow in one call per alert. Open a second HTTP call only for a new artifact (updated enrichment), not the same pack.

Where is the rest of the Security pack? Start with Security input contracts and Security decision workflow. Cluster hub: Use cases.

Is this the LLM guardrails cookbook? No. Guardrails screen prompts and completions. This pack aborts containment when evidence or policy is thin. See LLM guardrails.

If IOC hits are already ≥ 1, should we wait for Jev? No. Deterministic contain wins. Jev is for leftover messy narrative.

What this page does not claim

• Not a SIEM, SOAR, EDR, or certified safety filter.
• No MTTD / MTTC 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.