Classifiers
New classifierReusable decision classifiers for decision models such as TypeSafe's Jev and the open-weight Kev. Each classifier asks one constrained question about a state, and your code acts on the answer. Chains show how classifiers combine, with branches driven by outcomes.
Educational catalog. Nothing here calls a model. Example outcomes are illustrative judgments written for teaching, not model outputs, scores or accuracy claims. Sourced documentation is labelled separately.
Classifiers
6 classifiersAccess request completeness
Check that an access request names the resource, the role, a business reason and a duration before it reaches the approver.
Alert actionability
Decide whether a monitoring alert needs action now, is informational, is already tracked, or is flapping noise.
Change-related incident signal
Check whether a recent deploy or config change plausibly explains an alert.
Customer impact signal
Check whether an alert and any incoming reports show customers are affected right now.
Proposed incident severity
Propose a severity level from the incident description. The incident commander confirms it.
IT request type
Route an internal IT helpdesk request: access, password or MFA, hardware, software, network, or a security concern.
Decision chains
2 chainsComplete flows that reuse the classifiers above, with branches driven by outcomes.
Incident alert triage
Filter noise, check customer impact, propose a severity, and look for a recent change to blame.
- Alert actionability
- Customer impact signal
- Proposed incident severity
- Change-related incident signal
IT helpdesk intake
Screen helpdesk tickets for secrets and personal data, route them, check access requests, and triage reported phishing.
- Sensitive data in text
- IT request type
- Access request completeness
- Phishing report triage