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
4 classifiersCancellation reason
Categorize why a customer is cancelling, for product and pricing insight. The cancellation always goes ahead.
Feature request specificity
Tell whether a feature request explains the user's problem, only proposes a solution, or is a vague wish.
Feedback sentiment
Rate how positive or negative a piece of feedback is, with neutral and mixed in the middle.
Feedback topic
Tag a piece of product feedback with its main topic: usability, performance, pricing, missing feature, bug or praise.
Decision chains
2 chainsComplete flows that reuse the classifiers above, with branches driven by outcomes.
SaaS billing desk
Sort billing messages, check unknown charges for account takeover, process cancellations as asked, and match the reply to the customer's mood.
- Billing issue type
- Account takeover signal
- Cancellation reason
- Customer frustration
Feedback triage
Tag feedback by topic, send bugs to engineering, check feature requests for a use case, and find unhappy users to follow up with.
- Feedback topic
- Feature request specificity
- Feedback sentiment