Jev integration with DeepClause and Pi enables probabilistic logic programming for routing and decision-making tasks. The system combines LLM capabilities with Prolog-based determinism to handle customer message triage efficiently, using structured predicates for safety checks, classification, and routing decisions.
Find-jevable-code is an agent skill for Claude Code and Codex that audits repositories to identify semantic decisions (routing, triage, relevance, escalation) that could be converted into Jev primitives: Choice, Score, or Noul. The read-only pipeline surfaces opportunities ranked by code evidence without invoking paid inference.
Hush is a GitHub Action that automatically labels issues using a decision model that returns probability scores, only applying labels when confidence exceeds configurable thresholds. Unlike other LLM-based triage bots, it abstains from labeling when uncertain, costing roughly $0.00002 per issue.