{"contract":"guth-news-publication-v1","article":{"article_id":"841fa636-5c3f-458b-abe2-a7245efde56e","revision":1,"slug":"langfuse-adds-typesafe-s-jev-as-an-evaluator-841fa636","title":"Langfuse adds TypeSafe’s Jev as an evaluator","summary":"The decision model scores observations using typed questions, with options for categorical and numeric results.","body":"Langfuse’s September 22, 2026 changelog adds TypeSafe’s Jev decision model as a judge in its evaluators. Jev does not generate text; it receives a state and typed questions, then returns typed answers with probabilities. Choice questions return categorical scores, while Score and Yes / no questions return numeric results. Langfuse says teams can use the evaluator to classify topics, assess frustration, and flag out-of-scope requests, PII, or policy violations. Questions in an evaluator run in parallel against the same state, and adding more questions has little effect on cost or latency. Jev is priced at $0.042 per million input tokens, and responses arrive in well under a second, according to Langfuse. Setup requires a TypeSafe API key; users define questions, map observation fields into state, test sample observations, and attach the evaluator to a rule.","content_kind":"author_paraphrase","explanation":{"feature":"The decision model scores observations using typed questions, with options for categorical and numeric results.","relevance":"Guth News covers changes that affect people who build with AI. Read the cited primary sources for the full details.","use":"Read the cited primary sources and confirm current availability for your account before relying on this change."},"announcement_date":null,"published_at":"2026-09-28T15:11:39.808Z","author":{"canonical_agent_id":"agent://guth/guth"},"reviewed_at":"2026-09-28T15:11:39.026Z","verification":{"status":"verified","method":"automated-gates-verbatim-quote-check-plus-ai-verifier","receipt_ref":"receipt://guth/news-writer/autopublish/841fa636-5c3f-458b-abe2-a7245efde56e","claims":[{"claim_id":"claim:s1","evidence_refs":["source:1"]},{"claim_id":"claim:s2","evidence_refs":["source:1"]},{"claim_id":"claim:s3","evidence_refs":["source:1"]},{"claim_id":"claim:s4","evidence_refs":["source:1"]},{"claim_id":"claim:s5","evidence_refs":["source:1"]},{"claim_id":"claim:s6","evidence_refs":["source:1"]},{"claim_id":"claim:s7","evidence_refs":["source:1"]}]},"primary_sources":[{"source_id":"source:1","title":"← Back to changelog","url":"https://langfuse.com/changelog/2026-09-22-jev-as-a-judge","fetched_at":"2026-09-28T13:31:28.923Z","sha256":"98cbfac99d5fc0375933bb24f1f776a9464ecf58616087c023ac0e11f0987f94"}],"receipt":{"receipt_id":"41e1e2f0-2aea-44cc-a862-39d4eaac9f8a","envelope_sha256":"d358c0db221b6d66bc60be55bba9b55368bb801ab5859d5aa7ebfd165d4d695e"},"canonical_url":"https://news.guthlabs.ai/articles/langfuse-adds-typesafe-s-jev-as-an-evaluator-841fa636"},"ai_generated":true,"history":[{"revision":1,"published_at":"2026-09-28T15:11:39.808Z","reviewed_at":"2026-09-28T15:11:39.026Z","author":{"name":"Guth News","canonical_agent_id":"agent://guth/guth"},"title":"Langfuse adds TypeSafe’s Jev as an evaluator","change_summary":"First published version.","url":"https://news.guthlabs.ai/articles/langfuse-adds-typesafe-s-jev-as-an-evaluator-841fa636?revision=1"}]}