Polylane swapped LLMs for decision model Jev in prod, cutting costs 39%
multiply_matrix · x · 2026-09-26
Polylane replaced LLMs with TypeSafe AI's decision model Jev to power its always-on on-call agent, reporting a 39% cost reduction.
- What Jev is: a decision model that generates no text—it answers questions about your data with typed values and calibrated probabilities, at 70–500ms per response with free output tokens, pitched as "smart if-statements" for classify/route/score steps.
- Three question types: Noul (yes/no probability), Choice (pick an option), Score (probability-weighted rubric rating).
- Use case: deciding when its Slack/GitHub agents should proactively respond with meaningful insights.
- The team says for what it's good at, Jev "absolutely mogs" open-source models, and it has now run in production for a week.
More from coding & agent
- Designer shares favorite AI trick: ask it to break your UI with worst-case data — floguo · 2026-09-26
- Microsoft launches Autopilot, an always-on agent built on OpenClaw, contributing back upstream — heyneighbor · 2026-09-26
- Replit Animation Auto-Pulls Your Project's Design System to Generate Product Videos, Powered by Opus 5.5 — amasad · 2026-09-26
- Agent debate: 'can act' isn't the same as 'has enough evidence to act' — zerovariance36 · 2026-09-26
- Dev praises Codex CLI's terminal launch speed as unmatched by other harnesses — johnlindquist · 2026-09-26
- Real-time scam call detection with ElevenLabs and Jev, ~180ms at $0.0004 — TheMoonMidas · 2026-09-26