Dataiku puts Jev decision model inside LLM agents: typed judgments at cents per 1,000 calls
mattturck · x · 2026-10-07
Dataiku integrated TypeSafe's Jev—a new class of "decision model" alongside OpenAI's Decisions API that returns typed judgments with probabilities (yes/no, choice, score)—into its visual agent canvas and benchmarked it against LLM agents on 200 supplier requests at a few cents per thousand calls. The design principle: explicitly structure agent graphs with decide/analyze sub-nodes (system 1 vs system 2), likely the state of agentic design for six months until variable token pricing arrives.
More from coding & agent
- raindrop_ai Cofounder Ben Hylak on Rogue AI Agents, Catching Agent Failures and What Safety Talk Misses — soleio · 2026-10-07
- IR4RL turns intermediate render progress into RL rewards, new SOTA for image-to-code — phillip_isola · 2026-10-07
- Ramp Data Shows Enterprise AI Adoption at Peak: How to Turn Your Skills into Agents — vasuman · 2026-10-07
- Combining OpenAI's Decisions API with Live API Lets Voice Agents Act Mid-Conversation — pbbakkum · 2026-10-07
- 27B Model at 256k Context, 110+ tok/s on a Single RTX 5090 via focus-llama — Ok-Shower7286 · 2026-10-07
- Google Testing Blog: Two-Way Doors — Don't Code Yourself into a Corner — rseroter · 2026-10-07