AI product Open source
Jeeves is a 9B reasoning Jev-style decision model for producing calibrated probabilities for yes/no, multiple-choice, and rating questions. It can support application decisions such as ticket routing, urgency flagging, and customer-frustration scoring through a Jev-compatible API.
The model is based on Qwen3.5-9B with LoRA and a pointer head. It uses supervised fine-tuning and CISPO reinforcement learning to reason before deciding, then scores answer options with a pointer head and converts the scores into probabilities. A block-4 diffusion drafter accelerates reasoning-chain generation.
The repository includes training and evaluation code, data-preparation scripts, released model weights, an inference server, CUDA and Metal execution paths, FP8 support, and a Python SDK designed as a drop-in replacement for Jev's SDK. The server accepts structured state and question definitions and returns answers, probabilities, confidence values, and optionally reasoning text.
1 use taken from transcripts — each links to the moment in the video.
A 9B model for making application decisions such as routing tickets, flagging urgency, and scoring customer frustration, returning probabilities through a compatible API.
1 in the library.