CONTROLAgents & automation

Air Defence Simulator with Jev

Anmoldeep Singh@anmold_s

Play video0:13

Original post ↗

17 views · 1 likes on X · does not affect score

This project builds an air defence simulator that uses Jev to answer typed questions about aircraft, including their identity, danger score, and threat probability, enabling rapid decision-making.

TakeJust typed questions per aircraft: - what is it? (choice) - how dangerous? (score 0–4) - threatening us right now? (probability) 21 decisions in ~400ms.

Related builds

Jev Decision Model

Jev is a typed decision model that returns a probability for a given state (question, answer, evidence) instead of generating prose or structured data, making it faster and cheaper than traditional AI judges.

Jose Luis Latorre | #MVP | #K6 | @DotNetZurich@joslat

40 views on XJev score 79

TypeSafe Computer Use

This project enables a Mac to achieve plain-English goals by combining OCR and the Accessibility tree to drive actions, avoiding large model loops for screenshots.

Yash Chaudhary@YashChaudhary

4 views on XJev score 78

Play video

Jev Decision Layer for Voice Pipelines

Jev acts as a decision layer in voice pipelines, utilizing typed primitives like Noul (yes/no with probability), Choice (labeled decision), and Score (scalar on a defined rubric) to process conversational turns before and during LLM responses.

Himanshu@Fabulous_7781

72 views on XJev score 76

Jev Skill Review

Jev is a decision model used to review a corpus of skills, providing ratings across rubric dimensions and identifying skills that may need distillation.

Kunal Jain@Kunal_Jain9

90 views on XJev score 76