---
session_id: "1376197"
title: "Your Judge Is Hallucinating Too"
phase: live
last_checked: 2026-11-12T13:24:21-08:00
render: 20261112-132421-c4d6ee
---

# Links: Your Judge Is Hallucinating Too

## Speaker

**Brian Kennedy**, Principal Engineer, Agentic AI Platform, ZoomInfo

- LinkedIn: [Brian Kennedy](https://www.linkedin.com/in/brianpk/)

## Company

**[ZoomInfo](https://www.zoominfo.com/)**: "ZoomInfo is the #1 GTM Platform:
Marketing and sales AI plus the best B2B data." (from the site)

## Resources

- **Blog** · [Agent Teams: Reliable Multi-Agent Orchestration for GTM](https://pipeline.zoominfo.com/sales/zoominfo-agent-teams)
  (ZoomInfo). The multi-agent system whose every step the talk's judge grades.
- **Blog** · [Introducing System One Models & Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev)
  (TypeSafe AI, 2026-09-15). Jev, the decision model the abstract says ZoomInfo
  ran beside its LLM grader as the second check.
- **Blog** · [TypeSafe Jev: Can Decision Models Replace LLM Judges?](https://arize.com/blog/typesafe-jev-llm-judge/)
  (Arize AI, 2026-09-18). A decision model in place of an LLM judge: the question
  the talk's closing asks every team to measure ("Measure yours.").

## Gaps

- The recording is a 28-second closing fragment. It never names the speaker, his
  company or the systems, so these links are matched to the abstract.
- No ZoomInfo write-up of the judge-versus-Jev comparison was found.
- No official recording or slides found yet. The dossier rechecks every 6 hours
  during the event.