Changelog
New features and changes in Judgment.
October 2026
Tests
Set up testsTests run your agent over a set of test inputs, Judgment's judges grade each trace, and you compare runs.
Judge actions
Set up judge actionsEvery judge can now send an email, post to Slack, add the trace to a dataset or run more judges when it returns the labels you pick, with a cooldown. Automations are now judge actions.
Scheduled Tasks
Schedule a taskBackground agents are now Scheduled Tasks, under Scheduled in the sidebar. A task is a Judgment Agent chat that runs on a schedule and can post to Slack. Start from scratch, from a template, or let Judgment suggest one.
Issues
Find issues in your tracesAn agent reads your recent traces and turns recurring failures into Issues, each with a severity, a diagnosis and the traces behind it. It needs traces only, no judges. You review each Issue, hand it to Codex, Claude Code, Cursor or Devin with Fix with, and choose Monitor with Judge or Dismiss issue. Detection can run on a schedule and post a report to Slack after each run.
Query with SQL
Query your traces with SQLQuery traces with Judgment's virtual SQL (vsql) through the Judgment Agent and the MCP tools
sql_queryanddiscover_schema. The SDK addsclient.sql()in judgeval 1.3.3 (Python) and 1.3.4 (TypeScript).Project setup
Follow the quickstartNew projects open a five-step setup on the project home: Tracing, Issues, Judges, Slack and Judgment Agent. As your first traces arrive, Judgment starts an Issues run and creates up to five judges from them.
Agent Knowledge
Add agent knowledgeProject memory moved to Agent Knowledge in project Settings. Files there are shared by the Judgment Agent in chats and Scheduled Tasks, and files under
skills/become slash commands.Labels
Use labels as indexesThe values a judge applies are now called labels. API and SQL names still say
behavior(for examplebehavior_id).Deprecated
The CLI and prompt management are deprecated. Old CLI documentation links redirect to the pages that replace them.