/AI6h ago

Deepagents Adds Agent Rubrics For Self-Evaluation And Iteration

--0--
Quote posts
Reposts
Original postHarrison Chase#739
Sydney Runkle@sydneyrunkle

new in deepagents: agent rubrics!

you define a rubric, and the agent self-evaluates and iterates until it satisfies every rubric criterion.

this is similar to /goal in claude code or codex, but more flexible because grading is conducted by a dedicated subagent that you can tune with a prompt or custom tools.

Sydney Runkle@sydneyrunkle

http://x.com/i/article/2061868304654864384

11:13 AM · Jun 2, 2026 · 5.8K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS5.8KBOOKMARKS21LIKES30REPLIES3
LangChain@LangChain

New in Deep Agents: Agent Rubrics!

Attach a rubric to your agent invocation, and a grader evaluates and self-corrects output until it satisfies all requirements.

This is helpful for long/complex tasks where you need to keep the agent on track re an end goal!

Sydney Runkle@sydneyrunkle

http://x.com/i/article/2061868304654864384

6hViews 5.8KLikes 30Bookmarks 21
RETWEETS7
LangChain@LangChain

New in Deep Agents: Agent Rubrics!

Attach a rubric to your agent invocation, and a grader evaluates and self-corrects output until it satisfies all requirements.

This is helpful for long/complex tasks where you need to keep the agent on track re an end goal!

Sydney Runkle@sydneyrunkle

http://x.com/i/article/2061868304654864384

6hViews 5.8KLikes 30Bookmarks 21