Harrison Chase#423
we just shipped support for rubrics in deepagents ✅
give your agent a clear definition of what "done" looks like, and force it to run in a loop until said goal is complete
this is similar to /goal in claude code, but works for any agent (not just a coding agent)
Users praise the new DeepAgents documentation for its clear guidance on configuring rubric middleware in goal-based agent loops.
Rubrics are even more flexible than /goal
You can define a custom subagent for the grading, including custom tools, prompt, and iteration limits.
Try it out and let us know what you think!
we just shipped support for rubrics in deepagents ✅
give your agent a clear definition of what "done" looks like, and force it to run in a loop until said goal is complete
this is similar to /goal in claude code, but works for any agent (not just a coding agent)
@sydneyrunkle Sydney can you direct me some resources for Sandboxing for agent to read about and implement in project.
Definetely gonna test this new feat.
great new docs by @sseshadri43
https://docs.langchain.com/oss/python/deepagents/rubric#configure-the-middleware
@byanujpatel @sydneyrunkle is this helpful? https://docs.langchain.com/oss/python/deepagents/sandboxes
Harrison Chase#423we just shipped support for rubrics in deepagents ✅
give your agent a clear definition of what "done" looks like, and force it to run in a loop until said goal is complete
this is similar to /goal in claude code, but works for any agent (not just a coding agent)