[Unit 12] Tracing and Evaluating Agents
Are you open to a contribution on tracing and evaluating agents?
I recently contributed a unit on this topic for the Hugging Face Agents course (https://github.com/huggingface/agents-course/pull/309) and believe a module on this using autogen and semantic kernel could be a good addition to this course.
Let me know what you think!
👋 Thanks for contributing @jannikmaierhoefer! We will review the pull request and get back to you soon.
thanks @jannikmaierhoefer - I agree this is an interesting topic we should be covering. Ping you in the DM you sent earlier so we can put together a plan and submit it.
Love seeing programmers being collaborative and finding more ways to improve the code for the users.
I am relatively newcomer to the field of working with A.I. agents, i think its really cool that we have all these tools to not only trace but evaluate how well our A.I. is doing, but also understanding what an AI agent did and why. I'm looking for to learning more as I try to build my own models.