Skip to content

Details

Part 5 of the SambaNova coding agent series. Free live webinar with Kwasi Ankomah, Lead AI Architect at SambaNova Systems.
Every failed run contains information about how your agent could do better. Most teams stop at evaluation and fix problems by hand. In Part 5, Kwasi shows how to read failing agent runs, find the patterns behind them, and improve the agent automatically, without fine-tuning.
You will learn:

  • How to read and analyze an agent's failing traces to find what is going wrong
  • How to group individual failures into recurring failure modes
  • How to automatically update an agent's instructions, memory, and tools based on those failures
  • How to do it with off-the-shelf libraries instead of a bespoke pipeline
  • How to A/B test the improved agent against the baseline and measure the gain in pass@k, with no fine-tuning

Wed, Dec 2, 2026 | 11:00 AM PT | Virtual | Free
Register: https://datasciencedojo.com/event/improving-ai-agents-from-traces/

Related topics

Artificial Intelligence
Machine Learning
Data Science

Sponsors

Data Science Dojo

Data Science Dojo

Venue, speakers and food.

You may also like