Evaluate Coding Agents with Confidence: Tests, Trajectories & SambaEval
Details
Part 4 of the SambaNova coding agent series. Free live webinar with Kwasi Ankomah, Lead AI Architect at SambaNova Systems.
Coding agents have a luxury most agents don't: ground truth. The tests pass or they don't. Kwasi builds a full evaluation harness around that signal: pass@k over a task set, trajectory evaluation and full tracing, then uses SambaEval to pick the best SambaNova model for the executor role.
You will learn:
- Why tests make coding agents uniquely measurable
- How to measure pass@k across a task set
- How to run trajectory evaluation
- How to add full tracing so every run can be inspected
- How to use SambaEval to select the best model for the executor role
Wed, Nov 18, 2026 | 11:00 AM PT | Virtual | Free
Register to get the joining details: https://datasciencedojo.com/event/evaluating-coding-agents-sambaeval/

