Arize
Day 0 after signup
How to test an agent change end to end
Prompt-level, code-level, and full-agent experiments. Live Sep 3.
Email copy
Hi [First name], There are three useful scopes for an experiment: Playground: test one prompt. Code: test a Python function. Agent: test the deployed system, including routing, tools, and multi-step execution. On September 10, we will show the third workflow live in Arize AX. You’ll see how to run a dataset through a deployed agent, inspect linked traces, attach evaluators, and compare experiments before deciding whether a change is ready to ship. Join us for our live session: Prove it end-to-end: experiment on the full agent before you ship a change Register Now September 10th 2:00pm BST / 3:00pm CEST Virtual See you there, Marine @ Arize Arize AI, 260 California St., 4th floor, San Francisco, California 94111, United States of America Unsubscribe Manage preferences
