Our team at Invariant has built an awesome agent testing challenge for the holidays, that showcases how agent development can benefit from concepts known from test-driven software engineering.<p>You can play the challenge at the linked URL. You are given a pre-existing agent implementation where you can only change the system prompt and your goal is to make a small test suite of unit tests pass. The tool implementations are complete, but the agent needs to be instructed to use them properly.<p>The challenge was created to showcase two open source projects we released recently: A trace viewer for agent trajectories (Explorer, <a href="https://github.com/invariantlabs-ai/explorer">https://github.com/invariantlabs-ai/explorer</a>) and a library for building agent unit tests (Testing, <a href="https://github.com/invariantlabs-ai/invariant">https://github.com/invariantlabs-ai/invariant</a>).<p>Let us know what you think, we'll be around in the comment section. Happy holidays everyone!