# OzWizards

- **Event:** [OpenEnv Hackathon SF](https://cerebralvalley.ai/e/openenv-hackathon-sf)
- **When:** Mar 7 at 9:00 AM – Mar 8 at 12:00 AM (PST)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Rajashekar V](https://cerebralvalley.ai/u/raj)
- **GitHub:** https://github.com/rajashekarcs2023/openenv-RL
- **Website:** https://colab.research.google.com/github/rajashekarcs2023/openenv-RL/blob/main/driftpa/colab_trainin   g.ipynb
- **Demo video:** https://youtu.be/cpdzrMLPAOQ
- **Hugging Face:** https://rajv24-driftpa.hf.space
- **Gallery:** https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery/104

DriftPA trains LLM agents to be reliable personal executive assistants in a world that breaks without warning.

Real AI assistants fail in production because APIs change schema mid-session, tasks expire while the agent deliberates, and wrong bookings or emails can't be undone. DriftPA is an RL environment that simulates exactly these four failure modes simultaneously: schema drift (field names change mid-episode), time pressure (urgent tasks expire), irreversible actions (book/reply/cancel can't be undone), and policy drift (cancellation windows tighten).

An untrained agent scores -9.55 mean reward — it uses stale API fields, misses the boss's urgent email, double-books dinner, and triggers cascade failures. A GRPO-trained agent learns to call list_tools() after drift, prioritize by urgency, and commit to irreversible actions only when safe.

Optimal score: +22. Untrained mean: -9.55. That 31-point gap is the problem we solve.

---

Markdown version of https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery/104. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt