# GEB

- **Event:** [WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80)
- **When:** Jan 31 at 9:00 AM – Feb 1 at 5:00 PM (PST)
- **Where:** 400 California St, San Francisco, CA
- **Team:** [Kian Kyars](https://cerebralvalley.ai/u/kian)
- **GitHub:** https://github.com/kiankyars/haggler
- **Demo video:** https://youtu.be/TE4BKvLXE-I
- **Gallery:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/58

My project is called Haggler and it is a negotiation/refund agent which autonomously self-improves such that you can get refunds without having the pressure of negotiating yourself. It uses Redis to store the different negotiation tactics, Pipecat for the voice agent harnessing, GCP for the speech to speech model, and weave for the observability layer.

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/58. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt