# Weave Got This

- **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:** [Anna Saltveit](https://cerebralvalley.ai/u/BananaDuck)
- **GitHub:** https://github.com/asaltveit/map-searcher
- **Demo video:** https://drive.google.com/file/d/1IU8G0S1-YxZNmbd8DQp1mh3Fh4dlVUgu/view?usp=drive_link
- **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/57

An AI-powered research and mapping app that turns natural-language questions into live map updates. You ask about places, routes, or current events in plain language (typed or spoken); AI agents run the research—searching stored findings and the web, with sources—then a map agent drives the UI by adding layers, pins, and viewport changes to a MapLibre map. The interface (map and chat) updates in response to the agents, so you see current research visualized on the map as the workflow runs. The project supports self-healing agents and workflows: W&B Weave traces research and map runs, automated scorers evaluate quality, and improvement reports suggest persona and config updates so agents get better over time.

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/57. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt