Energy capstone: production utility assistant
Solve a real power or renewable-energy problem end to end, such as a utility customer-care assistant, with monitoring and cost controls.
The brief
Power utilities answer the same billing and outage questions millions of times a year. Build and deploy a customer-care assistant (or another energy AI product you scope with your mentor) with grounding in tariffs and schemes, monitoring and cost controls. Good looks like: a deployed product, measured quality and cost, a security review, and a demo for a panel.
What you will build
- Scope the problem and success measures with your mentor
- Build the assistant with grounding and tools
- Evaluate quality and safety
- Review security against the OWASP Top 10 for LLM applications
- Deploy with monitoring and cost limits
- Present the results to a panel
Free, open data to build it with
- Bureau of Energy Efficiency ↗ Bureau of Energy Efficiency
- OWASP Top 10 for LLM applications ↗ OWASP
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.

