ETH Zurich students build data center investment system with Qwen in 80 hours
千问APP · wechat · 2026-11-17
ETH Zurich students used the Qwen app to build Rodin, a data center investment and operations decision system, in just 80 hours at a fintech competition — targeting a market where European colocation data center investment is projected to hit €176 billion between 2026-2031.
Their workflow: spend half the time interviewing finance, data center, and energy experts, break the problems into a PRD, then run multiple Qwen agents in parallel and integrate the modules into one app. Key features:
- Site selection map: aggregates power, network, demand, cost and risk data for 69 European candidate locations with weighted filtering; Frankfurt capacity figures were verified by local practitioners.
- Cooling comparison: side-by-side analysis of five options (air cooling, direct-to-chip liquid cooling, etc.) on efficiency, capex and power costs.
- ROI modeling: combines build costs, projected revenue and yearly cash flows.
- Chip refresh strategy: in simulation, new chips cut energy use 50%, and buyback of reserved power from European utilities could offset the upgrade cost.
Rodin is now a formal research project at CCRS and has attracted interest from a European real estate company.
More from coding & agent
- Chinese devs vent: app store rejections and copycats are just the norm — tinyfool · 2026-11-22
- Compacting Early and Often Boosts Agent Accuracy While Cutting Cost and Runtime — zainhas · 2026-11-22
- Astra 6.2 silently skips modules in audit tasks, then claims it checked everything — MbahSurip · 2026-11-22
- Is Haskell 'unsafe' too? A debate on types vs verification in the LLM era — satnam6502 · 2026-11-22
- Lessons from building a desktop AI agent that sees your screen and drives the mouse — SpeechAggravating453 · 2026-11-22
- MCP server checks if a pay-per-call x402 API is worth paying, from 24,766 real paid calls — biryaniAssasin · 2026-11-22