> Markdown version of [/events/world-congress-2025/sessions/917-how-we-built-an-ai](https://www.wearedevelopers.com/events/world-congress-2025/sessions/917-how-we-built-an-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # How we built an AI-powered code reviewer in 80 hours - **Date:** Friday, Jul 11, 2025 - **Time:** 16:20–16:50 (30 min) - **Room:** Stage 2 - **Event:** World Congress 2025 - **Tags:** ai, aws, llms, node.js, serverless ## Recording [Watch recording](https://www.wearedevelopers.com/videos/1511-how-we-built-an-ai-powered-code-reviewer-in-80-hours) ## Description How hard can it be to build an AI-powered code reviewer using modern LLMs? Easier than you think—until it isn’t. In late 2024, I helped a client launch an AI-powered code reviewer. We built the initial prototype in the first few hours. But we soon encountered many unexpected challenges as we tried to productionize the idea into a coherent user experience. In this session, let me tell you the surprises, challenges, and lessons learned from building an AI-powered code reviewer and what it tells us about the current state of LLM technologies. ## Speaker ### [Yan Cui](https://www.wearedevelopers.com/@yan-cui) Developer Advocate at Lumigo ## Related talks at this congress - [Three years of putting LLMs into Software - Lessons learned](https://www.wearedevelopers.com/events/world-congress-2025/sessions/561-three-years-of) — Simon A.T. Jiménez - [ Evaluating AI models for code comprehension](https://www.wearedevelopers.com/events/world-congress-2025/sessions/723-evaluating-ai-models) — Merrill Lutsky - [AI-Powered Code Documentation: Simplify the Complex](https://www.wearedevelopers.com/events/world-congress-2025/sessions/719-ai-powered-code) — Patrick Schnell - [ The Limits of Prompting: ArchitectingTrustworthy Coding Agents](https://www.wearedevelopers.com/events/world-congress-2025/sessions/637-the-limits-of) — Nimrod Kor