World Congress 2025
July 10, 2025 · 12:50–13:20
Stage 2
Three years of putting LLMs into Software - Lessons learned
Simon A.T. Jiménez
create better software specifications in less time
World Congress 2025
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
How we built an AI-powered code reviewer in 80 hours
July 11, 2025
16:20
–
16:50
·
30
min
Stage 2
ai
llms
aws
serverless
node.js
What this session covers
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.
Related talks at this congress
World Congress 2025
July 11, 2025 · 09:00–09:30
Stage 11
Evaluating AI models for code comprehension
Merrill Lutsky
Graphite CEO and Co-founder
World Congress 2025
July 11, 2025 · 09:00–09:30
Stage 7
AI-Powered Code Documentation: Simplify the Complex
Patrick Schnell
Patrick Schnell, AI-enabler and CEO at schnell.digital GmbH
World Congress 2025
July 10, 2025 · 15:30–16:00
Stage 2
The Limits of Prompting: ArchitectingTrustworthy Coding Agents
Nimrod Kor
Co-founder & CTO @ Baz
