AI-powered Code Review
summary
Claim: an LLM-driven code‑review system that collects formal rules from security, architecture and team leads into a middleware rules layer, runs reviews inside an IDE extension and auto-fixes issues like hardcoded secrets and naming violations. Implementation uses hosted GPUs (port‑forwarded to a local Ollama instance) and models such as Qwen Coder 2.5/3B, tunes seed/top‑k/temperature for deterministic outputs, shows a working PoC, and cites studies claiming up to ~55% faster coding with AI.
AI-written summary · about
chapters (9)
- 0:00Introduction and speaker background
- 2:28Current code review challenges
- 8:16Manual code review bottlenecks
- 11:11AI solutions for code review
- 14:48AI-powered solution architecture
- 17:20Practical AI implementation demo
- 22:42Solution demo walkthrough
- 24:31Key challenges and solutions
- 25:13Conclusion and Q&A
related talks
23mAI assisted code reviews Quality and Security at Scale
34mAI and Code Quality: Building a Synergy with Human Intelligence
07mLightning Talk: Shift Left With AI: Smarter Code Reviews for DevOps...
14mAI-Powered Code Review and Quality Assurance
26mCode Review Around Artificial Intelligence: Good and Bad Practices
20mAI inside the IDE
10mAI powered entomology: Lessons from millions of AI code reviews
59mUsing AI for Secure Code Creation: Enhancing Software Security