Jake McCrary

We weren't solving the right problem in code reviews. Our engineers were spending hours catching accessibility violations, security patterns, and architectural anti-patterns during PR reviews. Not debating design decisions. Not mentoring. Just... repetitive pattern detection that machines should handle. The real cost? Senior engineers burning cognitive capacity on checklist items instead of strategic thinking. So we built something different: an agentic code review system that learns from every merge request outcome. What makes this agentic (not just "AI-assisted"): 🤖 7+ language-specific agents with specialized pattern detection - each agent understands the idioms and anti-patterns of TypeScript, Java, Python 🧠 Autonomous learning pipeline - extracts patterns from review history, validates them, and continuously improves from every interaction 🎯 Auto-approval agent with confidence thresholds - escalates to humans only when needed (≥0.7 confidence, ≥0.8 accuracy, ≥5 observations) 📊 Self-correcting through feedback - yes, there are false positives initially, but that's the point: every correction teaches the system, reducing noise over time The real shift: moving feedback left We're now building an IDE plugin that catches these patterns during development, not during review. Why wait days for a PR comment when you can get feedback in seconds while you're still in flow state? This is the compounding effect of agentic systems: faster feedback loops → more learning cycles → better pattern detection → less cognitive load on engineers. The transformation: Engineers now orchestrate quality rather than enforce it manually. They set standards, validate edge cases, and focus on architecture - while agents handle pattern detection at scale and learn from their corrections. This is what agentic SDLC looks like in practice: not replacing engineers, but fundamentally changing how they allocate their time and expertise. The question every engineering leader should be asking: Are you building productivity tools, or are you transforming how your engineers think?

17

10 Comments

Just submitted MAM: Maker Auction Markets to https://lnkd.in/gdfEhNhH (Designing Defi) MAM eliminates entire classes of MEV by shifting from reactive pricing to time bound collateralized commitments and user constraints/intents. Im curious do you think the way things are currently are the way things always have to be? We are what? 12-15 years into this industry? Innovation has only just begun.

1

Check out this short, clear, and helpful video by Matt Pocock on using the Red -> Green -> Refactor approach of Test-Driven Development (TDD) with Claude Code. I've been using this approach, and find it to work really well. I'll be updating my workflow with Claude Skills to keep Claude Code more focused and not try to create too many tests at a time. Have you tried this approach?

4

Screw vibecoding. You know what LLM coding agents are *really* useful for? Reverse-engineering legacy code! "Hey can you research and explain how the flux capacitor settings are loaded, specifically where are the margadon-level overrides applied exactly?" It's a lifesaver.

388

100 Comments

Anthropic shipped multi-agent code review for Claude Code. Their internal numbers: substantive review comments went from 16% to 54% of PRs. Less than 1% of findings marked incorrect. If your team's code output has doubled but your review capacity hasn't, this is worth watching. More expensive than Claude Code GitHub Action though. https://lnkd.in/g_Pg-SiS

6

I've always found myself switching to Claude models when working through coding problems. There's just something about how Claude handles context and works its way through large code bases and complex logic. With Claude Code, that workflow has become ridiculously smooth.                                                    Also been experimenting with OpenAI's Codex (GPT-5 powered) and the results are way better than previous versions. The code generation quality has taken a real jump. Now here's where it gets interesting. You keep hearing stories about developers opening multiple coding agents, feeding them the same task, and manually cross-referencing outputs to find the best solution. Turns out there's an easier way. By integrating Codex as a skill inside Claude Code, you get insights from both agents in a single terminal session when you need. No tab switching, no copy-pasting, no manual comparison. Claude Code orchestrates the workflow while Codex brings its strengths. Best of both worlds in one window. Claude OpenAI

35