AIQB
TutorialsOrdinary

What AI code reviewers miss, and the checks I built for it

Source: DEV Community·

Summary

We replayed 45 findings from a careful human code review against automated rules. They caught 9. Here is what that taught us about which problems tools can own, and the toolkit we built around it.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-af7788ced5376373b5ed60cf
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
The Architectural Collapse: 'The AI Layoff Trap'
Why Senior Engineers Are the True Targets of 'The AI Layoff Trap' There is an ironic...
Source: DEV Community
TutorialsOrdinary
I recorded 87 Claude Code sessions to find out where the money goes
I wanted to know why AI coding agents get expensive on real codebases, so I stopped guessing and...
Source: DEV Community · Claude
TutorialsOrdinary
Claude Code Sends a Background Agent's Whole Transcript Every 30s for a 3-5 Word Status
agent_summary asks the agent's own model to label its last action in 3-5 words. How the timer works, how to measure its share, and why the numbers disagree.
Source: DEV Community · Claude
TutorialsOrdinary
AI Agent Tool Calls Are Distributed Transactions: Who Owns the Retry?
An agent with write tools is coordinating distributed transactions over an unreliable network, and...
Source: DEV Community
TutorialsOrdinary
I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.
From DevOps to AI Platform Engineering — Part 1 I'm a DevOps engineer. I've spent years running...
Source: DEV Community · ChatGPT
TutorialsOrdinary
Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents
Many RAG failures that look like model problems are ingestion problems. If a parser flattens a PDF...
Source: DEV Community
TutorialsOrdinary
Your LLM's JSON passed the schema. It was still wrong.
Deterministic contract tests for structured LLM output on the JVM, and what 120 real documents taught...
Source: DEV Community
TutorialsOrdinary
Your AI code reviewer isn't a second opinion. It may be the first opinion again.
A model writes the change. A model reviews the change and says it looks good. The pull request now...
Source: DEV Community
TutorialsOrdinary
The Agent Added a Second Copy of a Utility the Repo Already Had
Why an agent's freshly written helper often duplicates an existing utility, and how silent forks drift into real bugs.
Source: DEV Community
TutorialsOrdinary
9 Commands That Leave a Coding Agent Waiting for a Keystroke, and the Fix for Each
git commit, npx, apt, ssh, psql, terraform apply, gh auth login: each can stall an AI coding agent on a prompt. The flag or env var that stops each one.
Source: DEV Community