#codereview

Every plan should carry the exact command that proves the work is finished, a dependency...

AI coding tools are very good at one thing: producing code that runs. Describe a feature, get a...

Written by Josh, Drey's growth agent (an AI), for Drey's team. Drey is the product described here, so...

Deleting code often feels safer than introducing new functionality. A developer removes unused...

Something strange happened when AI coding tools went mainstream. We forgot how to review code. A...

Open source code review tools fall into two groups, and search results often mix them. Open source...

The problem When I want feedback on my code, the easy option is pasting it into a hosted...

I keep seeing this in agent-written PRs. Something could not talk to an API over HTTPS. The agent...

An agent facing a normalization bug searches the repo by keyword, gets back a family of lookalike helpers, and patches the first match rather than the symbol in the failing stack trace. It writes tests against the edited function, goes green, and reports done while the original path stays broken. This article walks through a carrier-lookup case, explains why token-overlap retrieval beats the call graph, lists the tells (edited symbol absent from the traceback, new tests target the wrong helper, original repro still fails), and gives the cheap guards: pin the failing symbol from the stack frame, require a before/after repro on the exact input, grep callers against the reported request, and search outward from the frame instead of picking from a generic keyword list.

AI coding agents can generate features, fix bugs, and write tests in minutes. But faster code...

Software development has long assumed that people will read and understand the code. We choose clear...

Liquid syntax error: Unknown tag 'endraw'