Detail

Towards Self-Driving Codebases

Wed, 02 Sep 2026 00:00:00 +0000

Agents can oneshot games that are actually fun. With the right guardrails, agents can execute incredibly impressive migrations in complex codebases, even rewrites in new languages. But basically all “real” software work still has human engineers driving the process. How do we get to a place where a much bigger portion of the work gets handled for us, without requiring our attention?

It seems like agents should be able to build entire software systems themselves. Why is this going so poorly in practice? What new primitives will we need to make it all work? How far can this go?

What kinds of bugs does AI generate?

Sun, 28 Jun 2026 00:00:00 +0000

What bugs are agents generating? How does vibecoded software break? Where is automated code review coming up short? Is each bug a random oneoff, or can we characterize clear patterns? Are engineers at different companies creating the same few bugs over and over?

To answer these questions, we took 1,000 example bugs from 99 customer codebases and clustered them.

Same mistakes across codebases

We started with 1,000 bugs, each flagged by Detail and subsequently fixed by the customer. We rewrote each bug into a language-agnostic and company-free description of the specific mechanism of the bug, then embedded and clustered those descriptions to group bugs by how they fail.

Detail cleans up your Dead Code

Wed, 10 Jun 2026 00:00:00 +0000

tl;dr: Detail can now detect dead code in your codebase and open pull requests to remove it. To enable, go to Dead Code in the Detail dashboard , select a repository, and enable it.

Every codebase accumulates dead code. Products evolve, features get reworked, a refactor orphans a helper, an experiment gets rolled back and a stray endpoint stays behind. Dead code silently raises the cost of every future change by distracting and confusing the agents that write our software. And agents prolifically generate it.

Benchmarking a Bug Scanner

Thu, 30 Apr 2026 00:00:00 +0000

We’re all coding with agents now, but delivering high quality software at 10x velocity remains an open problem. Code review bots are an important start, but a lot of bugs are still landing in production. Even top products are accumulating a layer of low-grade brokenness.¹ We need new ways to make products secure and high quality.

We built a new kind of bug scanner to solve this problem.

The hard part about building a bug scanner is that any meaningfully complicated codebase has many thousands of bugs, and the vast majority don’t matter. You want to reserve human attention (and your tokens) for the bugs that matter. So, one of the most important ways we benchmark ourselves is that we want the bugs we generate to be significantly more important than the typical finding from a code review bot.