Ashby Engineering reports stable quality despite majority AI-generated code since 2025
By
Colin Howe
Summary
Ashby Engineering reports that since August 2025, over half of their production code has been AI-generated (via Cursor), yet customer issues have remained stable with no regressions in code quality, velocity, or engineer onboarding time. The company argues that AI-assisted coding is not a toy project but a viable approach for a serious enterprise software suite serving high-growth companies.
Source
Hacker NewsAshby Engineering reports stable quality despite majority AI-generated code since 2025ashbyhq.comKey quotes
· 4 pulledSince August 2025, more than half of the new code hitting Ashby's production systems has been AI-generated, yet customer issues remain broadly stable.
More customers. More AI-written code. The sky didn't fall.
We've also not seen any regressions in code quality, velocity, or onboarding time for engineers (anecdotally, we've seen comprehension of the codebase increase!).
This isn't a toy project. Ashby is a suite
You might also wanna read
AI-generated code passes reviews with high marks but causes more production failures
The article examines a growing problem in the tech industry: while AI-generated code receives high quality ratings during review due to its
helpnetsecurity.com·13d ago
The Verification Crisis: How AI-Generated Code Is Reshaping Software Development
The article examines the rapid integration of AI in software development, highlighting staggering statistics: Cursor alone generates nearly
dev.to·29d ago
AI coding agents gain developer trust, bypassing human code reviews
The article reports on the growing trend of developers trusting AI coding agents like Cursor to work autonomously, with AI-generated code in
businessinsider.com·12h ago
Study finds most developers refuse to code without AI, raising quality concerns
A February 2026 study by AI research lab METR reveals that most developers now refuse to work without AI coding tools. While these tools hel
techcrunch.com·29d ago
AI coding shifts from prompts to loops, making verification the key challenge for engineering teams
The article discusses a paradigm shift in AI-assisted software development, moving from individual prompt engineering to designing "loops" t
bit.ly·14d ago
Workshop: Closing the verification gap in AI-generated code through invariant-based self-correction
This article/workshop announcement discusses the verification gap in AI-assisted coding. As AI tools like Claude Code and Cursor accelerate
luma.com·4d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.