See what agents choose, where they get stuck, and what to improve in your docs, examples, and tooling.
Record what coding agents do. See what to improve.
From the researchers behind the original What Claude Code Chooses study.
Latest research / October 1, 2026
All 8 builds used Cloudflare Workers and D1 through ChatGPT Sites, with ChatGPT sign-in. Follow the builds, see the apps, and compare their approaches to scheduled scraping.
Two products
01 / Choices, findings, playbooks
Measure when coding agents choose your product, what they choose instead, and why. Get findings and prioritized playbooks for your team.
02 / Changes, tests, results
Make a change to your docs, skills, or tooling. Rerun the same task to see what gets better or worse, then iterate.
More from our research
Our original study / February 2026
Our original What Claude Code Chooses study put numbers behind agents’ developer-tool decisions. Today, we help developer tool teams measure and improve how coding agents find, understand, and use their products.
Read the original studySafety / April 2026
Six development tasks leave the security defaults unspecified. The report checks the resulting code against 33 exploit tests.
Read studyNew Amplifying research on coding agents, delivered by email.
Tell us what you’re working on. We’ll show you where Amplifying can help.