AI coding tools are everywhere now, but they don't make teams faster on their own

Back in 2019, a software engineer might have heard about deep learning breakthroughs in computer vision or translation, but few imagined a direct impact on their own daily work. Five years later that has changed dramatically: GitHub's survey of 2,000 people on software development teams across the U.S., Brazil, India, and Germany found that more than 97% of respondents had used AI coding tools at work at some point, a finding consistent across all four countries. The open question is what happens after that first use: a smaller share of respondents said their companies actively encourage AI tool adoption, showing that individual enthusiasm doesn't automatically turn into organizational adoption.

Google built its response inside the internal development environment where engineers spend most of their time, working on both the inner loop (IDE, code review, code search) and the outer loop (bug management, planning), building on the ML-based code completion it had already rolled out internally. The team frames this as part of an ongoing transformation of internal tooling rather than a one-off project. On the measurement side, the 2025 DORA report on AI-assisted software development takes a different angle: instead of asking whether AI works in the abstract, it looks at how AI amplifies whatever dynamics, good or bad, already exist inside an organization.

The picture that emerges is not one of automatic productivity gains. The 2025 DORA report concludes that AI does not automatically improve software delivery performance; instead it acts as an amplifier of the practices and organizational conditions already in place. At the same time, GitHub's survey shows near-universal individual adoption (97% having used AI tools at least once) paired with uneven company-level support, with only a smaller share of companies actively pushing adoption. These are two sides of the same transition: the tools have reached everyone, but the organizational payoff hasn't caught up yet.

Engineering leaders can't treat AI adoption as a simple switch to flip: if delivery practices are already solid, AI amplifies the gains; if they're weak, it amplifies the weaknesses too. The useful first step isn't counting how many people use an AI tool, it's checking whether the company is genuinely backing that use with consistent incentives and processes, because widespread individual use, as the 97% figure shows, doesn't by itself guarantee better team performance.