Google product manager Ryan Salva oversees the company's developer AI tools, including Gemini CLI and Code Assist. In a revealing interview, he shares how AI coding has moved beyond autocomplete to full workflow automation, with developers spending 70-80% of their time directing AI through natural language rather than writing code directly. The shift signals a fundamental change in how software gets built.
Google's latest research reveals a striking timeline: most developers didn't start using AI coding tools until April 2024. That's when everything changed. "This corresponds fairly neatly to Claude 3 coming out and Gemini 2.5 coming out," says Ryan Salva, Google's product manager for developer tools. "This is really the dawn of the reasoning or thinking models."
Salva would know. He's responsible for tools like Gemini CLI and Gemini Code Assist, putting him at the center of how AI is reshaping software development. His team's new third-party research published Tuesday shows the rapid adoption isn't just hype - it's a fundamental shift in how code gets written.
The breakthrough wasn't just better language models. "Around that same time, we got much better at tool-calling," Salva explains. "For coding tasks, you really need to leverage external information to problem solve. It may need to grep, compile the code, run unit tests. Tool-calling gave models the ability to self-correct as they move along."
This self-correction capability transforms coding from a conversation into an autonomous workflow. Salva uses Gemini CLI for 70-80% of his development work, but not the way you might expect. "I would say probably 70% to 80% of my work is me working in the terminal with natural language," he reveals. "I'm using the IDE as a place to read the code, rather than to write the code."
His process starts with under-specified GitHub issues - the kind of vague bug reports every developer knows. He feeds these into Gemini CLI to generate robust requirement documents, often 100 lines of technical specifications. Then the AI writes the code based on those specs and the team's documented preferences for testing and dependency management.
"As Gemini CLI is going through and doing the troubleshooting, I'll have it update my requirements doc saying, 'I fixed this step. Now I'm on to the next step,'" Salva describes. Each step creates its own commit and pull request, creating an audit trail that lets developers rewind or undo changes.
This workflow represents a fundamental shift from the IDE-centric development that's dominated for three decades. "You had the IDE, you had the browser, and you had the terminal window," Salva notes. "I think that's still largely the case, but I suspect that over time we'll end up spending a lot more time working with the requirements, and the amount of time spent in the IDE will gradually shrink."
The implications go beyond productivity gains. When asked about developer job security, Salva sees evolution rather than elimination. "I think that your job as a developer is going to look a lot more like an architect," he predicts. "It is going to be about taking big, complex problems and breaking them down into smaller, solvable tasks. You'll need to be thinking about the bigger picture about what you're trying to produce, rather than the intermediate language to express that in machine code."
Salva practices what he preaches, using a heterogeneous mix of tools including Zed, VS Code, Cursor, and Windsurf alongside command-line AI tools. "I'm interested in just seeing how the world works and how the industry is evolving," he explains. Even for professional work as a product manager, AI handles specification and requirements documentation.
The research timing isn't coincidental. Google faces intense competition in AI coding tools from Microsoft's GitHub Copilot, Anthropic's Claude, and startups like Cursor. The company's developer tools strategy hinges on demonstrating that AI coding has moved beyond simple autocomplete to full workflow automation.
But challenges remain. The April 2024 adoption timeline suggests most developers are still early in their AI coding journey. Tool-calling capabilities that enable self-correction are relatively new, and many developers haven't yet reorganized their workflows around natural language direction rather than direct coding.
Salva's vision of developers as architects also raises questions about skill development. If future programmers spend less time writing code directly, how do they develop the deep understanding needed to architect complex systems? The industry is still working out these implications.
For now, the data shows a clear trend: AI coding tools are moving from experimental to essential. Google's research captures a inflection point where reasoning models and tool-calling capabilities have made AI coding workflows practical for real development tasks. The question isn't whether AI will transform coding, but how quickly developers will adapt their processes to take advantage.
The shift from coding to directing AI represents more than a productivity boost - it's a fundamental change in what it means to be a developer. As AI tools handle more of the syntax and implementation details, developers are evolving into system architects who focus on problem decomposition and requirements rather than code syntax. Google's research captures this transformation at a crucial moment, just as the technology has matured enough for mainstream adoption. The industry is still figuring out the long-term implications, but one thing is clear: the developers who adapt to this new workflow will have a significant advantage over those who don't.
