Chintan Turakhia is the Head of Engineering for Base App and leads AI acceleration within Coinbase. Over the past year, he’s been pushing agents deeper into every layer of product development. By early 2026, he felt something had shifted underneath them. Agents had become genuinely capable, and the workflows his team had built around the previous generation of tools were already holding them back. We spoke with Chintan about how he got there, and what he did next.
In January 2026, Chintan asked his entire engineering organisation to delete their IDEs and write zero lines of code. For two weeks, every engineer at Base would have to do their job without touching a code editor. The point was to figure out how work actually gets done when agents are doing most of it, not humans.
The real story is in what led them here, and in the growing divide it reveals between companies that layer AI onto existing workflows and those that tear them out and start again.
The hidden tax of asking questions
At most workplaces, progress happens through asking questions. Unsure how something works? Slack a teammate. Notice a bug? Mention it in a channel. It’s the most natural way of working there is.
Asking costs nothing. Answering, on the other hand, is very expensive. It pulls someone out of whatever they were building, forces a context switch, and burns focus that’s hard to recover. Small teams can absorb this cost. At a company of thousands, with everyone taking the path of least resistance, it really starts to slow you down.
As an engineer, my interest is in having my work presented in a way that makes it easy to know what I can pick up right now and keep track of all the loose ends, what I’m blocked on and updates to projects as we go. Linear enables me to do that.
“Linear Asks ensures everything gets collected into a single triage queue,” adds Wilf, “enabling us to easily review and groom our backlog, saving us time from losing feedback or having to collect and organize feature requests ourselves. Craft is at the heart of everything we do. We care deeply about solving customer problems in delightfully simple yet complete ways. We want to build products and customer relationships that last, and it’s important to us that our own tools and processes do too.”