Developer Tool Integrations with AI — The AWS Approach

Developer tool integration and AI differentiate workflows to achieve that “fluid” state developers strive for in their work.

Amazon CodeCatalyst and Amazon CodeWhisperer exemplify how developer workflows are accelerating and helping to create these fluid states. That’s a big part of the story we hear from Harry Mower, director, AWS DevOps Services, and Doug Seven, director, Software Development, AWS CodeWhisperer, from our recording in Seattle earlier in April for this week’s AWS Developer Innovation Day.

CodeCatalyst serves as an end-to-end integrated DevOps toolchain that provides developers with everything they need to go from planning through to deployment, Mower said. CodeWhisperer is an AI coding companion that generates whole-line and full-line function code recommendations in an integrated development environment (IDE).

CodeWhisperer is part of the IDE, Seven said. The acceleration is two-fold. CodeCatalyst speeds the end-to-end integration process, and CodeWhisper accelerates writing code through generative AI.

CodeCatalyst and CodeWhisperer reduce the “paper cuts,” those little things that get in the way of doing creative work. They also reflect the rich history of developer communities to build out tools to make the process of building software easier.

“You know, from a developer perspective, I think this is a great evolution of the kinds of things we’ve seen, really over the last decade or two in terms of developer tools, trying to build capabilities that just make the process of building software easier,” Seven said.

Both Mower and Seven shared the lessons learned at AWS about tooling and how customers benefit from that knowledge.

“Amazon’s famous for this idea that, like, if you build it, you run it,” Mower said. “And so we expect a lot from our development teams to be able to do a lot of things. They’ve got to plan their work, they’ve got to execute the job, they’ve got to operate their services once they’re in production. And so this idea, like paper cuts, are all the little things that sort of take away from the ability to deliver the value to the customer, as opposed to that sunk cost stuff that you do operating services. And we overcome that internally by trying to automate everything.”

It’s a lot about just getting to that flow state, Mower said. Hours will go by with developers immersed in the code. Later, the tools go into production, and developers start using them. Then there is all the collaboration among the developers and the teams to build something more intricate and more complicated.

“There’s joy in that as well, right?” Mower said. “There’s joy in seeing all that stuff, move through these pipelines, and just watching it flow very easily. And that’s what we’re trying to make. We’re trying to put that into the product – that  joy of seeing it being used and deployed and running for, you know, hopefully, millions of people to consume.”