Amazon

“normally that would have taken 40 or 50 people about a year to do. And we took five really smart people, AI forward thinking people building on agentic coding tools. And those five people rebuilt it in 65 days.”

AmazonPublished by the organization itself (earnings call), no named author

“Normally, this sort of activity might take a team of 40 people about a year to carefully build. Instead, the Bedrock team spun up a separable group of six very skilled engineers who were excited about starting over and building on our agentic coding service (Kiro)”

AmazonPublished by the organization itself (post), no named author

“90% of these teams used Kiro, among other internal tools that we have, and what they found was it wasn't about the tools, it was about the way that they worked. The teams that achieved step function improvements intentionally changed the way that they worked, and the other simply kind of sprinkled Kiro and some of the other tools that we have on top of their existing way of working.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“And sometime last year, we knew, or I say we, but the bedrock team knew that they were going to need to build a new inference data plane. But they had estimated it at 30 people over 18 months. This is a big, big service, and it was … take time to build the new one, migrate customers over, migrate models over, and they decided to take a step back. They took six people and they built it in 76 days with …”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“And completely anecdotally based on my own experience, I've really only felt maybe 10 to 20% more productive with all of these phases that have come before. But now inside of Amazon, we've been running pilots with different teams across the company, and we've been seeing a median of 4.5x productivity improvement and sometimes more than 10x.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“So another experiment that I want to talk about is an experimental sprint that was done in the Prime Video Organization. They took a 10-day sprint and they … experiment where they put, again, six engineers in a room and they let them go wild with Kiro. They brought down the project delivery time estimate from what was going to be 90 weeks down to 24, based on all of the progress they had made in this 10-day sprint.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“They watched 50 teams that were totally … distribution of early career folks, mid-career senior engineers, and that worked on existing systems. … And they watched them for the better part of last year, and they found something super interesting. They found that there was a big difference in the productivity gains that they saw between half of the teams and the other half. And in this case, they used a productivity metric of deployment velocity to production. … And they saw that for half of the teams, they achieved less than 3X increase.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“Previously, writing code manually was the bottleneck. I find that with an Amazon, we've found the speed of decision making becomes a new bottleneck. … When it used to take nine to 12 months to build a new product, it didn't matter so much in the overall wash of things if it took two months to make the decision to build the product and then two months to approve the launch. But now, those are the bottlenecks. … Often, I find that frontier engineering teams spend more time making decisions than they do writing code.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“And I like to define what we've been calling frontier developers inside of Amazon by three behaviors that I've been seeing. One is hands off coding, frontier developers write maybe … of the code that they produce. The rest is agents. The second is that they interact with their agents infrequently. They'll aim to get their coding assistant to run for up to hours at a time without their intervention. And third is that they minimize idle time. These frontier developers tend to run multiple agents in parallel, … through a backlog of tasks.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner

“The second one is slowing down to speed up. In almost every team that was interviewed, they reported that their productivity actually went down, as they intentionally adopted a new way of working. That's counterintuitive, right? You have to do intentional engineering work before you're gonna see that hockey stick curve in productivity improvement.”

Clare LiguoriSenior Principal Engineer, AWS · Practitioner