What slows teams down once agents write the code?

“Coding agents abruptly changed that reality. They can turn a ticket into a pull request in minutes, so teams end up getting greater numbers of PRs, much faster. Review didn't speed up with them and, as we well know, it became the bottleneck.”

Simon MapleHead of Developer Relations · Leader, Tessl

“As code generation becomes faster, code reviews started becoming a bottleneck. We help reviewers by keeping pull requests small and providing all relevant context, but ultimately, we found that giving agents the tools to test their integrations autonomously gives the reviewer the most confidence.”

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

“the amount of tests across our codebase grew 10x and we added a nominal amount of engineers. This all led to a 25x increase in CI jobs over a six month period”

Sachin MalhotraAnthropic engineer (author) · Practitioner, Anthropic

“Writing code is no longer the constraint, and once PR review gets accelerated, CI starts feeling the pressure.”

Sachin MalhotraAnthropic engineer (author) · Practitioner, Anthropic

“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, Amazon

“Back in 2024, we were seeing that engineers would get their first review within three hours. Now, in 2026, that has grown to nine hours, in addition to all of the volume changes. So in short, code review is now the bottleneck that we are running into.”

Will BondStaff Engineer, AI Foundations team, Development Platform organization · Practitioner, Uber

“One of the other things that we're really thinking about now is bottlenecks. We're now putting more strain on our infrastructure so we're trying to anticipate where our CI capacity needs to be and make the right foundational investments there. There's only so many experiments that we can feasibly run as well. So that's another bottleneck. And then lastly, too, … decision-making … It's not about … can we build? We know we can probably build it now. It's more of a question of should we build it?”

Adam HudaSenior Engineering Leader, AI Developer Tools, Uber · Leader, Uber

“Because before, you could probably argue that the coding part was the bottleneck in our kind of product lifecycle. But now … is doing all the coding. And when he took over the coding, we found that the requirement part, the first part, is the new bottleneck. Because me and …, we can be tied up in some prioritized work. And then a product owner creates a new feature or a feature request in an Epic in the boards. And we won't kind of look at that before some time has passed. And then we have some questions, clarifications. And the product owner might not even remember what she wanted the first place when she wrote it. And it becomes this async ping-pong where you kind of try to figure out what to do. And you're not able to begin the implementation.”

Hallstein BrøtanSenior consultant, Novanet; developer on Nordic Corporate Bank's system · Practitioner, Nordic Corporate Bank

“cortex hit exactly this. The moment we ran Claude Code at full throttle, writing speed jumped by an order of magnitude or more. Meanwhile the human time available to read and approve PRs only grew linearly. If the reviewer (=me) took a day off, the whole org stalled -- a classic single point of failure.”

Ryosuke TsujiCTO · Executive, airCloset

“Code output per Anthropic engineer has grown 200% in the last year. Code review has become a bottleneck, and we hear the same from customers every week.”

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

“As we ship more code with agents, the bottleneck shifted from writing code to reviewing it. Devin Review turns large, complex GitHub PRs into intuitively organized diffs and precise explanations. We use it for every PR now.”

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

“When we decided to rebuild our apps natively, we went back to the drawing board with a basic question: how should a mobile app be built when agents write most of the code? The biggest bottleneck we had was the feedback loop. An agent can write a screen in minutes, but proving that the screen works requires an emulator, a build, a tap script, and a lot of patience.”

Thiago MagalhaesAuthor, Shopify Engineering blog · Practitioner, Shopify

“My advice to engineering teams is, whether you build or buy, assume your architecture will be at a 25x load within two quarters.”

Sachin MalhotraAnthropic engineer (author) · Practitioner, Anthropic

“So the next thing we're going to do is add flow control. Because the other problem that we had when we did this was that if we were at a customer site for a week or if we were traveling or spent six days working on slides instead of writing code, the PRs from all of our loops would just stack up. They'd duplicate work. They'd conflict. And we wouldn't get around to doing it. And the loop's work is important, but it's not that important. And so now we just had all this junk we had to deal with…”

Kyle MisteleCo-founder, HumanLayer · Executive, HumanLayer

“Our team averages 10.8 PRs per engineer per week, 2.5x the 90th percentile according to DX benchmarks. But every one of those PRs still needed a human to look at it, and the review queue became the constraint.”

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

“Pull requests arrive faster than human-driven review can stay meaningful.”

Bence A. TóthAuthor on the Zendesk Engineering blog (role not stated on the pages read) · Practitioner, Zendesk

“Right now, … the workflow for the developers has changed and is changing further. They're spending more and more time in planning and code review because there's so much more code being generated that they're being forced to do it. This probably isn't the favorite type of work that developers love doing, code review.”

Ty SmithPrincipal Engineer, AI & Developer Productivity, Uber · Practitioner, Uber

“At industrial scale, a flaky test or broken environment that a single developer can work around turns into a failure that interrupts every agent run.”

Michael TruellAuthor of the Cursor blog post; CEO of Cursor per the lead record (the page gives no title) · Executive, Cursor (Anysphere)

“year over year, the number of CI jobs also doubled or more than doubled. So we had to like also like beef up whole bunch of foundations in this space”

Uday Kiran MedisettyDistinguished Engineer, Uber · Practitioner, Uber

“And … since the beginning of this year at Anthropic, we've seen an 8X increase in code output per engineer. And this is just unheard of in the industry. … And the thing that we did to get to the … 8X is we systematically improve a bottleneck at a time. … We throw [Claude] at it and [Claude] is the coding. The next bottleneck is the code review. … And so just like one step at a time, we unbottleneck every part of the process.”

Boris ChernyCreator and head of Claude Code, Anthropic · Leader, Anthropic

“We are definitely still bottlenecked on reviews, especially for things that are touching some architecture pieces. And it's actually more subtle than just being bottlenecked on review, … we can carve out time differently. It's … bottlenecked on human ability to even fully conceptualize what we're doing.”

Mike KriegerHead of Anthropic Labs · Leader, Anthropic

“We can now take bigger swings that say, oh, reviews are a bottleneck, let's try to make high quality … reviews. Is toil work like cleaning up feature flags or cleaning up things or doing small changes of bottleneck? Let's give you that ability to get you out of that zone. And then measure directly.”

Nikhil RamakrishnanAI Foundations & Developer Experience · Practitioner, Uber