How is AI changing code review?
Most agree AI is automating and accelerating code review, often acting as a first filter or reviewer, though human or peer oversight is still seen as necessary by several respondents.
8 answers
Answers


Sagnik Nandy
Chief Technology Officer · Docusign
Auto‑generating PRs
Sagnik Nandy says AI coding agents create a PR and send it over, after which engineers can review it and ask for more changes, and GitHub code owners must approve and merge it.
The answer starts at 22:05.
The Engineering Leadership Podcast · Listen on Apple Podcasts
Gautam Korlam
Principal Engineer · Sonar
First‑pass automated reviews
Gautam Korlam says AI is changing code review by enabling first-pass automated reviews, so humans aren't doing every single review; without that, reviewers become the bottleneck.
AI Engineer · Watch on YouTube

Michael Jenkins
C.T.O. · Threatlocker
First filter
Michael Jenkins says using AI to review AI code can be a good first filter, but he argues it still needs a solid peer review by a developer, whether AI or human, for all code.
Security Weekly - A CRA Resource · Watch on YouTube

Venkat Venkataramani
VP, App Infra · Openai
Agentic code reviews
Venkat Venkataramani says the way code review is done today makes less and less sense, and that agentic code reviews are now emerging to examine code changes through several lenses — making it possible for infrastructure and security engineers to review every change.
The Pragmatic Engineer · The Pragmatic Engineer · Read

Will Bond
Staff Software Engineer · Uber
Automating approvals
Will Bond says AI is moving code review toward a percentage of code landing automatically with automatic approvals, and notes parts of the industry are already moving there.
AI Engineer · Watch on YouTube
Anders Hejlsberg
Technical Fellow · Microsoft
More ergonomic reviewing
Anders Hejlsberg says code review can be made more ergonomic than it is today, with AI potentially helping by explaining what the changes are.
Ryan Peterman · Watch on YouTube

Zach Lloyd
Founder / CEO · Warp
Shifting bottleneck upward
Zach Lloyd says that as agents produce code at volume, the bottleneck shifts to review—currently the biggest one—and he’s tackling it with computer-use verification and better specing so agents check spec adherence.
Dev Interrupted · Dev Interrupted · Read
Jarred Sumner
Creator of Bun · Anthropic
Automated and improved
Jarred Sumner says code review needs to be really good and automated, and he finds Claude's code review really good because it catches bugs that would take him an hour of close reading, though it's expensive.
The Pragmatic Engineer · The Pragmatic Engineer · Read
More Software Engineering questions
View all →- How are natural language interfaces changing software engineering?5 answers
- What practice customizes AI coding agents to your workflow?6 answers
- How do you drive adoption of new tools in engineering?5 answers
- Which software development parts still need human oversight despite AI?5 answers
- What practice best improves team use of large language models?5 answers











