CodeRabbit author
Hendrik Krack
11 articles · writing here since June 2026
Latest article
Which software engineering skills matter in the age of AI?
As AI takes on more implementation, what should engineers learn next? WeMakeDevs founder Kunal Kushwaha weighs in on the fundamentals, automated code review, and running LLMs locally.
More articles by Hendrik Krack
The feature works. But does it belong?
TRM Labs’ Rahul Raina and CodeRabbit’s Harjot Gill on choosing, validating, and shipping work as agents take on more development.
10.08.26
The Merge: What if your ‘if-statements’ could think?
TypeSafe's Allie Laabs explains how to find Jev-shaped problems in your code, why you should ask every question up front, and why coding agents still need help getting it right.
10.01.26
Claude Sonnet 5.5 for code review: More catches than Sonnet 5, in half the time
We benchmarked Claude Sonnet 5.5 for AI code review against Sonnet 5 and Opus 5.5: which bugs it catches, how fast it reviews, and what a review costs.
09.28.26
The Merge: Your tests pass. Can your agent finish the job?
Cua AI co-founder Francesco Bonacci explains why developers need to check whether AI agents finish the job, even when the tools they use work correctly.
09.25.26
Claude Opus 5.5 for code review: More catches, different misses
We tested Opus 5.5 against our production reviewer to see which bugs it catches, which it misses, and whether higher reasoning effort actually improves the results.
09.22.26
A software factory needs a review gate it can trust
Agents can write, test, and revise code across much of the delivery process. But teams still need a reliable way to decide which changes can move automatically and which require accountable human review.
09.10.26
What would the last software engineer still need to do?
Kent C. Dodds explains why product judgment, system understanding, and ownership become more valuable as AI agents take on more implementation work.
09.03.26
The Merge: Why Building AI Chat Is Harder Than It Looks
A conversation with Assistant UI founder Simon Farshid about the hidden work behind AI chat interfaces, product judgment, and his coding-agent loop with CodeRabbit.
08.27.26
Claude Opus 5 review: Coverage, comment quality, and cost
Explore CodeRabbit’s Claude Opus 5 benchmarks for code review: actionable comments, coverage, nitpicks, token use, and where the model fits.
07.24.26
Loop engineering: designing loops you can actually walk away from
Loop engineering allows you to step away completely by designing a system that operates autonomously, removing the human from the loop entirely.
06.25.26