Engineering notes · Hendrik Krack

writing about tools people trust

Field notes on AI code review, agent harnesses, product engineering, developer workflow, and climate-aware engineering—grounded in the practical details that make tools useful.

13 published posts · RSS available

These are the ideas I keep returning to in talks, workshops, and demos: how AI tools earn trust, what a useful harness actually does, and how teams can ship with more care and less ceremony.

The Merge

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.

Sep 25, 2026 · 4 min
AI evaluation

Claude Opus 5.5 for code review: More catches, different misses

We tested Claude Opus 5.5 against CodeRabbit's production reviewer to see which bugs it catches, which it misses, and what higher reasoning effort changes.

Sep 21, 2026 · 12 min
AI code review

A software factory needs a review gate it can trust

Why agent-driven delivery still needs a visible, risk-based gate before code ships.

Sep 10, 2026 · 7 min
Product engineering

What would the last software engineer still need to do?

Why product judgment, system understanding, and ownership matter when agents write the code.

Sep 3, 2026 · 7 min
The Merge

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.

Aug 25, 2026 · 4 min
Developer workflow

CodeRabbit CLI 0.7.1: improved performance and reliability

CodeRabbit CLI 0.7.1 brings faster local reviews, configuration validation, safer agent authentication, and CodeRabbit Skills for coding-agent workflows.

Aug 19, 2026 · 5 min
AI evaluation

Opus 5 for code review: Cleaner actionable comments, noisier overall

Opus 5 produced CodeRabbit's cleanest actionable-comment stream, but caught fewer known issues and generated roughly four times the baseline's nitpicks.

Aug 6, 2026 · 9 min
AI code review

Building an effective code-review harness

The twelve primitives around the model, explained through a code-review agent.

Jul 8, 2026 · 11 min
Agent systems

Loop Engineering: When is it worth the hassle?

What loops are, the primitives they need, and where they are worth the complexity.

Jun 24, 2026 · 7 min
AI code review

What AI code reviewers catch — and what they still miss

A frank account of where automated review earns its keep and where human judgment still matters.

Jun 1, 2026 · 8 min
AI evaluation

Why building your own benchmark will get you ahead

A practical three-stage guide to evaluating whether an AI feature is ready to ship.

Apr 23, 2026 · 18 min
Developer workflow

A field guide to pre-merge checks

How to build a check stack that protects quality without slowing the team down.

Feb 1, 2026 · 5 min
Climate-aware engineering

Carbon-aware CI: greener pipelines, same merge speed

Shift pipelines toward lower-carbon windows without making developers wait longer.

Dec 15, 2025 · 7 min