GuideAI in production
CodeRabbit: how to use AI code review
Learn what CodeRabbit does, set up AI code review, understand pricing and privacy, and decide when it helps your team or adds more work.
Articles
In-depth explanations, practical guides and independent analysis. Choose a topic and format to find your next read.
Guides show how. Explainers unpack a concept. Commentary makes an argument. Explore Production notes.
GuideAI in production
NVIDIA OpenShell: 6 Critical SRE Checks After Agent Containment
A blocked agent can leave a valid change behind. Reconcile in-flight writes, stale approvals and queued work before resuming production operations.
GuideAI in production
Meta Muse at work: what to delegate, and what to verify
Understand Meta Muse, its approval boundaries and a low-risk workplace trial. Check permissions, uncertain outcomes and data requirements before expanding access.
GuideObservability
OpenTelemetry Collector recovery: check freshness after the queue drains
Size Collector queues, distinguish retries from loss, and rehearse recovery without mistaking delayed telemetry for current service health.
GuideAI in production
Timed-out automation writes: reconcile before retrying
Keep unknown write results visible, preserve operation identity and rehearse a lost response with a local Python fixture.
GuideObservability
Prometheus missing data: test what your error-rate alert cannot see
A zero fallback can hide missing telemetry. Use a small PromQL test matrix to check what your error-rate alert can and cannot establish.
GuidePlatform engineering
Disruption budgets and the capacity left behind
Plan an inference-service node drain with a scoped disruption budget, replacement-capacity checks and a practical maintenance worksheet.
GuideAI in production
Prompt caching: measure the cost of useful work
Build a prompt-caching pilot that counts retries, failed work and unknown charges, with a local calculator and sample ledger.
GuideAI in production
How to evaluate incident-response agents
Build repeatable cases and check recovery independently, with a runnable Python grader.
GuideAI in production
Supervising coding agents with Herdr
Check agent status, terminal persistence, and recovery before adopting Herdr.
GuideIncident response
What did the postmortem fix prove?
Separate a completed task from evidence that the underlying risk was reduced.
GuideIncident response
Use the 5 Whys without forcing an incident into one cause
Follow evidence through technical failure and incident response, then test whether the proposed correction changes the mechanism.