GuideAI in production
Supervising coding agents with Herdr
How Herdr keeps coding sessions available while you detach, and what changes when its server restarts.
Articles
Guides, news and explanations about AI and reliable systems.
CommentaryIncident response
What MTTD misses
Separate detection from response and find delays that an improving average can conceal.
CommentaryAI in production
When agents can change production
The permissions, state and recovery paths an agent needs when its tool calls can change a running service.
ExplainerObservability
Connect the signals with OpenTelemetry
Use instrumentation and context propagation to connect the evidence in an investigation.
ExplainerPlatform engineering
The SRE and platform handoff
Clarify ownership across shared platforms, service reliability, and incident response.
GuideIncident response
What did the postmortem fix prove?
Separate a completed task from evidence that the underlying risk was reduced.
ExplainerAI in production
The operational cost of AI tokens
Account for context limits, retries, latency, and the work behind a useful result.
GuideIncident response
Why a 5 Whys investigation can branch
Evidence can split a 5 Whys investigation into several contributing causes. A concurrency example shows how to turn those explanations into useful tests.
GuideAI in production
Comparing incident sources with NotebookLM
Conflicting restart instructions show where a source-backed notebook helps: finding the relevant passages, dates and exceptions for the runbook owner.
ExplainerPlatform engineering
GPU capacity depends on power and cooling
Power and cooling affect the work a GPU pool can sustain. Device signals, request completions and queue growth help distinguish a physical limit from a workload change.
GuideAI in production
Evaluating Claude Opus 4.6 for incident work
A rollback exception tests whether Opus 4.6 preserves decisive evidence across a long session, and whether the resulting answer arrives in time to help.
GuideAI in production
Recovering an interrupted agent skill
A timed-out scaling request needs a durable record and destination-state checks. Reusable operational skills need to recover unfinished work as well as start it.