Find articles, news, tools and templates by subject or by the work you need to do.
73 results for “Write a runbook” · 25–36
Guide · Incident response ·
A synthetic order-service incident follows a shared handoff through page edits, new findings and shift change, including the review and access work involved.
Read guide: An SRE incident handoff in ChatGPT SpaceExplainer · AI in production ·
Meet Pi, the open-source terminal agent built for people who want to shape their tools. Learn its history, uses, setup, model choices, costs and customization.
Read explainer: Pi.dev guide: the coding agent you can make your ownGuide · AI in production ·
OpenShell can stop an agent after Kubernetes has accepted its scaling request. Recovery then depends on the Deployment state, available replicas and customer-facing result.
Read guide: Recovering an agent task after OpenShell containmentGuide · Observability ·
A durable queue can preserve telemetry through an outage, then take longer to catch up. Arrival rate, export capacity and event age explain what recovery looks like.
Read guide: OpenTelemetry Collector queues and the wait for fresh dataGuide · AI in production ·
An independent checkout request can contradict an agent’s recovery claim. This evaluation separates the agent’s evidence from the grader’s observations and includes a runnable Python example.
Read guide: Testing an incident-response agent against the service it must recoverGuide · AI in production ·
Herdr combines agent status, terminal panes and session recovery. Its server architecture explains what continues after a disconnect and what a restart restores.
Read guide: Herdr brings coding-agent sessions into one terminalGuide · AI in production ·
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.
Read guide: Recovering an interrupted agent skillGuide · Incident response ·
A reference design for duplicate deliveries and partial API success, with durable incident identifiers and summaries drawn from the resulting record.
Read guide: Keeping incident state consistent across PagerDuty, Jira and SlackGuide · AI in production ·
Follow a weight through a training update, save a tiny model, and learn how checkpoints, fine-tuning, LoRA and held-out evaluation fit together.
Read guide: What are model weights, and how does training change them?News · AI in production ·
Separate distributed inference from a contained replication test, then match an edge-fleet containment claim to the evidence that can establish it.
Read news: What Anthropic actually tested in its AI self-replication studyGuide · AI in production ·
Understand the model marketplace and gateway, compare chat and API workflows, and choose a useful route through its models, providers, costs and privacy controls.
Read guide: What is OpenRouter? A practical guide to choosing and using AI modelsExplainer · AI in production ·
Scion reduces repeated repository work for online agents. Its cache hierarchy explains why warm checkout speed and fleet recovery need different tests.
Read explainer: Anthropic Scion puts source control behind a cache hierarchy