Toolkit · SLOs & reliability
Review a reliability budget
Calculate the allowance, inspect burn rate and connect the result to your release policy.
Open toolkit: Review a reliability budgetSearch AIOpsSRE
Find articles, news, tools and templates by subject or by the work you need to do.
83 results for “Improve a postmortem” · 13–24
Guide · AI in production ·
Testing an incident-response agent against the service it must recover
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 ·
Comparing AIOps tools on responder work
Detection, correlation and remediation need different trials. The comparison includes specialist escalations, correction effort and the integrations left to maintain.
Read guide: Comparing AIOps tools on responder workGuide · Incident response ·
Finding the response delay AIOps can reduce
Evidence gathering, authorization and restoration can each hold up an incident. The timeline shows which kind of assistance could shorten the wait.
Read guide: Finding the response delay AIOps can reduceCommentary · Engineering leadership ·
SRE accountability needs authority, capacity, and a clear owner
A service owner may depend on another team’s access, risk decision or engineering time. Following a shared-database change reveals where that arrangement needs help.
Read commentary: SRE accountability needs authority, capacity, and a clear ownerExplainer · SLOs & reliability ·
How SRE feedback loops reveal work that moved out of view
Alert cleanup can reduce interruption or conceal a recurring failure. Customer reports and correction effort help distinguish the two results.
Read explainer: How SRE feedback loops reveal work that moved out of viewGuide · AI in production ·
What are model weights, and how does training change them?
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?Guide · AI in production ·
Hermes Agent guide: what it is, when to use it, and how to get started
Understand Hermes Agent, its origins, models, memory and skills. Choose a setup, try two checkable examples, and learn where its limits matter.
Read guide: Hermes Agent guide: what it is, when to use it, and how to get startedGuide · AI in production ·
What is OpenRouter? A practical guide to choosing and using AI models
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 modelsGuide · AI in production ·
Model inference: what happens when you ask AI a question?
What a model does when you ask a question, how we got here, and how to choose between local and hosted inference without confusing fast text with useful work.
Read guide: Model inference: what happens when you ask AI a question?News · AI in production ·
What LFM2.5's 2.45B active parameters mean for local agents
Sparse routing reduces per-token compute, but the full 24B checkpoint, agent harness, license and representative workload still decide deployment fit.
Read news: What LFM2.5's 2.45B active parameters mean for local agentsGuide · AI in production ·
Measuring retry amplification in AI agent workflows
Connect logical tasks to every model and tool attempt, then measure cost and latency per accepted outcome without hiding failed or unknown work.
Read guide: Measuring retry amplification in AI agent workflows