GuideAI 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.
Articles
Guides, news and explanations about AI and reliable systems.
GuideAI 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.
GuideObservability
Shadow-testing an AI log classifier before migration
Run a candidate log classifier beside the current route, preserve complete outcomes, and promote only the slices whose mistakes and review cost are understood.
GuideObservability
Measuring streaming LLM latency from first text to completed work
A client-side SSE probe separates first answer text from normal completion. Fixed arrivals and outcome counts show whether a serving change delivers more useful answers.
GuideObservability
Tracing an AI request through Cloudflare and its origin
Follow a slow AI request from Cloudflare to an instrumented origin, configure sampling, and verify that the trace preserves the evidence needed to investigate.
GuideObservability
Measuring a latency SLO with Prometheus histograms
Build a latency SLI from Prometheus histogram buckets, include failed requests, and compare classic and native queries with a worked search-service example.
GuideObservability
OpenTelemetry tail sampling through a checkout failure
Tail sampling selects recorded traces by error, latency and other evidence. A checkout timeout shows how routing, waiting time and memory affect the trace a responder can retrieve.
GuideObservability
OpenTelemetry Collector queues and the wait for fresh data
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.
GuideObservability
Why a Prometheus error-rate query can return no data
Zero errors, no traffic and absent series produce different PromQL results. Synthetic tests show how ratios, fallback zeros and absence checks behave for a checkout service.
ExplainerObservability
Connect the signals with OpenTelemetry
Use instrumentation and context propagation to connect the evidence in an investigation.
CommentaryObservability
What AIOps alert correlation can hide
Grouping can shorten the incident queue while hiding a second failure. Following a replay past the first mitigation reveals whether that failure stays visible.
GuideObservability
Grafana dashboards for incident response
Regional failures can disappear in fleet averages. Grafana queries, population labels and linked traces help responders find the affected requests.