<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>On-Call on LLM API Reliability Notes</title><link>https://llmapireliability.com/tags/on-call/</link><description>Practical guides for LLM API reliability and fallback engineering.</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://llmapireliability.com/tags/on-call/index.xml" rel="self" type="application/rss+xml"/><item><title>CometAPI Timeout Evidence Pack for On-call Reviews</title><link>https://llmapireliability.com/posts/cometapi-timeout-evidence-pack-for-on-call-reviews/</link><pubDate>Wed, 17 Jun 2026 08:43:24 +0000</pubDate><guid>https://llmapireliability.com/posts/cometapi-timeout-evidence-pack-for-on-call-reviews/</guid><description>A structured guide to assembling and using timeout evidence when reviewing CometAPI incidents on call — covering which HTTP telemetry fields to capture, how to apply retry-with-backoff safely, and what to hand off to support.</description></item><item><title>Overload Signal Triage for LLM API On-Call Engineers</title><link>https://llmapireliability.com/posts/overload-signal-triage-for-llm-api-on-call/</link><pubDate>Wed, 17 Jun 2026 08:38:47 +0000</pubDate><guid>https://llmapireliability.com/posts/overload-signal-triage-for-llm-api-on-call/</guid><description>A practical guide for on-call engineers who need to distinguish real LLM API overload from transient noise, decide when to retry, and know when to escalate or shed load.</description></item></channel></rss>