- LLM API calls hang for minutes: client timeouts, retries and connection limits in the OpenAI SDK and boto3AI & GenAI · 8 Nov 2026
- AI agent tool calls executed twice: retries, timeouts and re-planning that send duplicate emails, tickets and paymentsAI & GenAI · 28 Oct 2026
- Same prompt, different answer at temperature 0: where LLM non-determinism comes from and how to live with itAI & GenAI · 28 Oct 2026
- Advisory: designing for Availability Zone failure on AWS - static stability and zonal shiftAWS · 25 Oct 2026
- Advisory: reviewing a live OCI workload against the Well-Architected FrameworkOCI · 25 Oct 2026
- Advisory: running a Well-Architected review on a live AWS workload with the WA ToolAWS · 25 Oct 2026
- Advisory: running a Well-Architected review on an existing Azure workloadAzure · 25 Oct 2026
- Optimization: Azure spot VMs for Databricks workers - which jobs, fallback settings and eviction handlingDatabricks on Azure · 25 Oct 2026
- Sev1: the LLM step in a production workflow starts returning invalid JSONAI & GenAI · 25 Oct 2026
- Reliable Databricks pipelines: retries, zones, instance pools and Delta Live Tables recoveryData Platform · 22 Oct 2026
- Handling 429s and latency spikes from LLM APIsAI & GenAI · 19 Oct 2026