- Running LLM-generated code safely on Kubernetes: gVisor sandboxes, no network, resource limits and hard timeoutsAI & GenAI · 11 Nov 2026
- Text-to-SQL agent returns wrong numbers or runs runaway queries: schema grounding, read-only roles, statement timeouts and AST validationAI & GenAI · 11 Nov 2026
- Checklist: giving an AI agent its own identity - scoped, short-lived credentials and an audit trail for every tool callAI & GenAI · 9 Nov 2026
- Testing AI agents before release: trajectory assertions, recorded tool replays and pass-rate gates in CIAI & GenAI · 9 Nov 2026
- vLLM tool calling not working: fix auto tool choice errors, parsers and tool calls returned as textAI & GenAI · 7 Nov 2026
- MCP basics: what the Model Context Protocol does, and your first read-only server in PythonAI & GenAI · 6 Nov 2026
- Securing MCP servers: authentication, scoped tool permissions, input validation and audit for ops toolingAI & GenAI · 29 Oct 2026
- AI agent tool calls executed twice: retries, timeouts and re-planning that send duplicate emails, tickets and paymentsAI & GenAI · 28 Oct 2026
- MCP server not connecting or tools missing: fixing stdio, Streamable HTTP and auth failuresAI & GenAI · 27 Oct 2026
- Advisory: agents or workflows - when to let the model decide the steps, and how much autonomy to giveAI & GenAI · 25 Oct 2026
- Advisory: designing human-in-the-loop for AI actions - approvals, confidence thresholds and review queuesAI & GenAI · 25 Oct 2026
- AI kill switches explained: the six levels you can switch off and how to design each oneAI & GenAI · 25 Oct 2026
- Optimization: keeping agent costs under control - step limits, trimmed tool outputs and context managementAI & GenAI · 25 Oct 2026
- Sev1: an AI agent is taking harmful actions. The emergency stop runbookAI & GenAI · 25 Oct 2026
- Switching off one agent tool without stopping the agent: tool-level kill switches and MCP serversAI & GenAI · 25 Oct 2026
- Transformation: from a single-prompt workflow to a bounded agent using MCP toolsAI & GenAI · 25 Oct 2026
- Build a read-only MCP server so AI assistants can query your ops tools safelyAI & GenAI · 22 Oct 2026
- Checklist: rolling out an AI incident-triage assistant safelyAI & GenAI · 22 Oct 2026
- LLM tool calling fails: wrong tool, bad arguments or endless loopsAI & GenAI · 22 Oct 2026
- Prompt injection defense checklist for production LLM appsAI & GenAI · 22 Oct 2026