Operations | Monitoring | ITSM | DevOps | Cloud

Lightrun's Gidi Freud demonstrates Ask Prod, the latest Lightrun AI Skill that teaches AI coding agents how to use Lightrun to answer production questions with live runtime evidence. Watch Codex use the skill to discover runtime sources, collect focused runtime data, adapt its investigation, and return an evidence-backed answer. Compatible with Claude Code, Cursor, GitHub Copilot, and other AI coding agents through the Lightrun MCP.

AI looks great in a demo. The real test is production. In this week's Zero Ticket Minute, Ian explains why success isn't about what AI can do. It's about what it can reliably resolve.

Learn more: speedscale.com.

Meet your digital teammate. Persona-based AI agent designed for critical ITSM workflows. Transform IT operations with AI agents that plan, coordinate, and execute autonomously, delivering measurable business impact through intelligent automation. Your conversational front door to IT that replaces forms with natural language, cutting ticket load and improving data quality through guided capture.

Every team is doing something with AI right now. What that something is, is an entirely different question. And whether that something is successful? Most teams are still figuring it out as they go.

AI coding tools are accelerating development velocity, creating a release challenge most teams aren’t equipped for. Without controlled rollout, higher change velocity makes it harder to know which specific release drove the results you’re seeing in production. And when teams use AI, to build AI – LLM apps and AI agents– complexity multiplies. Traditional observability can’t ensure AI agent quality, performance, and cost-efficiency at production scale.

#aicoding #softwareengineering #claudecode

What is physical AI? Physical AI embeds machine learning directly into hardware, enabling algorithms to interact, move, and perform autonomous tasks in the physical world. Traditionally, robots relied on precise, hardcoded coordinates; if an object shifted by a single millimeter, the entire system failed. Today, robotics is moving past rigid automation toward truly adaptive architecture. Neural networks help machines process raw sensor data in real time. Consequently, machines can dynamically reason through the unpredictable physical world.