How to collect telemetry from Claude Code and Codex
#aicoding #softwareengineering #claudecode
Operations | Monitoring | ITSM | DevOps | Cloud
The Place Where Modern Operations & Technology Come Together
Claude Routines Need a Governed Home: Centralizing What Your AI Agents Can Reach
Claude Routines are a great automation primitive. But the network rules that decide what an agent can reach are set per engineer - and that's the real enterprise risk. Here's why Routines need a centrally governed home. Romaric founded Qovery to make Kubernetes accessible to every engineering team. He writes about platform strategy, developer experience, and the future of cloud infrastructure.
Language AI to physical AI explained
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.
Ship Reliable AI Faster: How to Operate AI Agents with Control and Confidence
Replace "AI shipped on hope" with an operating model that holds up once real users depend on it. AI quality is multi-dimensional, covering accuracy, tone, safety, and faithfulness to user data, and can't be debugged from outputs alone. Without visibility into what their AI actually did in production, teams miss regressions, reverse-engineer chains by hand, and watch a single bad answer erode trust built over hundreds of right ones.
The AI vendors just started watching the meter. CFOs need to watch the return.
On June 18, OpenAI gave ChatGPT Enterprise admins new credit usage analytics and spend controls. It’s a single view of credit consumption broken down by user, product, and model, default workspace budgets, per-group limits, and a Cost API for pulling the data into their own systems. Two days earlier, Microsoft shipped Copilot Cowork with spending limits, budget allocation, usage alerts, and user-level caps. This is a step in the right direction.
AI Works in Demos. But Can It Survive Production?
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.
Ivanti Agentic AI for ITSM
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.
Seedance 2.5: Cinematic AI Storytelling
In the rapidly expanding digital economy, the ability to produce high-quality video content at scale has become the primary competitive advantage for e-commerce brands, self-media creators, and digital production studios. As audience attention spans continue to shrink, the necessity for high-fidelity, emotionally resonant, and visually consistent video content has reached an all-time high. This is where Seedance 2.5 enters the picture, representing a significant leap forward in generative AI video technology.
Azure FinOps with AI: What's New in Turbo360 v5.2
Turbo360 v5.2 is the biggest AI update we've shipped. Every module now has AI built in - not just to surface data, but to explain it, guide you through it, and help non-experts take action without needing to call in a specialist. In this video, Mike Stephenson walks through every new feature in v5.2, from AI agents that explain cost drivers and rightsizing recommendations, to a brand new Savings Tracker that gives you a better way to prove FinOps impact to management.