kurtsh✅ Daniel Meppiel's Project Post
https://www.linkedin.com/posts/danielmeppiel_enterpriseai-ai-devops-ugcPost-7338909052267061248-DmG4
✅ Azure Cost Optimization Workflow
https://github.com/danielmeppiel/agentic-hike-planner/blob/main/.github/prompts/az-cost-optimize.prompt.md
#AI #Azure #githubcopilot #CostOptimization
💥 What if AI could shrink your cloud bill by 80% in the time it takes to drink your coffee? | Daniel Meppiel
💥 What if AI could shrink your cloud bill by 80% in the time it takes to drink your coffee? 💥 I recently got it to happen—firsthand. What started as a quick experiment turned into something game-changing. Using VSCode's reusable prompts and the Azure MCP server, GitHub Copilot identified key optimizations for my app's infra in a predictable manner. Then, the Coding Agent implemented them. 📉 The result? An 80% smaller cloud bill. Just like that. In this 2-minute demo (linked below 🎥), I walk through the simple 4-step prompt-driven process I followed: 🔍 Scan & Identify: My structured reusable prompt asks Copilot to search for unused VMs, stale storage accounts, and idle services across my Azure setup. 🧠 Plan Efficiently: The reusable prompt instructs Copilot to generate a clear, prioritized optimization plan—deciding what to delete, resize, or shut down. 🤖 Automate Remediation: With oversight, I let Copilot interface with Azure and GitHub MCP servers to diagnose, dispatch issues and assign Coding Agent to work on them. ✅ Validate Continuously: the reusable prompt includes validation guidelines to ensure reliability. This wasn’t just automation. It is a glimpse of what AI-native development really looks like: engineers becoming system designers, focusing on outcomes, orchestrating agents—not coding line-by-line. Think about it. It shifts the role of the developer entirely. 🔄 Why this matters: - In this new paradigm, reproducible prompts and architectures become the spec, and AI does the heavy lifting. These artifacts are the new building playground. - That means faster prototyping, smarter iteration, and more room for human creativity—all while staying in control. - Of course, with great power comes the need for new guardrails: thresholds for cost, review layers for large changes, and built-in checks for safety. That’s the evolving role of DevOps Engineers in an AI-native Development world. 🌱 So here’s my question to you: How is your team rethinking Software Development in the age of Agentic DevOps? Are you experimenting with Copilot agents, reusable prompts, or intelligent workflows? I’d love to learn from your experiences too. 👇 (---> PS: I dropped my open-source automation workflow in the first comment—feel free to explore it.) (big thanks to the VSCode team Harald Kirschner and Pierce Boggan as well as Chris Harris for the Azure MCP Server 🙌) #EnterpriseAI #AI #DevOps #TechLeadership #GitHubCopilot #VSCode #Azure #CostOptimization #Innovation #AIEngineering #CloudComputing #ReusablePrompts
wiggitywhitney
Claire V.
RedRobot
Matt Williams
Conflux
Matt Black
TSM at Work
InfoQ
Nazeq