Now that everything is agentic, what should I be learning?
Summary
Filisha Shah advises learning observability, evaluations, and evaluators as traditional app logic shifts to agents. Microsoft Copilot's AI Foundry platform integrates datasets, evaluations, and observability to manage these non-deterministic agents. This approach addresses the new scientific challenges of maintaining healthy AI agent systems.
Why it matters
As AI agents become central to application logic, the focus shifts from deterministic code to managing non-deterministic behavior. This impacts developers and organizations building with AI. Microsoft's AI Foundry aims to provide a unified platform for this, a space where competitors like Google Gemini and Anthropic are also developing tools for agent management and evaluation. Future developments will likely center on refining these observability and evaluation tools to ensure agent reliability and performance.
Related: OpenAI: First impressions of GPT-6 Astra from developers · Google: Graph Engineering 101 · Anthropic: Anthropic Cookbook: feat(claude_agent_sdk): add scheduled repository reviewer recipe (#860) · Meta: Nvidia launches free tool that links idle computers into a personal AI data center · xAI: Ajeya Cotra – "This might be the clearest warning shot we ever get"
Rated low: routine. Worth knowing, not worth rearranging your day for.
- Now that everything is agentic, what should I be learning?Microsoft Developer on YouTube
- Inside Microsoft's marketing team: scaling expertise with AIMicrosoft Azure on YouTube
- What does it really take to ship an AI agent?Microsoft Developer on YouTube
From Code to Agents: Build Production MCP Servers on Azure Functions
Questions people ask
- What skills are important as app logic moves into agents?
- Filisha Shah recommends learning observability, evaluations, and evaluators to manage the non-deterministic nature of AI agents.
- What is Microsoft AI Foundry?
- AI Foundry is a Microsoft platform that brings datasets, evaluations, and observability together to help manage AI agents.
More from Microsoft Developer on YouTube 14 more
5 things you didn't know about Azure SQL Database Hyperscale | Data Exposed
Build Your Personal Brand with GitHub Copilot — Full Course for Students
From Code to Agents: Build Production MCP Servers on Azure Functions
Shield sensitive fields with Dynamic Data Masking for Microsoft SQL | Data Exposed MVP Edition
Bring Your Own Model in VS, Foundry Models, .NET Conf Sets Date | The Upload Ep 4
Page generated Sep 3, 2026. Summaries are Subvolts' own; the story belongs to Microsoft Developer on YouTube.