# Build apps & agents that scale with VS Code, GitHub Copilot, and Agent Framework Source: https://www.youtube.com/watch?v=ob-TOPfQmbk Recap page: https://rapidrecap.app/video/ob-TOPfQmbk Generated: 2025-11-11T01:38:52.539+00:00 --- ## Quick Overview The presentation highlights the evolution of agentic workflows, exemplified by building and deploying a multi-agent system for pet-sitter recommendations using GitHub Copilot and Azure AI services, culminating in the announcement of the Azure SRE Agent for continuous production improvement. **Key Points:** - GitHub Copilot was used to build a pet-sitter recommendation application from scratch, demonstrating agentic workflows from specification to deployment. - The presentation introduced the concept of evolving developers into AI orchestrators who manage teams of specialized AI agents. - GitHub Spec Kit was shown as a tool to create unambiguous, specification-driven development, contrasting with traditional, manually updated, infrastructure-heavy code. - The Azure AI Agent Evaluation tool was demonstrated to provide offline evaluation of AI models and agents within CI/CD pipelines, showing metrics like Tool Call Accuracy, Response Relevance, and Response Coherence. - The final stage involved deploying a custom Azure SRE Agent, which automates incident management and resource optimization based on predefined execution plans and tools. - A key metric shown was the 80.0% Tool Call Accuracy for the Sitter Agent evaluation run. ![Screenshot at 03:04: Amanda Silver introduces the 'Evolution of agentic workflows' slide, contrasting traditional agent logic \(rule-based, manual\) with agentic logic \(autonomous, adaptive reasoning, specification-driven\).](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-03-04.png) **Context:** This presentation segment, delivered during GitHub Universe '25, focuses on the maturation of AI-assisted development, specifically showcasing how GitHub Copilot and the Microsoft Agent Framework facilitate the creation, evaluation, and deployment of complex, multi-agent systems. The core theme is the shift from developers writing infrastructure-heavy code to developers specifying behavior and orchestrating AI agents to execute tasks, exemplified by building a functional pet-sitter recommendation app. ## Detailed Analysis The presentation details the progression toward AI-driven development, moving from agents that rely on fixed, manually updated logic to autonomous, specification-driven systems where developers act as orchestrators collaborating with AI agents. GitHub Spec Kit is presented as the tool enabling this shift by allowing developers to define clear, testable specifications that guide agent behavior, rather than writing verbose, platform-specific code. The process demonstrated involved using Copilot to build the 'Octopets' application, which finds pet-friendly venues. This development workflow included utilizing Azure AI tools, specifically the Azure AI Agent Evaluation framework, to run offline testing via CI/CD pipelines. The evaluation results showed metrics like 80.0% Tool Call Accuracy and 100% Response Relevance/Coherence, confirming the agent's capability. Finally, the Azure SRE Agent was introduced as a tool to automate incident management and resource scaling based on these evaluations and predefined response plans, significantly reducing manual toil and improving system reliability. The presenter concluded by showing the successful deployment and evaluation of the SRE Agent itself. ### Agent Workflow Evolution - Shift to autonomous systems - Specification-driven development - Evolving developer role (from coder to orchestrator collaborating with agents) ### GitHub Spec Kit Benefits - Enables spec-driven development, resulting in clear, testable specifications for agent behavior. ### Agent Development Tools - Use of GitHub Copilot for building agents and Azure AI Toolkit for local development/testing. ### Agent Evaluation - Azure AI Agent Evaluation provides offline testing within CI/CD, measuring Tool Call Accuracy (80.0% achieved), Response Relevance (100% pass rate), and Response Coherence (100% pass rate). ### Azure SRE Agent - Extends AI to continuously improve apps in production, automating incident management, resource optimization (scaling CPU/memory), and rollback procedures based on evaluation outcomes. ![Screenshot at 00:02: Announcement poster for 'UNIVERSE 25' happening OCT 28-29, 2025, in San Francisco & Virtual.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-00-02.png) ![Screenshot at 00:07: Amanda Silver introduced on stage at GitHub Universe, with dual screens showing her photo and title.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-00-07.png) ![Screenshot at 00:34: Slide titled 'Evolution of agentic workflows' showing Gen 1 \(Human-centric, Suggests\) evolving to Gen 3 \(Humans and agents collaborate\).](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-00-34.png) ![Screenshot at 01:12: Slide showing the combination of Visual Studio Code \(VS Code\) and the GitHub Copilot logo, emphasizing integration.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-01-12.png) ![Screenshot at 02:30: Shayne Boyer joins Amanda Silver on stage to present a demo on scaffolding and deploying with Spec Kit and MCP.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-02-30.png) ![Screenshot at 03:30: Demonstration of the 'Octopets Constitution' file in VS Code, detailing core principles for Azure-related development using AI Toolkit MCP tools.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-03-30.png) ![Screenshot at 04:14: The presenter navigates to the 'research.md' file showing the decision to use 'gpt-4-mini' for the Sitter Matching Agent.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-04-14.png) ![Screenshot at 05:04: The presenter shows the 'tasks.md' file generated by Copilot, detailing 146 tasks across 9 phases for the Octopets application.](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-05-04.png) ![Screenshot at 06:41: The presenter previews the 'research.md' file content, which outlines model selection rationale \(e.g., gpt-4-mini offers excellent balance of cost/quality\).](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-06-41.png) ![Screenshot at 07:12: The presenter demonstrates the execution of the plan, showing agents starting up in the terminal and the infrastructure changes applied in the Bicep file for resource scaling \(minReplicas: 3, maxReplicas: 15\).](https://ss.rapidrecap.app/screens/ob-TOPfQmbk/00-07-12.png)