nitya/ASSERT
Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), and inspect local-first artifacts.
PhD & Polymath · Engineer · Researcher · Educator · Illustrator · Community Builder · Distributed & Ubiquitous Computing · Mobile & Web · Cloud & AI · MSFT
Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), and inspect local-first artifacts.
OpenShell is the safe, private runtime for autonomous AI agents.
Model Mondays is a weekly livestreamed series on Microsoft Reactor that helps you make informed model choice decisions with timely updates and model deep-dives. Watch live for the content. Join Discord for the discussions.
In this workshop learn how to use the Microsoft Foundry Observability platform capabilities with GitHub Copilot coding agent support, to observe and optimize a hosted agents solution for a Travel Concierge scenario.
Automated quality, cost, and latency evaluation of Microsoft Foundry Model Router against any baseline model — bring your own prompts, get a full report in one command.
Track the latest model releases on Microsoft Foundry — with a changelog of announcements plus runnable capsules (README + notebook) per release, organized by publisher.
Model Mondays: data-first, agent-first knowledge base + Astro site for the weekly Model Mondays series
Materials for running the Model Mastery Worshop series (2026). These offer hands-on experience with partner models in Microsoft Foundry. Register for in-venue events or try the self-guided session with your own subscription.
Movie DB App built with Astro
Step-by-step workshop for the "Simplifying Data Analysis" talk
This open-source curriculum is designed to teach the concepts and fundamentals of the Model Context Protocol (MCP), with practical examples in .NET, Java, TypeScript, JavaScript and Python.
Explore https://playwright.dev/ the End-To-End Testing platform for modern web apps from Microsoft
Recipes for AI alchemists forging with Microsoft Foundry
Nitya Narasimhan's Website
Repo for fine tuning examples and sample datasets
Playful one-shot static apps built with GitHub Copilot
Deploy Anthropic Claude on Microsoft Foundry with `azd up` (Bicep or Terraform) and call it with the official Claude SDKs over Entra ID.
Workshop : Observe, optimize and protect your hosted agents in Microsoft Foundry
Ready-to-use structured and progressively complex agent demos with demo scripts and How-it works.
Learn to build trustworthy AI with systematic evaluations in Azure AI Foundry. The session covers quality, safety, agent and custom evaluators
Samples on AI toolkit usage
The official Windows Driver Kit documentation sources
Microsoft Build 2026 · Build smarter AI systems in Microsoft Foundry as models and costs evolve · Learn to hill climb across quality, cost and latency with a model playbook
Resources for modern agent observability — cross-framework tracing, evals, always-on signals connecting agent behavior to business outcomes, cost, and ROI. From Microsoft Build 2026.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Portable guardrail orchestration and enforcement for AI agents