Microsoft Community Insights Podcast

Hosted by Nicholas Chang

TechnologyInterviews guests

Website RSS feed

Episodes

Latest episode

May 2026

Language

EN-GB

About the show

Welcome to the Microsoft Community Insights Podcast, where we explore the world of Microsoft Technologies. Interview experts in the field to share insights, stories, and experiences in the cloud. if you would like to watch the video version you can watch it on YouTube below https://youtube.com/playlist?list=PLHohm6w4Gzi6KH8FqhIaUN-dbqAPT2wCX&si=BFaJa4LuAsPa2bfH Hope you enjoy it

Listen to episodes

54 recent

May 23, 2026Episode 5410 min

Episode 54 - Securing Fabric SQL Analytic Endpoint with John Miner

If you are letting people query Microsoft Fabric with T-SQL, you are already making a security decision, whether you meant to or not. We sit down with data platform MVP John Minor to unpack what it really takes to secure the Fabric SQL analytic endpoint, from the basic shape of the Fabric ecosystem to the small settings that can derail a rollout.We start with the fundamentals: which Fabric objects actually expose a SQL analytic endpoint (lakehouse, warehouse, mirrored database, SQL database), what “read-only endpoint” means in practice, and why the SQL database has both OLTP and OLAP representations. John explains the purpose of the SQL analytic endpoint, what you can build with T-SQL (views, functions, object-level controls), and why case sensitivity is a gotcha worth fixing before you deploy anything widely. We also cover connectivity, including the TDS protocol and how SSMS fits into real-world management and testing.Text Us About the Show

May 3, 2026Episode 5322 min

Episode 53 GitHub Copilot for Azure with Muhammad Samiullah

Deployment is where motivation goes to die: the app works locally, the deadline is close, and suddenly you’re buried in portals, docs, and mysterious errors. We sit down with Microsoft MVP Mohammed Sami to talk about a more practical approach: using GitHub Copilot in VS Code to keep your focus, ask better questions, and move from “it runs on my machine” to “it’s live” with less stress.Text Us About the Show

April 25, 2026Episode 5222 min

Episode 52 — GraphRAG in Action using Microsoft Agent Framework with Christian Glessner

You will learn how small knowledge graph, implement a GraphRAG workflow, and connect it to an AI agent powered by the Microsoft Agent Framework and Microsoft Foundry. You will learn how the agent traverses a graph database, interprets relationships, and answers queries over connected data.https://www.linkedin.com/in/christian-glessner/https://ilovemesh.comText Us About the Show

March 15, 2026Episode 5129 min

Episode 51: Empowering Women in Tech with Samantha St-Louis

Tech does not just need more women, it needs more women who feel free to show up as themselves. We sit down with Samantha St Louis, VP of AI App Innovation and a Microsoft MVP, to talk about what it really looks like to build an AI career, lead AI strategy, and navigate a male-dominated industry without shrinking your personality to fit the room.Her career journey is the proof point. She starts as an nurse then moves into early health tech, builds her own company, and later levels up through Microsoft Learn and certifications like Power Platform Fundamentals before going deeper into AI engineering and AI architecture. Along the way, she shares candid stories about bias, the quiet gatekeeping that keeps people out, and why soft skills are a real competitive advantage in modern tech.Text Us About the Show

February 15, 2026Episode 5025 min

Episode 50 - Adopting AI Product Development with Kate Catlin

Choosing the right AI model shouldn’t feel like roulette. We sit down with Kate Catlin, the product manager from GitHub. Kate shares how model strengths and explains how auto mode aims to pick the right model for the job so developers can focus on outcomes.We dig into practical tactics that cut through hype: start with a golden dataset, run evaluations early, and keep refining with real user prompts once your AI is live. If you’re overwhelmed by weekly model releases, you’re not alone—Kate outlines how to compare new options with scoring and selective manual review. She also tackles the enterprise challenge: slow model approvals that leave teams on outdated systems. With a disciplined eval pipeline, organisations can safely adopt newer, faster, and often cheaper variants that deliver better results.Text Us About the Show

January 31, 2026Episode 4923 min

Episode 49 - Dataverse MCP with Copilot Studio with Nathan Rose

Build an agent that understands intent, finds the right data, and takes action across your CRM—without wiring a maze of connectors. We sit down with Microsoft MVP and functional architect Nathan Rose to explore how Dataverse and Model Context Protocol in Copilot Studio turn instructions into outcomes, shrinking complexity and unlocking reliable, low‑code automation.Text Us About the Show

January 16, 2026Episode 4815 min

Episode 48 - GitHub Copilot Agent with Johan Smarius

We walk through a plan-first workflow that asks Copilot to survey the codebase, propose a step-by-step solution, and only then switch to agent mode to implement. That simple change lifts code quality, reduces rework, and keeps diffs aligned with architecture. We also dig into custom agents with scoped permissions and roles: a testing agent for unit coverage, a docs agent for READMEs, a refactor agent limited to certain directories. Prompt craft matters, but stable configuration, coding standards, and CI guardrails matter more. Think of it as turning best practices into reusable instructions that AI can follow every time.Johan shares field notes from consulting and charity projects: where AI saves hours, where it still stumbles, and how code generation quality has improved over the past year. We explore SpecKit’s promise for scaffolding and simpler apps, acknowledge its preview status and quota costs, and outline how to adopt incrementally in legacy systems. Along the way, we cover open source tracking via changelogs and issues, integrating agents into CI/CD, and designing a workflow that is auditable, secure, and team-friendly.Text Us About the Show

December 27, 2025Episode 4730 min

Episode 47 - Inside the Co‑op Translator Journey with Minseok Song

What if your documentation never drifted out of sync across 54 languages? We sit down with MinSock, Microsoft AI MVP and open-source maintainer, to unpack how a hackathon prototype grew into a robust translation automation pipeline now living under the Microsoft Azure GitHub organisation. The story starts with a simple pain: reading English technical docs as a non-native speaker. It evolves into a system that watches your repo, translates Markdown, images and Jupyter notebooks, and keeps everything aligned as source files change.Enjoy the episode, and if it sparks ideas, share it with your team, subscribe for more community-driven engineering stories, and leave a review with the one translation challenge you want solved next.Text Us About the Show

December 20, 2025Episode 4622 min

Episode 46 - Building Trustworthy AI with Liji Thomas

We dig into how to make that magic reliable, sharing a practical blueprint for building trustworthy AI on Microsoft Foundry with guest Microsoft AI MVP, Liji Thomas.From there, we tour Microsoft Foundry’s control plane and show how to configure guardrails at model and agent levels to block PII, reduce jailbreaks, and filter harmful or protected content. We explore observability and evaluations for groundedness, coherence, and relevance, plus why an evaluation-driven approach matters most after deployment. Text Us About the Show

December 12, 2025Episode 4543 min

Episode 45 - LLM on K8s with Seif Bassem

We start by weighing the trade-offs: managed AI gives you speed, safety, and a deep model catalog, but steady high-volume workloads, strict compliance, or edge latency often tilt the equation. That’s where AKS shines. With managed GPU node pools, NVIDIA drivers and operators handled for you, and Multi-Instance GPU to prevent noisy neighbours, you get reliable performance and better utilisation. Auto-provisioning brings GPU capacity online when traffic surges, and smart scheduling keeps pods where they need to be.The breakthrough is Kaito, the Kubernetes AI Toolchain Operator that treats models as first-class cloud native apps. Using concise YAML, we containerise models, select presets that optimise vLLM, and expose an OpenAI-compatible endpoint so existing clients work by changing only the URL. We walk through a demo that labels GPU nodes, deploys a model, serves it via vLLM, and validates responses from a simple chat UI and a Python client. Tool calling and MCP fit neatly into this setup, allowing private integrations with internal APIs while keeping data in your environment.Text Us About the Show