Tired of chatbots that answer Intune incidents with poetry instead of fixes? In this episode, we go hands-on with Azure AI Foundry and Semantic Kernel to build a mini, self-healing, governed multi-agent system for enterprise IT. You’ll learn why single agents stall on real Intune, Entra ID, and Microsoft Graph workflows, and how planner, operator, reviewer, and concierge agents collaborate to deliver faster, safer automation. We break down patterns for tool-driven remediation, identity-scoped actions, content safety, and observability, then apply them to three real-world scenarios: ghost device cleanup in Intune, truly zero-touch onboarding, and automated BitLocker security hardening. Along the way we mix small language models with GPT-4-class reasoning models to cut cost, reduce hallucinations, and keep prompts short while still getting production-grade results. If you’re an Azure, Intune, or security engineer looking to turn AI agents into reliable teammates instead of risky toys, t…

You’re wasting AI on small talk. In this session I show you how to turn chatty models into hardened IT ops agents that actually fix incidents while you sleep. We wire Semantic Kernel, MCP, Microsoft Graph and Azure OpenAI with managed identity so agents can plan, act and auto-verify – without handing root access to a hallucinating chatbot. You’ll see how to slash MTTR, auto-resolve password reset tickets, drain bad builds, and roll back safely using tool schemas as “laws of physics,” not vibes. We’ll build a six-part agent molecule (persona, memory, planner, tools, policy, verifier) and drop it into real incident flows: 5XX spikes, canary failures, onboarding waves and weekend fire drills. If you care about uptime, sleep, and not turning your data center into glass, this is your blueprint: SK orchestrates, MCP connects, Foundry governs, managed identity contains – and your agents prove every action they take.

The night is thick with static inside your tenant, and the questions aren’t small anymore. Copilot can walk the clean, well-lit M365 streets — summarizing inbox noise, tightening your notes, finding what you already have permission to see. Fast, friendly, useful. But tone isn’t truth, and guesses don’t survive compliance. This episode pulls you into the alleys where real knowledge lives: stale PDFs, forgotten SharePoint stacks, file-server ghosts, wikis no one maintained. That’s where Copilot reaches its boundary — and where Retrieval Augmented Generation starts. RAG becomes the librarian with receipts, dragging ground truth from your own systems, forcing citations, refusing to bluff. We map when Copilot is enough, when you must build a pipeline, and why teams explode cost, tickets, and trust by confusing the two. A secret step makes the whole discipline 10× easier — and we go there. If your world runs on proprietary policy, SOPs, baselines, and high-stakes questions where wrong…

AI agents are shipping faster than your change control, and they’re carrying master keys to your data. This talk rips into how LangChain4J and Copilot Studio quietly turn “helpful copilots” into data-leaking, over-permissioned shadow admins with no audit trail. You’ll see exactly how prompt injection, over-scoped connectors, and missing logs create reportable incidents, and how strict schemas, per-agent identities, and real DLP stop the bleeding. The core move most orgs skip: give every agent its own locked-down identity, no shared creds, no tenant-wide scopes, and treat it like a very dumb, very powerful user you have to restrain by design.

In this episode of The M365 Show we investigate a familiar but often misunderstood failure pattern in enterprise AI: GPU costs rise, throughput collapses and latency becomes unpredictable, even though the dashboards look healthy and the models appear to work. Instead of blaming parameters or architectures, we treat the problem as a forensic case and follow the evidence through the entire compute pipeline. We walk through a realistic Stable Diffusion workload under concurrency, with strict P95 latency objectives and GPU hardware that looks perfectly adequate on paper. From there, we trace how silent CPU fallback in ONNX Runtime, subtle version mismatches across CUDA, cuDNN, TensorRT and ONNX Runtime, and container misconfiguration combine into a single pathology that turns an accelerator into an expensive heater. The system continues to return correct outputs, but at 10 to 30 times the expected latency and with a fraction of the intended throughput. Building on that, we construct…

Tired of “smart” AI agents doing dumb, dangerous things in your Microsoft 365 tenant? This episode shows you the one architectural move that turns flaky prompt-powered agents into reliable, auditable systems: a pre-execution contract check that blocks bad behavior before it ever hits your data. We walk through how to separate LLM cognition from real-world operations, why executors and validated workflow graphs beat prompt hacks every time, and how to wire this into Microsoft 365 Graph, Azure OpenAI and Copilot Studio without creating a compliance nightmare. You’ll see how a validator proves three things before any tool call runs: the capability is real, the caller actually has permission right now, and the outcome is feasible and verifiable within strict data boundaries. No “trust the model,” no silent partial failures, no hallucinated tools. Instead, you get schema-checked JSON, idempotent executors, policy-enforced allow lists, human checkpoints as first-class workflow nodes, and…

Why do so many Microsoft 365 Copilot projects fail — even when the prompts look fine? In this episode, we explain why the real issue is not prompt engineering, but context engineering. Most AI failures are not model failures. They are context failures. When Copilot lacks structured, governed, and relevant information, it produces inconsistent, low-quality, or misleading results. Context Engineering goes beyond writing better prompts. It is the systematic design, management, and governance of all information your Copilot has access to — ensuring accurate, stable, and trustworthy outputs. We break down what context engineering really means in Microsoft 365 environments, why it matters for enterprise AI adoption, and how to design Copilot solutions that scale reliably. If you want consistent Copilot results instead of AI randomness, this episode is essential.

Summary: In this episode I explain why “1,400+ connectors” is a vanity metric and compare Power Automate vs Azure Logic Apps for real enterprise integration. We dig into throttling, throughput, vNet and private endpoints, Azure Arc hybrid, AI agents with Azure Functions, and give you a simple decision rule: Power Automate for departmental M365 convenience, Logic Apps for high-volume, governed, hybrid workloads.

n this episode, we put Microsoft 365 Copilot’s Workflows Agent head-to-head with Power Automate and ask the uncomfortable question: are your painstakingly hand-built cloud flows now the slow, expensive option? We break down where conversational, intent-driven automation beats traditional designer-driven flows for everyday work across Outlook, Teams, SharePoint, Planner and Microsoft Graph—and where Power Automate still absolutely owns the room. You’ll see real-world use cases—approvals, data sync, incident triage, CRM updates and IT onboarding—timed and dissected for build time, error surface, governance, and licensing cost. We unpack DLP, environments, auditability, SLAs, and why hybrid patterns (Agent front, Power Automate spine) are where the real ROI hides. By the end, you’ll know what to keep in Power Automate, what to move to Workflows Agent, and what to retire entirely—so you stop hoarding fragile flows and start shipping automations that match how your org actually works.

Worried your SharePoint or Copilot agent is “hallucinating” data leaks? In this episode, we unpack why that’s almost never the model’s fault and almost always your permissions and scope design. You’ll learn how SharePoint and Microsoft 365 agents actually see your data through Microsoft Graph, why overscoped knowledge sources plus permissive inheritance turn into accidental disclosure at machine speed, and why grounding does not equal a security boundary. We break down a practical mental model for agents – user persona plus retrieval filters, gated by permissions, labels, and Purview DLP – and show exactly how an agent can quietly stitch together truths from adjacent libraries you never properly isolated. From there, we go deep into the four control planes that stop bleed without killing usefulness: scoping knowledge sources at the library level with strict metadata and multiple narrow, specialized agents instead of one encyclopedic monster; breaking SharePoint inheritance where it…

This episode rips apart the illusion that “Copilot training” is a workshop, a slide deck, or a single rollout campaign. It starts with a familiar pain: you trained users on Microsoft Copilot, pinned decks, hosted Q&As, ran office hours—and your help desk ticket queue still grew. Users got smarter for 24 hours, then went straight back to asking, “Which Copilot do I use?” and “Is this safe?” The episode argues that the core problem isn’t users, or even Copilot. The problem is that most organizations are trying to manage a fast-moving, AI-driven behavior engine with static training and scattered documentation. Without a governed, tenant-aware learning system, you’re not doing adoption—you’re role-playing a help desk. From there, the conversation reframes Copilot adoption as an information architecture and governance problem, not a training problem. Traditional one-off training creates “shadow training” everywhere: rogue slide decks in Teams, PDFs with filenames like “Ultimate Copilot …

Python is NOT the language of AI inside the Microsoft stack—and in this episode, I show you why that belief is quietly wrecking your Power Platform projects, inflating defects, and burning your budget. If you’re cramming Python into Power Automate, Power BI, Fabric, or custom connectors as “glue code,” this is your wake-up call. We break down why Python is amazing for analytics, ML, and Fabric notebooks—but a terrible choice for everyday orchestration inside Power Automate, Power BI Dataflows Gen2, Dataverse, and Microsoft 365. You’ll learn how Office Scripts (TypeScript-flavoured), Copilot, and agent-style orchestration (like type-agent) can write and run the glue for you, with typed contracts, native connectors, and AI-generated scripts that actually respect your schemas and governance. Instead of debugging brittle Python in Azure Functions at 2:14 a.m., you’ll see how to: Keep Python where it shines: Fabric notebooks, advanced analytics, ML. Use Copilot + Office Scripts to …

Out-of-the-box Microsoft Copilot sounds like a genius—but in real enterprises it’s a dangerously confident intern. In this episode, we expose where default Copilot quietly fails on the questions that actually matter: “Can I share this file?”, “Who’s on-call right now?”, “Is this HIPAA-safe?” You’ll see how generic, Graph-only Copilot ignores your DLP exceptions, regional SOPs, escalation paths, and legal memos—and why that’s how incidents are born. Then we show you the fix: plug your own specialist engine agent straight into Microsoft 365 Copilot Chat with a simple manifest upgrade. You’ll learn the retrieval + actions + guardrails pattern, how to wire Azure AI Search, internal APIs, and tenant controls, and the exact schema 1.22 tweaks (copilotAgents + customEngineAgents) that flip Copilot from smooth-talking generalist to hard-edged policy enforcer. The before vs. after is brutal: vague essays and hallucinated “best practices” turn into crisp, cited decisions, “Page now” butto…

Your Copilot rollout is probably going to flop—and it won’t be the AI’s fault. Most organizations treat Microsoft 365 Copilot like a feature toggle: light up licenses, send a heroic memo, run one training… and three months later MAU is a rounding error. In this episode, we expose the five hidden failure modes that quietly kill Copilot adoption: vague “be more productive” use cases, governance theater that stalls everything, launch-and-ghost comms, license confetti with no telemetry, and users who were never actually taught how to talk to the model. You’ll learn the brutal truth that deployment is not adoption, the week-one leadership decision that predicts your long-term MAU, and why your real product isn’t Copilot—it’s behavior change. We walk through the C4 prompting pattern (Context, Constraint, Critique, Continue), the 10/30/60 “Tuesday task” model that kills blank-page syndrome, how to stop governance panic without freezing the rollout, and a practical 90-day adoption playb…

SharePoint looks confident on the surface, but under the hood it’s drowning in duplicates, forgotten drafts, and every “final final V2” that ever existed. In this episode, we pull back the curtain on why your search results lie, why Copilot sounds smart while guessing, and how a quiet storm of rogue files destroys governance without anyone noticing. It’s not a storage problem, it’s a relevance problem, and the chaos is baked into human behavior—people hoard because delete feels dangerous. SharePoint obeys, versions multiply, and truth dissolves in a fog of near-identical copies that confuse ranking systems and derail compliance. This episode dives into the architecture that fixes the mess without breaking collaboration or scaring users. We redesign the entire content lifecycle using a SharePoint command, an Azure Function, Blob tiers that behave like a warehouse district, and a ledger that remembers everything you move. Search becomes sharper, Copilot stops hallucinating, and your …

Your SharePoint / Microsoft 365 document libraries are quietly killing productivity — and Microsoft already shipped the fix. In this episode, I show you how the NEW Doc Libs UX, Forms, Autofill and Copilot turn your “final_v3_REALLY_final.docx” graveyard into an intelligent workflow that actually guides work instead of hiding it. You’ll see how enhanced breadcrumbs, visible filter pills, board view and saved views slash “where did my file go?!” drama, and how one adoption-killing mistake in your forms is sabotaging everything. Then we flip the front door: idiot-proof intake with Forms, smart metadata from Autofill (reading time, abstracts, categories) and a simple triage routine that keeps your response folders from turning into purgatory. Finally, we weaponize Copilot inside Doc Libs: instant version comparisons, punchy abstracts, audio overviews and grounded Q&A that turns a file pile into decisions on demand. Implement the five switches from this episode and your library stop…

Your M365 AI agent isn’t failing because the model is bad—it’s failing because your plumbing is. This episode exposes why DIY agents that “work in dev” die the second real users and security show up. You’ll hear how app-only auth quietly nukes permission fidelity and audit trails, why stateless bots forget context the moment you add a second node, and how hand-rolled Teams/Slack/Outlook adapters create glitchy, untrustworthy UX that feels cheap and amateur. The host then reveals the real unlock: the Microsoft 365 Agent SDK as the non-optional backbone for identity, state, channels, and governance. You get act-as-user auth, durable conversation state across clusters, real adapters for Teams/web/Slack/Copilot, streaming that just works, and built-in hooks for Purview, DLP, Defender, and eDiscovery—so security says “yes” instead of “absolutely not.” If you’re gluing LangChain, SK, and custom tools together and hoping it passes review, this episode is the wake-up call: stop shipping…

Think spreadsheets are chaos? Cute. In this episode we stress-test Microsoft Fabric against the worst data you own: photorealistic 3D assets and full-fidelity digital twins. We break down why a single “file” is actually a sprawling supply chain of scans, meshes, textures, physics, and licenses — and how one sloppy ZIP export can turn into a global compliance nightmare. You’ll learn how Fabric turns governance from theater into an always-on safety system: Entra ID–backed identity, object-level security, lineage that behaves like a black-box recorder, rights-as-code, and streaming with signed tokens instead of random file copies. We walk through real workflows for artists, simulation engineers, and robotics teams, and show how to version twins so “latest” stops being a ticking time bomb. If you’re still trusting folders, shared drives, and good intentions to protect multi-gigabyte 3D assets, this episode is your wake-up call. Hit play to see why, if your governance can hold a 1:1 …

Your Copilot isn’t smart – it’s a very expensive autocomplete. In this episode, we break down why classic RAG (retrieve-augment-generate) quietly fails the moment your truth lives in more than one system, and how “agentic RAG” on Azure turns Copilot from a context tourist into an actual reasoning engine. You’ll hear how Planner, Retriever, and Verifier agents running on Azure AI Agent Service can roam Microsoft Fabric, SharePoint, and external data, cross-check their own answers, and deliver evidence-linked insights that auditors, CISOs, and data leaders can actually trust. We dig into On-Behalf-Of auth, RLS/CLS, and Purview labels so your AI respects the same permissions as your humans, instead of leaking CFO forecasts to interns. If you’re a CIO, CDO, architect, BI lead, or security/GRC owner who’s tired of hallucinated KPIs and pretty-but-useless dashboards, this is your blueprint. Learn how to cut decision latency from months to minutes, turn SharePoint chaos into a semantic…

Typing to Copilot is the new fax machine—and your thumbs are the bottleneck. In this episode we break down how to give Copilot an actual voice, a memory, and a legal department, so it can keep up with the way you think, not the way you type. You’ll hear how GPT-4o Realtime turns Copilot from a slow, QWERTY-bound chatbot into a true conversational partner that listens while you speak, lets you interrupt mid-answer, and responds in milliseconds. Then we plug that voice into a real brain: Azure AI Search with RAG, so every answer is grounded in your own policies, standards, and FAQs—fully cited, fully governed. We walk through the blueprint step by step: Blob Storage, Azure AI Search, a hardened proxy layer, and secure M365 voice integration in Copilot Studio, Power Apps, and Teams. No biometrics, no cowboy connectors, just Entra ID, Purview, DLP, and logs your CISO can sleep on. If you’re still typing into Copilot, you’re leaving productivity—and compliance-grade insight—on the…

Stop your cloud migration. Seriously. If you’re still bragging about being “cloud first,” this episode will show you why your shiny Azure estate is actually AI hostile. 🧨 We break down the brutal truth: lift-and-shift doesn’t modernize anything—it just moves your technical debt into someone else’s data center. Your VMs won’t give Copilot safe, governed access to data… they’ll give it a front-row seat to your permissions sprawl, lineage gaps, and compliance nightmares. You’ll learn: Why cloud ≠ AI (and how your 2015 migration is blocking 2025 AI use cases) The Fintrax case study: “cloud-first” optics, AI pilot failure, compliance incident, and a 70% cost blowout The 3 pillars of real AI readiness: data discipline, MLOps maturity, and governance talent A no-BS 3-step playbook: Unify → Fortify → Automate so every AI decision becomes traceable and defensible If your roadmap still reads like a relocation plan instead of an AI architecture, hit play before you burn the next dec…

Still dragging cards around in Microsoft Planner like it’s 2015? In this episode, I show you how to stop babysitting boards and start speaking tasks into existence with a “Task Planner” Copilot agent. You’ll learn how Planner, Copilot Studio, and Power Automate actually fit together: Planner keeps the board tidy, Copilot reasons over your requests, and Power Automate quietly runs the rules in the background. Step by step, we build an agent in Copilot Studio with tight instructions and locked-in Group/Plan IDs so it can safely create, list, and update Planner tasks from natural language — including “tomorrow”, “next Friday”, or “set everything to Friday”. Then we push it into Microsoft 365 Copilot and Teams so you can say things like “Create three tasks for next week’s sprint” or “List my open tasks, then set them all to Friday” without touching a single card. We wrap with the unsexy parts that actually matter: governance, DLP, connector ownership, context limits, and how t…

This episode explains how to eliminate manual Excel work by using an autonomous agent that completes spreadsheet-based RFIs without human involvement. Instead of relying on macros or step-by-step automation, the system watches for incoming Excel files, interprets the questions inside them, generates accurate responses using defined knowledge, writes the answers back into the spreadsheet, and sends the completed file automatically. The episode emphasizes the difference between simple automation and true autonomy. Automation waits for instructions, while an agent acts independently by observing, reasoning, and completing tasks end to end. RFIs are used as the ideal example because they are structured, repeatable, and clearly define what “done” looks like. This structure allows the agent to behave predictably rather than creatively, reducing errors and eliminating wasted effort. A major theme is the importance of structure and discipline. Clean inputs, consistent spreadsheet layout…

Your Copilot sounds smart but secretly knows nothing about your business. It’s guessing from Wikipedia while your real memory—orders, invoices, inventory—sits locked in SQL Server behind the firewall. This episode exposes the fix: the Power Platform Data Gateway, a locked-down, outbound-only “spinal cord” that lets Copilot read and write live SQL data without exposing your database. You’ll hear how to plug Azure SQL into Copilot Studio as a Knowledge Source so every chat can fire real-time T-SQL through the gateway instead of stale CSV exports. Then it gets wild: SQL Actions turn Copilot from a chatty analyst into a digital employee that can safely insert and update records with confirmations, least-privilege access, and full audit trails. Finally, you’ll blueprint the “hybrid brain”: SQL as memory, the gateway as spine, Copilot + Power Platform as brain, and Teams/Web as the face your users see. With clusters, indexes, telemetry, and a battle-tested checklist, you’ll ship an AI…