Microsoft Mechanics Podcast

Microsoft Mechanics

Made for tech enthusiasts and IT professionals. Expanded coverage of your favorite technologies across Microsoft; including Office, Azure, Windows and Data Platforms. We'll even bring you broader topics such as device innovation with Surface, machine learning, and predictive analytics.

  1. 44m ago ·  Video

    Build apps by describing what you want | Copilot Code

    Turn your app idea into a working, interactive web app with Copilot Code. Describe what you want in plain language, ground it in your work data with Work IQ, build what-if modeling from your own business logic, and refine it prompt by prompt. Publish and share cloud projects that reside within your company's Microsoft tenant boundary and respect your organization's access and security controls. Track usage, health, and connected services, and block or delete any app from the Microsoft 365 admin center. Anjali Muralidhar, Copilot Code Product Manager, shares how to take an idea from first prompt to a published, governed app.  👥 Who it's for: Business analysts and team leads who need dashboards built from internal data, Microsoft 365 admins governing who builds apps and what they connect to, and developers who want to inspect AI-generated code.  ⏱️ Chapters: 0:00 Build apps by describing what you want 0:57 Pick a cloud or local project and model 1:31 Ground prompts in SharePoint data with Work IQ 2:41 Preview the app and its data model 3:09 Inspect the code Copilot writes 3:36 Refine the app with follow-up prompts 4:14 Explore the finished market dashboard 4:38 Model returns with what-if sliders 5:09 Publish and share the app by link 5:32 How the Copilot Managed Runtime works 6:05 Track apps in the Microsoft 365 admin center 6:51 Block or delete apps that miss policy 7:08 License requirements and how to start How do you build an app with Copilot Code? Anjali Muralidhar, Copilot Code Product Manager, opens Copilot Code in the Copilot desktop app, starts a new cloud project, and keeps the model on Auto. Her prompt points to the Global Markets sheet in an Excel workbook in SharePoint, describes the business problem, sets layout and color behavior by revenue thresholds, and spells out the logic behind budgeting and capacity estimates. Copilot reasons through the instructions, builds a data model that reflects that business logic, and shows a preview. Follow-up prompts refine the app instead of rewriting it, and Files exposes the code Copilot writes for anyone who wants to inspect or edit it. The finished dashboard puts the whole portfolio on one screen, with what-if sliders that update top-line numbers, map color coding, and revenue uplift rankings as marketing investment changes. How does sharing work? Publish the app and share it with a link. Sharing apps built using Copilot Code leverages the Copilot Managed Runtime, which provides compute as well as dedicated storage using a Git repo. Cloud projects reside within your company's Microsoft tenant boundary and respect your organization's access and security controls. Local projects on your managed device work within an isolated and protected boundary on your local drive, controlled by your organization's Copilot Code policies. How do admins govern Copilot Code apps? The Microsoft 365 admin center lists every published app in a shared inventory with usage, operational health, performance metrics, alerts, and connected services. Admins control which plugins, connectors, and GitHub integrations are allowed, and block or delete apps that miss policy. Blocking disables an app across the organization and leaves its data intact and auditable. Copilot Code requires a Copilot license and usage-based billing enabled in your Microsoft 365 environment.  🔗 Related links: — Check out https://aka.ms/CopilotCodeDocs ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics   —  https://www.linkedin.com/company/microsoft-mechanics/  — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  2. 12h ago ·  Video

    Manage AI Cost + ROI with Copilot and Agent 365

    Take control of AI spend across Microsoft Copilot, Cowork, and agents inside and outside of Microsoft. Track your own Copilot Credit usage task by task, pin down your top cost drivers by service and model provider in Agent 365 Business Analytics, and weigh each use case's cost against its measured AI value. Forecast month-end spend, model a shift to lower-cost models, and enforce hard budgets with spending policies scoped to users, groups, or shared agents in the Microsoft 365 admin center. Delegate budget control to the owners closest to the work. Jeremy Chapman, Microsoft 365 Director, shares how users, budget owners, and IT admins each play a part in turning AI spend into measurable value. 👥 Who it's for: IT admins and Microsoft 365 admins setting up usage-based billing and AI budgets, FinOps and budget owners managing Copilot and agent spend, and CIOs and business leaders measuring AI ROI across their organization. ⏱️ Chapters:  00:00 Control AI spend across Copilot and agents 00:46 Track your own Copilot usage and limits 01:22 How Copilot Credits measure AI consumption 01:36 Measure AI ROI in Agent 365 Business Analytics 02:52 Pin down top cost drivers by model 03:35 Spot top users and spread best practices 03:57 Weigh use case cost against AI value 05:04 Forecast month-end cost and model scenarios 05:51 Raise spending limits as a budget owner 06:37 Enable usage-based billing in Microsoft 365 07:19 Create spending policies with hard limits 08:35 Delegate budget roles to owners outside IT 09:32 Start with Business Analytics and admin setup Every advanced AI task in Microsoft Copilot, from a simple prompt to a complex Cowork or agent workflow, consumes Copilot Credits. One Copilot Credit currently equals one cent in US dollars. Users check their own consumption under Usage details in Copilot, with a seven-day view, remaining monthly limit, and credits used per task. Agent 365 Business Analytics gives managers, budget owners, and CIOs an organization-wide or filtered view of AI usage and cost by manager hierarchy, organization, or job function. Break down spend by service, model provider, and use case. Compare services like GitHub Copilot and Cowork, and use the combined view to see which models each service relies on and how that adds up to cost. The Use cases view maps sessions, cost, and AI value by business domain, with AI value calculated from the time it would take a person to do comparable work, using official sources including the US Department of Labor. Cost & Forecast projects month-end cost and shows what drives increases and decreases by job function, model, and service. Model what-if scenarios, such as a spending cap, expanded access, or a shift to lower-cost models, and compare the results with current usage. In the Microsoft 365 admin center, IT admins enable usage-based billing with an Azure subscription on pay-as-you-go or prepaid billing, then create spending policies under Cost Management. Scope policies by identity or by resource, such as a shared agent, set cumulative and per-user monthly limits, configure alerts, and control which models are allowed with templates. Assign Delegator, Writer, and Reader roles so budget owners outside IT manage policies directly from Agent 365 Business Analytics.  🔗 Related links: — Check out Agent 365 Business Analytics at https://aka.ms/A365Analytics — Activate usage-based billing and set up your policies at https://admin.microsoft.com ► Unfamiliar with Microsoft Mechanics?  Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics —  https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  3. 1d ago ·  Video

    Azure SQL Database Hyperscale - Now for any size workload

    Start small and scale up to your most demanding workloads on Azure SQL Database Hyperscale. Run serverless compute that scales with demand and auto-pauses, so you stop paying for idle compute. Pool databases across tenants or business units and run cross-database joins and transactions natively. Build AI apps on the same SQL engine. Store relational data, JSON and vectors together, run hybrid vector search across more than 1 billion rows with DiskANN indexes, and move read-heavy workloads to named replicas with no data copy. Connect Foundry agents through a SQL MCP Server, control their access down to the individual cell, and turn on automatic index compaction to keep queries running at speed. Bob Ward, Principal Architect, SQL, shares how to size and deploy the right Hyperscale configuration from a single prompt with a GitHub Copilot skill in VS Code.  👥 Who it's for:  DBAs, database developers and app developers building on Azure SQL, plus solution architects planning multi-tenant, high-scale or AI-powered workloads. ⏱️ Chapters: 00:00 Run small to massive workloads on Hyperscale 00:56 How Hyperscale's distributed layers scale independently 02:01 No separate SQL Server license required 02:37 Size and deploy with a GitHub Copilot skill 03:27 Serverless compute scales up and down 03:58 Auto-pause stops billing for idle compute 04:34 Share capacity across databases with elastic pools 06:28 Cross-database joins and remote transactions 07:15 Store relational data, JSON and vectors together 07:38 Hybrid vector search with reciprocal rank fusion 08:38 Search 1 billion+ rows in milliseconds 09:12 Offload reads to named replicas, no data copy 10:04 Build Foundry agents with a SQL MCP Server 11:07 Control agent access down to the cell 11:36 Automatic index compaction for faster queries 13:16 Try the Copilot skill and go deeper Azure SQL Database Hyperscale is a fully managed, cloud-native SQL database built on the familiar SQL Database engine. Compute, page servers, a log service and long-term Azure Storage each run as separate layers that scale independently, with storage up to 128 TB and zone redundancy for automatic failover. The name describes room to grow, not a minimum size. Hyperscale provisions in minutes, updates continuously and needs no separate SQL Server license. The demo takes a patient scheduling app from a single serverless database to a three-clinic elastic pool sharing 24 vCores. Cross-database views find open appointments across every clinic, and remote transactions keep bookings consistent end to end. On the AI side, a biomedical evidence explorer runs hybrid vector and keyword search, merges the results with reciprocal rank fusion, and then scales to 192 vCores and about 8 TB. Up to 30 named replicas share the primary's page servers and vector index, spin up in minutes, and take search and reporting load off the primary. A research agent in the Foundry Agent Service uses a SQL MCP Server to search evidence, compare sources and write up a briefing. Automatic index compaction, which you enable with ALTER DATABASE in SSMS, uses background tasks to compact sparse index pages. The result is fewer logical reads and faster dashboards. 🔗 Related links: — Try the Azure SQL Hyperscale configuration skill at https://aka.ms/SQLHyperscaleMechanics — Get started at https://aka.ms/SQLHyperscale — Read Bob Ward's book on Hyperscale at https://aka.ms/sqlhyperscaleunveiled ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics —  https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  4. Nov 10 ·  Video

    New Microsoft Copilot Harness | More power, token efficiency & control for agents in Foundry

    Build agents you can trust with your company's data, apps, and resources using Microsoft Foundry. Start with a fully managed prompt agent and move it onto the Microsoft Copilot harness so it plans, loops, calls subagents, and delivers finished reports. You can also bring your own harness, such as the Claude Agent SDK, and run it as a hosted agent with isolated VM sandboxes, autoscaling, and zero idle cost. Give every agent its own Entra Agent ID, restrict its egress to approved endpoints, and trace every action it takes. Curate tools once in a governed, MCP-compatible toolbox, cut token use with tool search, and tune agents against your own benchmark with Agent Optimizer. Jeff Hollan, Microsoft Foundry VP, shares how to balance agent autonomy with enterprise control from first build through production. 👥 Who it's for:  Developers and AI engineers building production agents, solution architects designing agent platforms, and IT and security teams responsible for governing agent identity, access, and network egress. ⏱️ Chapters:  00:00 Why the harness decides agent trust 00:59 What an agent harness does 01:22 Five components built into every harness 02:15 Microsoft Copilot harness meets Foundry controls 03:28 Where a prompt agent falls short 04:57 Same agent on the Microsoft Copilot harness 06:10 Guardrails block unauthorized agent actions 07:29 Entra Agent ID and egress rules 08:05 Bring your own harness as a hosted agent 09:06 Private networking, regions, and your own registry  10:13 Curate tools once with Foundry toolboxes 11:13 Tool search keeps agent context lean 11:54 Benchmark agents against your real tasks 12:54 Auto-tune agents with Agent Optimizer 13:53 Start building in Microsoft Foundry What is an agent harness? The harness is the environment you wrap around your model and agents. It runs the agent loop, manages context as it grows, provides skills and tools such as MCP servers, delegates work to subagents in parallel, and maintains memory across turns and sessions. The Microsoft Copilot harness is model-agnostic, optimized for enterprise task completion, and runs behind Microsoft services like GitHub and Microsoft 365. Inside Microsoft Foundry, it respects your existing permissions and data protection controls and runs each agent instance in its own isolated sandbox. Hosted agents in Microsoft Foundry Agent Service also support Hermes, OpenClaw, and fully custom harnesses, along with your own virtual network, container images from your own registry, and expanded regions so agents run where your data is. 🔗 Related links: ► Head to Microsoft Foundry to build your first project at https://ai.azure.com ►For hosted agent templates and the SDKs to start coding, check out https://github.com/foundry-samples ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics — https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  5. Oct 28 ·  Video

    New Conditional Access policy plans in Microsoft Entra

    Group related Conditional Access policies into policy plans and define users, apps and conditions once for every rule in the plan. Add a rule for each requirement, like phishing-resistant MFA or compliant devices, and keep the shared scope in one place. Build a plan around a user group, like headquarters staff, or a shared condition, like high agent risk, and start from templates. Merge existing policies into a plan with the migration tool. It pulls shared conditions up to the plan and turns each policy into a rule. Your current policies stay enforced until you cut over. Etan Basseri, Principal Product Manager, Microsoft Entra, shares how plans and rules fit together in the Microsoft Entra admin center. 👥 Who it's for: Identity and security admins who manage Conditional Access in Microsoft Entra, and architects planning how to organize or migrate large policy sets, including access controls for AI agents. ⏱️ Chapters: 00:00 Conditional Access policy plans in Microsoft Entra 00:48 Track policies beyond naming prefixes 01:29 How shared conditions and rules work 02:41 Create a policy plan for HQ users 03:43 Add a phishing-resistant MFA rule 04:43 Add a compliant device rule 05:51 Block high-risk AI agents in one plan 06:56 Migrate existing policies into a plan 08:11 Keep policies enforced until cutover What are Conditional Access policy plans? They organize access controls around an objective, either a persona like employees, external guests or administrators, or a security goal like requiring compliant devices or securing agent activity. Plan-level attributes cover identities, resources and applications, user actions and authentication context, plus shared conditions like risk levels, devices, network locations and client app types. Each rule layers its own conditions and grant or session controls on top. Plans live in a new Policy plans view, next to your existing policy list under Conditional Access. The headquarters plan in the demo includes the HQ All Users group and excludes a break-glass group to prevent lockouts. Its first rule requires phishing-resistant MFA through authentication strength and starts in report-only mode. A second rule requires devices marked as compliant. Neither rule repeats the included or excluded groups. The agent plan, built from a template, sets high agent risk as its shared condition. Separate rules block high-risk agent users and high-risk autonomous agents acting with their own agent-specific permissions. How do you move existing policies over? Filter your policy list, for example by a branch office naming prefix, select the policies and merge them into one plan. The preview shows which resources become shared conditions and how each policy maps to a rule, with its identities, locations, grant and session settings. After you enforce the new plan, turn off or delete the original policies. 🔗 Related links: ► Check out https://aka.ms/ConditionalAccessPolicyPlans ► Unfamiliar with Microsoft Mechanics?  Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics — https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  6. Oct 13 ·  Video

    Fight AI with AI | Multi-Agent Security Defense

    Match AI-powered attacks at machine speed with Project Perception. Point red, blue, and green AI agent teams at a known threat actor, confirm which vulnerabilities attackers can reach, then deploy KQL detections, harden your posture, and merge a tested code fix in minutes with Microsoft Defender. Stay in control and approve key actions before agents run them. Run Microsoft's pre-built playbooks or build your own, and manage sessions from the Defender portal or from your terminal with the MCP plug-in. Keep token costs low with MAI Cyber Flash, a purpose-built security model inside MDASH. Dave Weston, CVP Microsoft Security, shares how Microsoft's threat intelligence and incident response expertise power agents you direct.  👥 Who it's for: SOC analysts, security engineers, and red and blue teamers evaluating agentic AI for defense, plus AppSec and DevSecOps teams who own vulnerability remediation.  ⏱️ Chapters: 00:00 Fight AI-powered attacks with AI agents 00:45 How AI attacks adapt mid-breach 01:39 Jailbroken and abliterated models 02:04 Inside the Project Perception security stack 03:28 Red, blue, and green agent teams 04:07 Playbooks that orchestrate agent workflows 04:43 Ask Perception if you're protected 06:06 Red team agents emulate a threat actor 06:59 Approve high-impact agent actions 07:26 MDASH findings confirm reachable vulnerabilities 08:22 Blue team agent writes KQL detections 08:54 WAF, auth check, and tested code fix 09:36 Pull request merged into production 10:14 Session reports and MCP terminal plugin 11:02 MAI Cyber Flash keeps token costs low 11:57 Join the Project Perception preview AI helps attackers find, weaponize, and exploit vulnerabilities at a speed and scale no human team can match. Jailbroken and abliterated models generate custom tooling that adapts mid-breach, leaving defenses that hunt for known techniques chasing a target that changes every time. Project Perception answers with a full agentic security stack. It starts with trillions of daily security signals, correlates them in the Microsoft security graph, and uses multiple AI models, including purpose-built ones, to reason over risk and prioritize what matters most. Specialized agents act on that reasoning: red team agents simulate attacks and prove where you're vulnerable, blue team agents investigate and build detections, and green team agents harden posture and remediate. Playbooks orchestrate them through proven SOC workflows, and codified actuators let agents perform the fix instead of only recommending it. In the demo, one prompt, "Is my organization protected against Onyx Sleet?", launches threat intelligence, reconnaissance, and pen test agents. They pull MDASH code-scanning findings and confirm an internet-exposed SQL injection. A detection authoring agent writes KQL detections to cover the gap, and the posture remediation agent shields the app with a web application firewall, adds an authorization check, and produces a tested code fix merged through a pull request. Agents stop and ask before any high-impact action, so you stay in control. Every session produces a shareable report with the attack path, remediation plan, and timeline. An MCP tool plugin runs the same work from your terminal, and MAI Cyber Flash, a dedicated cybersecurity model inside MDASH, handles most vulnerability work to keep token costs low.  🔗 Related links:  ► Get started at https://microsoft.com/perception ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics —  https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  7. Oct 5 ·  Video

    Build Automated Agents, Workflows, and Apps - New in Copilot Studio

    Take a business process from prompt to production by building agents, workflows, and apps in one place with Copilot Studio. Describe the agent you need and generate its instructions and reusable skills, choose the model, connect MCP tools and specialist agents, then test its quality at scale with Evaluations. Trigger workflows from incoming email, classify submissions, hand work to your agents, and pause for human review on the decisions that need it. Track timing and paths for every step in the Activity tab. Then generate a full stack app on your Dataverse data so your team can filter, review, and approve every bid from one shared view. Jack Rowbotham, Copilot Studio Senior Product Manager, shares how to automate a procurement process for bids from multiple vendors, using agents that reason, route, and recommend.  👥 Who it's for: IT admins, Power Platform makers, solution architects, and developers building agentic solutions, plus operations and procurement teams automating reviews and approvals. ⏱️ Chapters: 00:00 Build agents, workflows, and apps in one place 01:04 Automate a multi-vendor bid review end to end 02:18 Build an agent from a prompt 03:28 Add models, MCP tools, and specialist agents 04:13 Test the bid agent in Preview 05:05 Evaluations 05:59 Automated workflows 07:42 Track every run in the Activity tab 08:13 Build an app from a prompt 09:10 Approve bids from the team app 09:37 Get started with Copilot Studio  Copilot Studio brings agents, workflows, and apps together in one place, all running on the GitHub Copilot harness. In this video, a supplier email triggers a workflow, a bid evaluation agent checks the bid against tender requirements, and the procurement team makes the final call in a shared app. Describe the agent you want, including the requirements to assess, the logic to apply, and the live data source to connect to. Copilot Studio reasons over your prompt, maps out its build steps, and generates the agent's name, instructions, and skills for requirement coverage and evidence verification. Connect Work IQ for supplier emails and the Dataverse MCP server for bid data, keep Claude Sonnet as the reasoning model, ground the agent in an RFP example PDF, and add a Supplier Risk specialist agent. Test the agent in the Preview tab and watch its chain of thought as it flags gaps in certification, cold-chain handling, and insurance minimums. Then run Evaluations with your own conversations, auto-generated tests, or a CSV file. Here, 18 test cases met the evaluation criteria 89% of the time. In the Workflows tab, drag in an Outlook "When a new email arrives" trigger, a Classify step for RFP submissions, a Get Attachment connector, and an Agent step running the Bid Evaluation Agent. An if/else Human Review step brings in a person on flagged bids, and the Researcher agent and a recommendation agent finish the job before results land in Dataverse. Finish in Apps by describing a Bid Management App connected to your Dataverse table, or to sources like SharePoint through connectors. Apply company branding with a follow-up prompt, then filter bids that need human review and approve decisions from the app.  Try it for yourself at copilotstudio.microsoft.com. Subscribe to Microsoft Mechanics for more videos like this. 🔗 Related links: — Get started with Copilot Studio: https://copilotstudio.microsoft.com ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe: https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast  ► Join us on social: — https://twitter.com/MSFTMechanics — https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

  8. Sep 23 ·  Video

    Create agents fast with Agent Builder in Copilot

    Build a specialist AI agent without writing a line of code. Describe what you want in one prompt, and Copilot Agent Builder generates the name, instructions, skills, and knowledge setup for you — grounded only in the SharePoint sites, files, and Copilot Connectors you choose. Teach your agent a Skill to handle recurring work, like drafting weekly status emails from your own template, then test it in Preview before you publish. Share it with people or groups and set exact permissions, track real usage in the new Monitor tab, and push your best agents into your org's Agent Store catalog. Ned Friend, Group Product Manager for Copilot Agent Builder shares how to turn an agent into a tool your whole team can run, measure, and trust. 👥 Who it's for: Team leads and managers who want trusted, repeatable answers for their team, plus IT admins and Microsoft 365 power users building specialist Copilot agents without code. ⏱️ Chapters: 0:00 Build specialist agents inside Copilot 0:34 Ground agents in trusted org knowledge 1:31 Create a new hire onboarding agent 2:15 Natural-language agent creation 2:41 Ground answers in SharePoint knowledge 4:13 Skills for repeatable tasks 4:53 Precise knowledge grounding 6:37 Preview and test before publishing 7:03 Share your agent with set permissions 7:39 See the new hire's agent view 8:22 Usage monitoring 8:41 Publish agents to your org catalog Copilot Agent Builder lets you create a specialist agent by describing what you want it to do in plain language. Agent Builder interprets that prompt and automatically generates the agent's name, description, instructions, skills, knowledge sources, and suggested prompts, which you can review and edit directly. Ground every answer in the exact knowledge you choose: SharePoint and OneDrive files, Outlook email and calendar, Microsoft Teams chats and meetings, or external business systems connected through Copilot Connectors. Turn on web search only when you want the agent to research beyond your organization, like competitor or customer research. Add Skills to teach the agent repeatable, multi-step work — in this video, a weekly status update email built from a real template, matching its tone, sections, and formatting automatically. Preview and test the agent before publishing, then share it with people or groups and set whether they can use it or edit it. Once your agent is live, the Monitor tab tracks total sessions, daily active users, average messages per session, average duration, and which knowledge sources get used most. For agents with strong adoption, publish them to the Built by your org section of the Agent Store for wider use across your organization. Try Copilot Agent Builder for yourself — it's included with Copilot. Subscribe to Microsoft Mechanics for more videos like this.  ► Unfamiliar with Microsoft Mechanics? Microsoft's Official Video Series for IT — Subscribe https://www.youtube.com/c/MicrosoftMechanicsSeries — Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog — Podcast: https://microsoftmechanics.libsyn.com/podcast ►Join us on social: — https://twitter.com/MSFTMechanics — https://www.linkedin.com/company/microsoft-mechanics/ — https://www.instagram.com/msftmechanics/ — https://www.tiktok.com/@msftmechanics

Ratings & Reviews

4.2
out of 5
20 Ratings

About

Made for tech enthusiasts and IT professionals. Expanded coverage of your favorite technologies across Microsoft; including Office, Azure, Windows and Data Platforms. We'll even bring you broader topics such as device innovation with Surface, machine learning, and predictive analytics.

You Might Also Like