Content by john edward (99)
John Edward outlines the generally available GitHub app for Microsoft Teams, including Copilot task tracking, multi-repository work, and MCP connections. He also explains onboarding and administrator requirements, showing how teams can turn conversations into issues and pull requests while retaining human review of AI-generated changes.
John Edward explains how Microsoft Copilot Studio flags agents that have never been evaluated or whose models have changed since their last evaluation. The automatic Review panel warnings link makers to evaluation tools without blocking publishing, helping teams identify when previous test results may no longer reflect current agent behavior.
John Edward explains an upcoming Microsoft Graph change that makes Threads the default layout for newly created Teams channels when layoutType is omitted. The article shows how developers can preserve Posts through explicit API configuration and outlines checks for scripts, provisioning applications, and third-party integrations before the November rollout.
John Edward covers the general availability of automation flow evaluations in Microsoft Copilot Studio. The capability extends structured quality assessment beyond agents to automation flows, helping makers assess expected outcomes and identify issues before production. The article also outlines repeatable evaluation practices and explains why no immediate administrative action is required.
John Edward covers the general availability of Microsoft Copilot Studio's tool accuracy grader, which evaluates whether AI agents select the correct tools and supply expected inputs. The feature adds execution-level checks to agent testing, while leaving response quality, downstream outcomes, and connected-system reliability as separate evaluation concerns.
John Edward compares Azure Bicep and ARM templates, explaining their shared deployment engine and differences in syntax, validation, dependencies, and reuse. Practical Azure CLI examples show how to compile templates, preview changes, and deploy resources, while migration guidance helps teams decide when to adopt Bicep or retain existing JSON workflows.
John Edward explains why hotpatch-enabled Windows Server 2022 systems will require restarts for November and December 2026 security updates. The article outlines affected devices, the planned January baseline update, and practical steps for scheduling maintenance, coordinating failover, and verifying successful installation without changing hotpatch enrollment.
John Edward explains how to connect Copilot Studio actions to Power Automate flows for controlled contract approval workflows. The guide covers structured inputs and outputs, ambiguous requests, execution permissions, validation, and error handling, with an emphasis on keeping business rules and authorization outside the agent’s conversational instructions.
John Edward explains the upcoming Move to Quarantine action in Microsoft Defender for Office 365 Plan 2. The article covers supported mailbox locations, required permissions, quarantine policies, and partial failures, helping security teams prepare for the worldwide rollout scheduled from November through December 2026.
John Edward breaks down six Copilot Studio enhancements landing in general availability on October 26, 2026, focused on building and operating Copilot Chat (declarative) agents with more predictable conversation flows, better testing and evaluation, usage monitoring, and clearer lifecycle controls across environments.
John Edward explains how to monitor Copilot Studio agents in production by combining conversation analytics with application telemetry, security controls, and outcome-based metrics. The guide focuses on catching failures early (tool-call errors, latency, unsafe access), setting baselines and alerts, and tying cost and performance back to successful task completion.
John Edward explains when multi-agent systems are worth the added complexity, and how to design them so they stay predictable, secure, and testable. The article breaks down common orchestration patterns, communication/state design, guardrails, and practical evaluation metrics for cost, latency, and accuracy.
John Edward explains an upcoming Microsoft Entra default-permission change that lets ordinary users create agent blueprints unless admins disable it. The post breaks down what’s changing, what isn’t, and the specific Entra admin center setting IT teams should review before the November 2026 rollout.
John Edward explains the planner-executor loop as a practical architecture for building agentic systems on Azure, focusing on how to separate planning from execution, validate model outputs, and run tool calls safely. The article maps the pattern to Azure services and highlights reliability, observability, and access-control decisions needed for production use.
John Edward breaks down how to design stateful AI agents that can keep context across interactions, safely call external tools, and coordinate multi-step work with structured planning. The article focuses on practical system design: what to store, how to retrieve it, and how to control execution so agents behave reliably in production.
John Edward explains a planned Microsoft Entra ID change that lets users register passkeys and other passwordless methods as their first MFA option, removing the previous requirement to set up SMS or voice first. The post outlines rollout phases and what admins should review in Conditional Access and authentication method policies.
John Edward outlines a practical audit process for old online accounts, focusing on reducing account-takeover risk through breach checks, password hygiene, MFA, recovery settings, and reviewing third-party access like OAuth tokens and API keys.
John Edward explains Microsoft’s Windows Update certificate rotation planned for 2027, including the two expiration deadlines and which Windows client and server versions need specific security updates to avoid losing access to Windows Update. It also outlines practical inventory, compliance, and recovery steps for IT teams.
John Edward covers Microsoft’s new self-service onboarding flow for publishing new applications to the Microsoft Entra App Gallery, including built-in validation for SSO and provisioning integrations, submission tracking, and the rollout timeline from public preview to general availability in late 2026.
John Edward explains Microsoft’s 2026 retirement of SharePoint Online’s one-time passcode (SPO OTP) flow and the shift to Microsoft Entra B2B guest accounts for external sharing in SharePoint Online and OneDrive, including what breaks, what stays, and what admins should do before the October–November rollout completes.
John Edward covers Microsoft and AWS’s Azure Multicloud Interconnect for AWS announcement, focusing on what it changes for private, high-bandwidth connectivity between the two clouds and why it matters for teams running cross-cloud, data-heavy workloads.
John Edward explains Microsoft’s general availability release of MCP-compliant tools in Copilot Studio agent workflows, and why standardized tool access matters for building enterprise AI agents that can reliably interact with proprietary systems, dynamic knowledge sources, and custom actions under existing governance.
John Edward explains Microsoft Edge’s plan to retire Manifest V2 extensions for enterprises starting in early 2027, what the rollout timeline looks like, and what it means for extension developers and IT admins managing allow-lists and force-installed extensions.
John Edward covers a Copilot Studio authentication update that adds Microsoft Entra ID-based identity for both delegated user access and service-to-service (S2S) scenarios, aimed at making enterprise agent deployments easier to secure and integrate with existing applications.
John Edward summarizes Microsoft’s warning that firewall, proxy, and TLS inspection setups can break Windows Update connectivity, leaving devices without security patches. The post explains the certificate trust model behind Windows Update, why wildcard FQDN allowlists matter, and how admins can use PowerShell and audit logs to confirm the issue before changing network rules.
John Edward lays out a practical checklist for taking an AI agent from demo to production using Microsoft Copilot and Azure AI Foundry, focusing on architecture choices, grounding with enterprise data, controlled tool permissions, evaluation, monitoring, and cost/latency controls.
John Edward explains Microsoft’s required Microsoft Defender for Endpoint update on Android ahead of infrastructure changes, including the minimum supported app version and the rollout timeline. The post focuses on what IT admins should do to avoid disruptions to mobile threat protection across managed and user-updated devices.
John Edward breaks down Microsoft’s August 2026 Windows security update, focusing on the phased Secure Boot certificate rollout, servicing stack improvements, and what admins and users should expect during installation (including a possible extra restart) across Windows 11, Windows 10, and Windows Server.
John Edward explains how to apply FinOps practices to high-volume Azure AI workloads, focusing on the real cost drivers behind model usage, compute, and request patterns. The article lays out practical tactics—visibility, right-sizing, scaling, batching, caching, and guardrails—to keep AI spend predictable without sacrificing latency or reliability.
John Edward covers a Microsoft Defender update that surfaces AI-generated Microsoft Purview Insider Risk Management triage summaries directly in the Defender alert queue, helping SOC analysts and insider risk investigators triage alerts faster while keeping the full investigation workflow in Purview.
John Edward explains Microsoft’s retirement of support for the Microsoft Entra SSO plug-ins used with self-hosted Atlassian Jira and Confluence (Server/Data Center), what “unsupported” means in practice, and the security and operational risks organizations should plan for after July 31, 2026.
John Edward breaks down what GitHub Copilot does (and doesn’t) send to the service, how training and retention settings vary by subscription, and the practical security risks teams should plan for when using AI-assisted coding in real projects.
John Edward explains how to build an AI-powered IT support agent on Azure, using Azure AI Foundry with Azure OpenAI Service and (optionally) Azure AI Search for RAG-based answers grounded in internal documentation, plus ideas for automating common help desk actions like ticket creation and password resets.
John Edward outlines practical Azure architecture best practices for enterprise applications, covering the Azure Well-Architected Framework, scalability and high availability patterns, security with Zero Trust, observability, infrastructure as code, CI/CD, cost controls, networking, disaster recovery, and governance.
John Edward explains why AI agents that look great in demos often break down in production, and what teams need to engineer around the model to make agents reliable at scale.
John Edward explains how Azure’s “Agentic Agents” can support resilient cloud operations across migration planning, observability, and continuous optimization. The article focuses on turning telemetry into actionable guidance, reducing alert fatigue, improving root-cause analysis, and driving cost, performance, security, and sustainability improvements in Azure environments.
John Edward explains how to get more out of Windows Terminal on Windows 11, focusing on practical workflow improvements like profiles, tabs, split panes, the command palette, and keyboard shortcuts, plus common setups for PowerShell, WSL, Git, and Azure CLI.
John Edward outlines an end-to-end approach for building a ServiceNow-focused AI assistant in Microsoft Copilot Studio, aimed at ticket auditing, SLA risk monitoring, and engineer performance reporting. The guide covers a layered architecture, ServiceNow REST API integration via Power Platform custom connectors, and practical security considerations for enterprise deployment.
John Edward explains how to combine a Copilot Studio agent with Power Automate to draft emails and route them through a human approval step before sending, creating a practical “human-in-the-loop” workflow for safer, more consistent business communication.
John Edward explains what an Agent Optimizer is in Azure AI Foundry Agent Service and why it matters for building reliable AI agents. The article breaks down how optimization works in practice—evaluating performance, refining instructions, improving workflows, and learning from feedback—to increase accuracy, efficiency, and user satisfaction.