Designing Safe and Actionable Agents in the New Azure Foundry Portal

AI, AI Agent, Azure AI Foundry, Cloud Security, Security February 22, 2026 Leave a comment

In this blog we will go through the Azure AI foundry Portal and its capabilities .The new Azure AI Foundry portal brings model experimentation, agent building, data grounding, and safety controls into a single, coherent workspace. It’s designed so builders can move from idea to prototype to hardened agent without context switching.

The first thing when we login is we need to switch on the toggle new foundry and it totally brings altogether a new interface and lands us to the dashboard.

This dashboard is the Foundry project home for a developer or team building AI agents. It surfaces the project endpoint and API key for integration, shows the project region, and highlights recent model and tooling updates so teams can stay current. The page also lists recent projects and provides quick links to documentation and community resources, making it a practical launchpad for both prototyping and production work.

In the coding quick start we have the option coding quick start. We can open in vs code for the web.

Continue reading →

Creating Specialized AI Agent with RAG(Retrieval Augmented Generation) in Copilot Studio: A Motorcycle Expert Demo

AI, AI Agent, Open AI February 11, 2026 Leave a comment

Building industry specific AI agents is now easier than ever with Microsoft 365 Copilot Studio especially when combined with Retrieval Augmented Generation (RAG). In this blog, we’ll walk through how to create a RAG powered Motorcycle Expert AI Agent designed for motorcycle store owners who manage large inventories and need to support both customers and sales representatives.

In this example there is a dealership with 200+ motorcycles and this agent helps streamline customer inquiries, improve product comparisons, and empower your sales team with accurate, data‑driven responses.

This step‑by‑step guide shows you how to:

  • Design and prepare your motorcycle dataset
  • Connect SharePoint/OneDrive as your knowledge source
  • Configure RAG settings inside Copilot Studio
  • Shape the agent’s persona and behavior
  • Add comparison logic for models and categories
  • Enable advanced features like deep reasoning and generative orchestration
  • Test and publish the agent with proper security and moderation settings

By the end of this tutorial, you’ll have a fully operational Motorcycle Expert AI Agent running inside Microsoft 365 Copilot Chat, Teams, or web capable of answering questions, comparing models, and delivering expert insights using your actual business data.

The agent will:

  • Answer questions about motorcycles (models, categories, specs, use cases)
  • Compare models (e.g., “MT07 vs SV650 for commuting?”)
  • Use your own data (spreadsheets, docs, or SharePoint lists) as its primary knowledge source
  • Run inside Microsoft 365 Copilot Chat / Teams / web
Continue reading →

The Future of Account Recovery: Microsoft Entra Verified ID Powered by AU10TIX for Account Recovery (Preview)

Cloud Security, Entra ID, Security, VerifiedID February 6, 2026 Leave a comment

Introduction

Microsoft Entra Verified ID transforms identity verification by enabling secure, privacy‑preserving, verifiable credentials. Whether you’re implementing Account Recovery (Preview) or integrating a trusted identity verification partner like AU10TIX, the onboarding process requires a few key steps: enabling the provider, provisioning resources, activating the integration, and validating the recovery flow.

This blog walks through the full, end‑to‑end Verified ID setup using AU10TIX as the identity verification provider. You’ll find prerequisites, detailed configuration steps, screenshots, and a summary to help you complete the setup smoothly

Prerequisites

Before you begin, ensure the following:

  1. Verified ID Setup :

You need to have the Verified ID setup properly configured in your tenant first and the foremost thing to do before proceeding to any steps. If this one is not setup then the account recovery (Preview) is not going to work . Especially your domain needs to be a verified domain here.

Also in the Authentication method you must have the Temproary Access Pass Enabled

Continue reading →

Build Trusted AI with Guardrails and Controls in Azure Foundry

Azure AI, Azure AI Foundry, Cloud Security, compliance January 25, 2026 Leave a comment

As AI systems move from proof of concepts to production, organizations must ensure their applications are safe, secure, and compliant without slowing teams down. Microsoft Azure Foundry brings these capabilities together under Guardrails & Controls, giving builders a central place to filter harmful content, govern agent behavior, block sensitive terms, and receive security insights.

In this walkthrough, We’ll learn how to use the Guardrails & Controls workspace in Azure Foundry with a focus on four areas:

  1. Try it out : experiment with safety checks (text, images, prompts, groundedness)
  2. Content filters : create and assign policy to deployments
  3. Blocklists :ban specific words/phrases from inputs and outputs
  4. Security recommendations : get posture guidance via Defender for Cloud

Why Guardrails Matter ?

Production AI faces unpredictable inputs, sensitive data, and regulatory requirements. Without guardrails, systems can hallucinate, leak private information, or produce unsafe content. Azure Foundry’s Guardrails & Controls reduce those risks by combining content moderation, agent behavior governance, blocked terms, and security posture insights in one place.

Navigate to Guardrails & Controls.

From your Foundry project:

Foundry → (Your Project) → Guardrails & controls

Guardrails & Controls Overview

The Guardrails & Controls landing page in Azure Foundry with tabs for Try it out, Content filters, Blocklists, and Security recommendations.

What you’re seeing:
The overview introduces the guardrails surface with quick entry points for Safety & security guardrails (content filters, blocklists, alerts) and Agent controls (behavior and tool use governance). Use this page as your starting point to design and test safety policies.

Continue reading →

Rethinking Network Access: A Deep Dive into Microsoft Entra Global Secure Access Diagnostics & Troubleshooting

Entra ID, Global Secure Access, SSE January 5, 2026 Leave a comment

Modern network access has evolved, and Microsoft Entra Global Secure Access (GSA) is leading the transformation. Whether users are accessing private resources, Microsoft 365 services, or the internet, every request is now routed through an identity aware, Zero Trust-aligned infrastructure. This shift introduces new troubleshooting paradigms and this guide is here to help.

Why Global Secure Access Exists

Global Secure Access combines multiple security layers to deliver robust protection and optimized routing:

  • Zero Trust enforcement for all traffic
  • Unified identity, device, and network controls
  • VPN replacement for private apps
  • Secure outbound internet access
  • Optimized Microsoft 365 routing

Traffic Profiles Explained

GSA categorizes traffic into three distinct profiles:

  • Internet Access → Secure outbound browsing
  • Microsoft 365 Access → Optimized, identity-aware routing
  • Private Access → Zero Trust access to internal apps

For architectural flow diagrams and examples (e.g., Synology NAS), refer to my previous blog.

Continue reading →

From Home to Zero Trust: A Hands-On Guide to Microsoft Entra Private Access

Entra ID, Global Secure Access, Network Security December 16, 2025 1 Comment

In today’s hybrid work environment, secure access to internal resources without relying on traditional VPNs is a key requirement. Microsoft Entra Private Access, part of the Global Secure Access suite, enables Zero Trust-based connectivity to private applications hosted on-premises or in private networks.

In this demo, we’ll walk through setting up a home lab using an Azure tenant, installing the Entra connector, and configuring access to a Synology NAS as a private application—all from a personal laptop and home network.

Before starting, make sure you have:

  • Microsoft Entra ID tenant with Global Secure Access enabled.
  • Microsoft Entra Global Secure Access license (Private Access feature).
  • Windows 11 Pro device (required for advanced networking and policy support).
  • Device joined to Microsoft Entra ID (Azure AD joined or Hybrid joined).
  • Intune-managed device for policy enforcement and NRPT configuration.
  • Administrative access to your Azure tenant and local machine.
  • Microsoft Entra Connector installer downloaded from the Entra Admin Center.
  • Global Secure Access Client installer for Windows.
  • Internal resource (Synology NAS or similar) reachable on your home network.
  • Internal IP address of the resource (e.g., 10.0.x.x).
  • Optional DNS setup:
    • Private DNS zone or hosts file entry for FQDN (e.g., demo.synology.me).
  • Self-signed certificate (optional) for HTTPS access.
  • Internet connectivity for connector registration and client sign-in.
Continue reading →

Exploring Microsoft Entra Agent ID (Preview): Identity, Governance & Zero‑Trust for AI Agents

AI, AI Agent, Cloud Security, Security December 7, 2025 Leave a comment

Note: Features are in Preview and may change.

As organizations lean into AI assistants and autonomous workflows, one challenge keeps coming up in every SOC and IAM conversation: agent sprawl. Agents show up in multiple teams and builder platforms, and before you know it, you’ve got non‑human actors touching sensitive data without a clear inventory, lifecycle, or policy boundary.

Microsoft Entra Agent ID and the Agent Registry (Preview) are designed to solve exactly that bringing identities, governance, and Zero Trust controls to AI agents, so you can securely discover, organize, and manage them easily in your directory.

What Agent Registry Adds (and Why You’ll Care)

Agent Registry is an Microsoft Entra integrated metadata repository that gives you a unified view of agents built on Microsoft platforms (e.g., Copilot Studio, Azure AI Foundry) and those from other ecosystems. It separates operational records (Agent Instances) from discoverability metadata (Agent Card Manifests) and introduces Collections to govern which agents can discover and collaborate with each other. Think discovery before access a crucial shift for reducing exposure.

A Quick Look at the Tenant Experience

Agent ID Overview (Preview) dashboard showing agent counts, status, types, and blueprints: high-level posture of agents, identities, blueprints, and collections

Continue reading →

Navigating DORA with Microsoft Purview: A compliance blueprint for Microsoft 365

Microsoft 365, Purview October 28, 2025 Leave a comment

Digital Operational Resilience Act (DORA) is reshaping how EU financial entities manage ICT risk, resilience testing, incident reporting, and third‑party risk. If you run Microsoft 365, Microsoft Purview Compliance Manager gives you a practical way to translate DORA requirements into actions, evidence, and measurable progress. This guide walks through a clean, step‑by‑step implementation flow from setting up a DORA assessment to assigning improvement actions and tracking your score, so you can be audit ready without drowning in spreadsheets.

Why use Microsoft Purview Compliance Manager for DORA ?

  • Prebuilt assessments: DORA assessment templates map regulatory articles to actionable controls you can assign and track.
  • Control mapping: Microsoft‑managed baselines and customer‑managed controls provide clarity on shared responsibility.
  • Improvement actions: Structured tasks with owners, due dates, and recommended steps create accountability.
  • Evidence management: Centralized artifacts (documents, links, screenshots) simplify audit preparation.
  • Real‑time scoring: Compliance scores help prioritize high‑risk gaps and demonstrate progress.

Prerequisites and approach

  • Access: Ensure you have appropriate roles in Microsoft Purview (e.g., Compliance Manager Admin or similar).
  • Scope: Decide which services to cover first; start with Microsoft 365 for a focused rollout.
  • Vanilla setup: Use a fresh assessment group to avoid inherited noise and control drift.

Quick Tip

Can also use the default user access options available from the Assesment option in the Compliance Manager Portal

Step‑by‑step setup in Compliance Manager

Create and configure your DORA assessment

  • Open Purview: Go to Microsoft Purview portal → Compliance Manager – Navigate to assessment – Select Regulation
  • Find templates: Search for “Digital” under assessment templates. (I was not able to find with DORA :))
Continue reading →

Top 10 Browser Security Controls that can be Enforced with Microsoft Intune

Cloud Security, Endpoint Security, Intune, Security October 17, 2025 Leave a comment

In today’s enterprise landscape, most applications are accessed through modern browsers like Microsoft Edge and Google Chrome, especially on Windows devices. While these browsers come with built-in security features, organizations must go a step further to enforce consistent and robust browser security policies across all endpoints.

If your organization uses Microsoft Intune, you have powerful tools at your disposal to configure and enforce browser security settings. In this blog, we’ll walk through 10 essential browser security controls you can implement using Intune’s Settings Catalog to enhance protection against web-based threats.

1. Enable Windows Defender SmartScreen

SmartScreen helps protect users from phishing attacks and malicious websites or downloads.

Recommended Settings:

  • Enable Windows Defender SmartScreen
  • Don’t allow SmartScreen warning overrides for unverified files
  • Don’t allow SmartScreen warning overrides
Continue reading →

Deep Dive into Microsoft Purview Adaptive Protection: A SOC Team’s Guide to Investigating Insider Risk Alerts in Adaptive Protection

Adaptive Protection, DLP, Microsoft 365, Purview October 7, 2025 Leave a comment

In today’s hybrid work environment, insider threats are becoming increasingly complex. Microsoft Purview’s Adaptive Protection and Insider Risk Management (IRM) offer a dynamic, risk-based approach to protecting sensitive data while enabling SOC teams to investigate and respond to alerts with precision.

This blog provides a step by step walkthrough of how SOC teams can leverage these tools to investigate alerts, assess user behavior, and take appropriate action.

Step 1: Understanding the Adaptive Protection Dashboard

The Adaptive Protection dashboard is the SOC team’s starting point. It provides a bird’s-eye view of user risk levels across the organization, helping analysts prioritize investigations.

Key Elements of the Dashboard:

  • User Risk Levels:
    • Elevated Risk: Users exhibiting high-risk behavior that may indicate potential data exfiltration or policy violations.
    • Moderate Risk: Users with concerning patterns but not yet critical.
    • Minor Risk: Users with low level anomalies or early warning signs.
  • Policy Integration:
    • Shows which Insider Risk policies are actively using these risk levels.
    • Helps correlate user behavior with policy triggers, such as data leakage,
    • Security violations, or unusual access patterns.
Continue reading →