21 min read
Fabric Data Agent Accuracy Is a Distribution, Not a Number
I asked a Fabric data agent 24 questions in three wordings, ten times each, on real AEMO data. It scored 82%, but only 39% of wordings were always right.
AI Agents
67 articles
9 min read
Fabric's Data Engineering Agent: Set Guardrails Before Autonomy
Fabric's preview data engineering agent runs with the launching engineer's permissions. What to delegate first, which settings to pick, and what stays human.
9 min read
Foundry Routines Are GA: Scheduled Agents Without Building a Scheduler
Foundry routines run an agent on a timer, a schedule or a GitHub or Teams event. When to use them, when to use a workflow, and guardrails for unattended runs.
9 min read
Egress Policy Belongs on the Agent, Not in Its Code
Foundry's preview egress controls attach ordered destination rules to a hosted agent. Why that limits prompt-injection damage, and how to roll it out safely.
8 min read
Fabric Data Agents Move to the Responses API: What Consumers Must Change
Fabric data agents now use GPT-5.1 and a Responses API client. What notebook, Foundry and app callers must change, and why you need a full eval re-run.
9 min read
Claude's Server-Side Tools in Foundry: What to Let the Provider Run
Claude hosted on Azure in Foundry now runs web fetch, web search, tool search and an MCP connector for you. Decide which belong behind your own gateway.
9 min read
Foundry Hosted Agents Are GA: When to Stop Running Your Own Containers
Hosted agents in Foundry Agent Service are GA. How they compare with Agent Framework on Container Apps or AKS on identity, networking, cold starts and tracing.
9 min read
Model Router Already Routes to Claude and Open Models: Govern the Pool
Foundry Model Router picks from OpenAI, Anthropic, DeepSeek, xAI and Meta models. Treat subsets, policy and model logging as governance, not tuning knobs.
8 min read
Harness Agent or Plain Agent? What Agent Framework Now Decides for You
The Agent Framework Harness bundles planning, memory, compaction, approvals and telemetry. When to accept its opinions and when a plain Agent is better.
7 min read
Agent Fallbacks Are a Launch Requirement, Not an Ops Task
Decide what an agent does when a tool fails, a step runs out of budget or grounding is weak before launch, and make the release check fail without it.
8 min read
Where Agent State Breaks: Resume, Retries and Duplicate Runs
Typed state and checkpoints don't stop an agent paying twice: five places agent workflow state breaks at its boundaries, and patterns that hold.
8 min read
Agent Tool Policy at the Gateway: MCP Through API Management
Tool rules inside agent code drift once several teams build agents. Put identity, rate limits and tracing for MCP tools in Azure API Management instead.
8 min read
Foundry Agent Versions as Releases: Git, Evals and Publishing
How I'd run Microsoft Foundry agent changes like releases in April 2026: definitions in Git, versions from CI, evaluation gates and Agent Application promotion.
8 min read
Testing Agent Tool Policies: Prove the Limits Hold
A tool policy nobody tests is a comment. How to assert agent tool lists and approvals in CI, then gate tool use on a golden set of scenarios.
6 min read
Explicit State for Agent Workflows: Stop Making the Model Remember
Agents get confused when workflow state lives in the chat transcript. Four patterns for typed state, fresh context and code-owned transitions.
9 min read
Foundry After the March GA: What's Governed and What's Still Preview
Foundry Agent Service went GA in mid-March 2026, but monitoring and tracing are still preview. What's governed now, and the controls I'd add first.
6 min read
Least-Privilege Tools for AI Agents: Four Layers of Control
Agent reliability depends on which tools a model can reach. Four layers of tool policy (surface, schema, approval, budget) with Agent Framework code.
6 min read
Semantic Kernel Apps in February 2026: Stay, Bridge, or Rewrite
Agent Framework is still in preview and Semantic Kernel is in fix-and-stabilise mode: how to decide whether to stay, bridge, or rewrite in February 2026.
6 min read
Workflow First, Agent Inside: Putting the Model in One Step
Most agent designs only need autonomy in one step. How to build the workflow around it with Agent Framework executors, switch-case edges and loop caps.
8 min read
Agentic Retrieval or a Hand-Built RAG Pipeline? How I Decide
Azure AI Search knowledge bases now plan queries for you, in preview. When to hand over the RAG pipeline, when to keep building it, and how to test both.
8 min read
Semantic Kernel Agents in Production: What's Stable, What Isn't
Running Semantic Kernel agents in production in early 2026: which APIs are GA, which are preview, how to guard tool calls, and where Agent Framework fits.
1 min read
Building Multi-Agent Systems with AutoGen and Azure
Instead of a single LLM handling all tasks, multi-agent systems divide work among specialized agents that communicate and coordinate to achieve goals.
1 min read
Ignite 2025 Day 3: Copilot Extensions and Agent Framework
The Copilot agent framework represents a significant step toward enterprise AI automation, enabling organizations to build intelligent assistants that work…
1 min read
Semantic Kernel: Orchestrating AI Agents with Plugins and Planners
Semantic Kernel abstracts the complexity of working with multiple AI services while providing extensibility through plugins. This allows developers to…
1 min read
Copilot Studio: Building Custom AI Agents for Enterprise Workflows
Traditional chatbots follow rigid conversation flows. AI agents powered by Copilot Studio understand intent, access knowledge bases, and execute multi-step…
1 min read
Building AI Agents with AutoGen and Azure OpenAI
AutoGen enables building sophisticated AI systems that can decompose complex tasks and collaborate to find solutions.
1 min read
AI Agent Memory: Implementing Long-Term Context
Long-term memory transforms one-shot interactions into ongoing relationships. Users feel understood when the AI remembers their preferences, past issues…
1 min read
Multi-Agent Systems: Orchestrating Specialized AI Agents
Multi-agent architectures shine for tasks requiring diverse expertise: research reports, code reviews, complex analysis, and creative projects. The key is…
1 min read
Building AI Agents with Tool Use: A Practical Architecture
At its core, an AI agent follows a simple loop: observe, think, act, repeat. Tools should be focused, well-documented, and handle errors gracefully.
1 min read
Building Multi-Agent Systems with Semantic Kernel
Define clear responsibilities for each agent to avoid confusion and improve reliability. Multi-agent architectures excel at complex workflows where…
1 min read
Building AI Agents with Semantic Kernel Planners
Planners analyze a user's goal and create an execution plan using available plugins. The Handlebars planner generates a template-based plan, while function…
1 min read
Building AI Agents with Azure AI Foundry: A Post-Build 2025 Implementation Guide
The new agent framework introduces several critical improvements. First, native multi-agent orchestration allows agents to collaborate without custom…
8 min read
AI Safety Research in 2025: What Builders Should Act On Now
Late-2024 safety research on scheming, alignment faking and prompt injection, translated into concrete controls for Azure teams shipping AI in 2025.
7 min read
Model Context Protocol Six Weeks In: What It Is and Where It Fits
A practitioner's read on Anthropic's Model Context Protocol in January 2025: the primitives, a read-only SQL server in Python, and when not to use it.
8 min read
Agentic Workflows That Survive Restarts with Durable Functions
Run an LLM tool-calling loop inside Azure Durable Functions so it checkpoints each step, stays within a step budget and waits hours for human approval.
7 min read
Multi-Agent Orchestration: Pick the Pattern Before the Framework
Four multi-agent orchestration patterns, what Semantic Kernel, AutoGen 0.4 and Azure AI Agent Service offered for each in January 2025, and when to skip them.
7 min read
AI Agents in 2025: What You Can Actually Ship on Day One
A practical look at the agent tooling that really exists on 1 January 2025, what is still preview, and where to draw the line on autonomy.
1 min read
Copilot Agents: Declarative and Custom Engine Approaches
Start with declarative agents for rapid prototyping and move to custom engines when you hit limitations.
3 min read
Enterprise Agent Patterns: Security, Governance, and Scale
Enterprise agents require these patterns to ensure security, compliance, and reliable operation at scale. Implement them from the start rather than…
1 min read
AI Agent Templates: Quick Start Patterns for Enterprise Use Cases
Templates accelerate agent development by providing battle-tested patterns. Start with a template, customize for your needs, and iterate based on real usage.
1 min read
Multi-Agent Frameworks: Orchestrating AI Agent Collaboration
Multi-agent systems unlock sophisticated automation capabilities. Start with simple patterns and evolve complexity as needed.
1 min read
Azure AI Agent Service: Building Autonomous AI Agents
Azure AI Agent Service provides the foundation for building sophisticated AI systems that can reason, plan, and act autonomously. Start with simple agents…
1 min read
Agent Observability: Monitoring AI Systems in Production
Observability transforms AI agents from black boxes into understandable systems. Combine metrics, logs, and traces to gain complete visibility into agent…
1 min read
Audit Logging for AI Agents: Complete Activity Tracking
Comprehensive audit logging is essential for AI agents in production. It enables debugging, ensures compliance, and provides the visibility needed to build…
1 min read
Permission Models for AI Agents: Fine-Grained Access Control
Permission models for AI agents must be flexible yet secure. Combine RBAC for broad access patterns with capabilities for fine-grained, time-limited access.
1 min read
Sandboxing AI Agents: Isolation and Containment Strategies
Sandboxing is your last line of defense. Even trusted agents can behave unexpectedly - proper isolation ensures that unexpected behavior doesn't become a…
1 min read
Agentic AI Capabilities: From Chatbots to Autonomous Agents
Agentic capabilities transform AI from a question-answering system into an autonomous problem-solver. The key is combining planning, tools, memory, and…
1 min read
Claude Computer Use Preview: AI That Can Control Your Desktop
Computer Use is a significant step toward truly autonomous AI agents. Use it responsibly with appropriate safety controls.
1 min read
Agent Reliability Patterns: Building Robust AI Systems
Building reliable agents requires investment in error handling, recovery mechanisms, and observability. These patterns form the foundation for production AI…
1 min read
AI Agent Best Practices: Lessons from Production
AI Agent Best Practices: Lessons from Production
1 min read
Multi-Agent Architectures: Collaboration at Scale
Single agents have limits. Multi-agent systems multiply capabilities. Today I'm exploring architectures for agent collaboration.
1 min read
Memory and State Management in AI Agents
AI agents need memory to maintain context across interactions. Today I'm exploring how to implement effective memory systems.
1 min read
File Handling in AI Agents
AI agents often need to work with files - reading documents, processing data, generating outputs. Today I'm exploring safe and effective file handling patterns.
2 min read
Code Execution in AI Agents: Safe and Effective Patterns
Code execution is one of the most powerful capabilities for AI agents - and one of the most dangerous. Today I'm exploring how to implement it safely.
1 min read
Tool Use Patterns for AI Agents
Tools extend what AI agents can do beyond text generation. Today I'm exploring patterns for effective tool use in production agents.
1 min read
Agent Orchestration Patterns for Production
Building single agents is one thing. Orchestrating multiple agents for complex workflows is another. Today I'm exploring production-ready orchestration…
1 min read
Building AI Agents: From Simple to Sophisticated
AI agents are systems that can take actions autonomously to achieve goals. Today I'm exploring how to build agents from simple tool-using assistants to…
1 min read
Azure AI Agent Service Preview: Building Intelligent Agents
Azure AI Agent Service provides: Managed agent runtime No infrastructure to manage Built in tools Code execution, file handling, web search Memory…
7 min read
LangChain, AutoGen, CrewAI or Semantic Kernel? Choosing in January 2024
How LangChain 0.1, AutoGen 0.2, CrewAI 0.1 and Semantic Kernel 1.0 differ in maturity, control and Azure OpenAI fit, and which one I'd pick for what.
6 min read
CrewAI 0.1 on Azure OpenAI: Roles, Tasks and Current Limits
A practical look at CrewAI 0.1.x with Azure OpenAI: how agents, tasks and sequential crews work, what's missing today, and when to choose it.
7 min read
AutoGen 0.2 on Azure OpenAI: Termination, Code Execution and Tools
A practical look at AutoGen 0.2 with Azure OpenAI: wiring the config, stopping runaway conversations, sandboxing generated code and registering tools.
7 min read
When to Split One AI Agent into Several: A Supervisor Pattern
When a single GPT-4 agent stops being reliable, split it into specialists. A framework-free supervisor pattern on Azure OpenAI, with trade-offs and limits.
6 min read
Self-Correcting RAG: Grade Retrieval Before You Answer
How to add retrieval grading, query rewriting, and groundedness checks to RAG on Azure OpenAI and Azure AI Search without tripling latency or cost.
1 min read
Azure OpenAI Assistants API: Enterprise AI Agents
The Azure OpenAI Assistants API — launched in preview on Azure shortly after the OpenAI DevDay announcement in November 2023 — is the stateful AI agent…
1 min read
Tool Use Patterns for AI Agents: Effective Function Design
The most consequential design decision in a function-calling agent isn't the model you choose — it's how you write the tool definitions. The model selects…
1 min read
Building AI Agents: From Chatbots to Autonomous Assistants
Function calling, released last week with the 0613 model versions, gives AI agents a proper foundation — and I've been rebuilding some agent prototypes to…
1 min read
Azure OpenAI Function Calling Patterns: Building Intelligent Agents
Function calling patterns enable sophisticated AI agents. Tomorrow, I will cover building AI agents in more depth.