by CPI Staff | Oct 12, 2026 | AI Agents, AI Governance & Risk Management, Blog, Microsoft Agent Framework
In this blog post Agent Harness Explained for Building Reliable Microsoft AI Agents we will show you how to move beyond an impressive AI demonstration without giving software uncontrolled access to your business. Many organisations can build an AI chatbot in days, but...
by CPI Staff | Oct 12, 2026 | AI Governance & Risk Management, Blog, MCP Server, Microsoft Agent Framework
In this blog post Microsoft Agent Framework Production Guide for A2A MCP Governance we will explain what the latest releases change for businesses moving AI agents into production, where the new risks sit, and what technology leaders should review now. Many...
by CPI Staff | Oct 12, 2026 | AI Agents, Blog, Microsoft Agent Framework, OpenAI
In this blog post How Compaction Keeps Long-Running AI Agent Workflows on Track we will explain how compaction helps business AI continue complex work without becoming slower, more expensive or increasingly confused as its history grows. This matters because an AI...
by CPI Staff | Oct 12, 2026 | AI Agents, AI Governance & Risk Management, Blog, Microsoft Agent Framework
In this blog post How to Pause and Resume AI Agent Work Without Starting Again we will explain how businesses can interrupt long-running AI tasks, preserve completed work and continue safely when they are ready. Imagine an AI agent reviewing 4,000 supplier records. It...
by CPI Staff | Oct 12, 2026 | AI Agents, AI Governance & Risk Management, Blog, Microsoft Agent Framework
In this blog post How Human Review Makes Resumable AI Agent Workflows Safer for Business we will explain how AI work can pause for a person, preserve its progress and continue safely once a decision is made. This matters because the biggest risk with AI agents is not...
by CPI Staff | Oct 12, 2026 | AI Governance & Risk Management, Blog, Microsoft Agent Framework, Microsoft AI Foundry
In this blog post How to Add Human Approval to Microsoft Foundry Agent Workflows we will explain how to stop a useful AI automation from turning into an expensive or risky mistake without someone checking it first. At a high level, human approval creates a controlled...
