by CPI Staff | Jul 24, 2026 | AI Agents, AI Governance & Risk Management, Blog, Claude
In this blog post How to Design Human Approval and Audit Controls for Claude Agents we will explain how to stop an AI agent from taking a costly, sensitive or irreversible action without the right person reviewing it first. This matters because a Claude agent can do...
by CPI Staff | Jul 24, 2026 | AI Agents, Azure Security, Blog, Microsoft AI Foundry
In this blog post Designing Private Network Access for Microsoft Foundry Agents we will explain how to keep AI traffic private, control what agents can reach and avoid creating a hidden security gap. The problem often appears after a successful pilot. An AI agent...
by CPI Staff | Jul 24, 2026 | AI Agents, AI for Business & AI Strategy, AI Governance & Risk Management, Blog
In this blog post Why Business AI Agents Should Follow the Principle of Least Agency we will explain how to give an AI agent enough freedom to deliver value without allowing it to create unnecessary cost, security exposure or operational risk. The principle is simple....
by CPI Staff | Jul 24, 2026 | AI for Business & AI Strategy, AI Vendor Selection & Implementation, Application Development, Blog
In this blog post What a Senior Forward Deployed Engineer Does for Your Business we will explain why this role is becoming important, what the engineer actually does, and how to decide whether your organisation needs one. Many businesses have an AI prototype that...
by CPI Staff | Jul 24, 2026 | AI Governance & Risk Management, Blog, Cybersecurity Strategy & Governance, Microsoft 365 Security
In this blog post The Microsoft Security and AI Checklist Every SMB Should Review we will explain what technology leaders should check before security gaps, uncontrolled AI use, and overlapping licences start costing the business. Most SMBs already own useful...
by CPI Staff | Jul 24, 2026 | AI Agents, Blog, Microsoft AI Foundry, VS Code
In this blog post Build AI Agents Faster with Microsoft Foundry Toolkit in VS Code we will explain how technology teams can move from an AI idea to a working business agent with less setup, fewer disconnected tools and better control. Many organisations are not short...
