AI in ERP

Microsoft has just introduced Toolboxes in MS Foundry - a managed, versioned bundle of curated tools that any MCP‑compatible agent can consume through a single endpoint, removing per‑agent wiring, centralizing auth, and enabling safer rollouts What is a Toolbox in MS Foundry Toolboxes in MS Foundry lets you define a reusable set of tools once (APIs, MCP servers, connectors, skills, flows), configure authentication centrally, and expose them through a single MCP‑compatible endpoint that agents discover and call at runtime. This removes duplicated integration code and secret sprawl across agents. Read more on toolboxes here . How do Toolboxes Work? Toolboxes are a named, versioned collection of tools you manage inside Microsoft Foundry and expose through a single MCP‑compatible endpoint. Each toolbox groups tools by namespace; tools can be APIs, MCP servers, connectors, skills, or flows. At runtime an agent points to the toolbox endpoint, discovers available tools, and invokes them. Fo...

AI tools and agents are no longer optional. They’ve become embedded in how employees and developers work every day. The question is no longer if your teams will use them- it’s how safely they’ll do it. [Image reference: AI Tools: Navigating the New Professional Landscape by Vicki Reyzelman] The Risk of "Free" AI Tools Organizations must recognize the inherent dangers of allowing employees to rely on publicly available AI platforms such as ChatGPT or Google Gemini. Under the pressure of deadlines and workload, employees may inadvertently copy and paste confidential information into these tools. Proprietary strategies, source code, and intellectual property can be transmitted outside the organization’s secure environment. These disclosures occur silently, without alerts or oversight, leaving leadership unaware until the damage is irreversible. The risk of loss of control is Permanent. Once confidential information enters a public AI model, it cannot be retrieved or contained. C...

Getting started with Microsoft 365 Copilot agents can transform how your organization leverages AI to streamline workflows, enhance productivity, and empower employees to build intelligent solutions. This blog outlines a phased approach—starting with forming a champion team, training employees, and scaling deployment—to help your organization confidently adopt Copilot Studio’s Agent Builder.  To start empowering employees to create and manage Microsoft 365 Copilot agents securely at scale, it is recommended that a three-phase approach is taken:  Form an "agent adoption champion" team within IT and try out Agent Builder. Train employees to build agents with Agent Builder. Provide selected employees with access to Agent Builder and set up pay-go meters.  Phase I – Form a team Step 1: Create an "agent adoption champion" team  Select a group of early adopters (your "champion team”) to explore building agents using Microsoft Copilot Studio Agent Builder in Microsoft...