Microsoft is putting AI agents in Teams. Anthropic is offering managed agents with plugins and connectors. Google is doing the same. Every vendor is using slightly different words to describe roughly the same thing: software that can think, plan, and act on your behalf — automatically, inside your business systems. This guide explains what that actually means, in plain English.
Most people's first encounter with AI was a chatbot: you ask a question, it answers, you move on. That's useful, but it's fairly limited. An AI agent is something more ambitious — it's an AI system that can take actions, not just answer questions.
A chatbot is like a very knowledgeable colleague you can ask anything. An AI agent is like a colleague who can actually do things for you — log into your systems, draft documents, send emails, update records — without you supervising every step.
That distinction matters enormously. When an AI is just talking, mistakes are annoying. When an AI is acting, mistakes can be costly.
Every vendor uses slightly different terminology. Here's a glossary that cuts through the noise.
An AI agent provided and maintained by a platform vendor (Microsoft, Anthropic, Google) rather than built in-house. You configure and deploy it; they handle the underlying AI model.
An extension that gives an AI agent access to a specific tool or data source. Think of it like an app you install. The agent uses the plugin to do things it couldn't do on its own.
A pre-built integration that links the AI platform to another system. Similar to a plugin, but often managed at the platform level rather than per-agent.
The component that decides which agents to call, in what order, and what to do with the results. It's the manager of a multi-agent system.
When an AI agent reaches out to an external system (API, database, service) to do something — read data, write data, trigger an action.
A checkpoint where a human must approve or review before the agent continues. Critical for high-stakes actions.
To make this concrete: in 2025, Anthropic announced managed Claude agents with plugins and connectors for financial services. Microsoft is rolling out Copilot agents through Teams and Copilot Studio. Google has Gemini agents in Workspace. These are not demos — they are available to deploy today.
Available through Microsoft 365 (Teams, SharePoint, Outlook). Built with Copilot Studio. Can read and write to Microsoft 365 data, Power Platform, and hundreds of third-party systems via connectors.
Deployed via the Claude API using the Agent SDK. Managed agents can be given plugins (tools) and connectors to specific systems. Anthropic hosts the model; you control the configuration and deployment.
Available through Google Workspace and Vertex AI. Agentspace provides a hub for enterprise agent deployment. Connects to Drive, Gmail, Calendar, and third-party systems.
Every capability is also a risk. An agent that can read your email and take actions is useful — and it's also a very powerful thing to get wrong. The PAI Production Safety Framework (PSF) organises these risks into 8 domains. Here are the ones most relevant to a first agent deployment.
What data is being fed into the agent? Sensitive customer data, financial records, health information — all could be processed by AI models hosted outside your jurisdiction.
Agents can confidently produce wrong answers — hallucinated numbers, wrong names, incorrect calculations. If outputs are acted on automatically, errors propagate.
When an agent does something unexpected, can you find out what happened? Without logging, you're flying blind.
Rushing to deploy without testing failure modes. What happens when the agent gets an unusual input? Does it fail gracefully or do something catastrophic?
Agents that act without any human checkpoint on consequential decisions. Automating the wrong thing at the wrong time.
Your business process now depends on a third-party AI service. What happens if it goes down, changes its pricing, or gets acquired?
These aren't theoretical concerns. The PAI incident database already contains dozens of real cases where automated AI actions caused data exposure, incorrect financial entries, inappropriate communications sent to customers, and system state corruption. The good news: all of these were preventable with the right controls in place before deployment.
You don't need to wait for perfect conditions — but you do need to ask the right questions before you deploy. Here's a quick readiness checklist:
The AIDA examination tests applied PSF knowledge across all eight domains — exactly the gaps and strengths covered in this assessment. 15 minutes. No charge. Ever.