AI Agents

Overview

AI agents let you automate complex, goal-driven processes. AI agents reason through decisions, act on your data, and trigger workflows automatically so your teams can focus on higher-value work.

Each AI agent combines a written prompt with reusable tools that connect to your data fabric and processes. Together, these components allow agents to make dynamic, context-aware decisions across your applications.

Use AI agents to:

• Automate flexible, multi-step goals.
• Test and monitor other AI agents to ensure reliable performance.
• Connect AI agents to your enterprise data and documents.
• Embed AI agents in workflows using the Execute AI Agent smart service.
• Engage end users through conversational virtual assistants.

How it works

An AI agent is a smart, configurable design object that can:

• Understand your goals through a natural language prompt.
• Interact with your data and systems using tools.
• Perform actions such as routing cases, updating records, or starting processes.

You define the goal and provide tools that the AI agent can use to complete its task. How you deploy the agent depends on its type:

• Process agents run inside a process model using the Execute AI Agent smart service. The agent interprets your prompt, selects the appropriate tools, and executes each step automatically.
• Chat agents run inside an interface using the agent chat component. End users interact with the chat agent through a conversational interface, and the agent responds in real time.

You select the agent type when you create the agent. For more details, see Agent types.

Why use AI agents

AI agents are best suited for scenarios that require adaptable, goal-driven automation rather than fixed, rule-based logic.

Common use cases include:

• Automating case triage and resolution.
• Interpreting unstructured requests or documents.
• Assigning work dynamically based on context.
• Combining AI reasoning with optional human oversight.
• Providing real-time conversational guidance to end users.

By using AI agents, you can scale automation beyond static workflows and give your applications the ability to reason through complex tasks.

Learn more

The following pages explain how to build, configure, and manage AI agents.

Page	Description
About AI agents	Learn what AI agents are, how they work, and when to use them.
Interface elements	Explore the tabs and layout of the AI agent screen.
Create and configure an AI agent	Step-by-step instructions for creating a new AI agent.
Monitor AI agents	Learn how to track AI agent performance over time.
Use AI agents in a process	Run process agents from a process model using the Execute AI Agent smart service.
Add a chat agent to an interface	Embed a chat agent in an interface using the agent chat component.
Conversation persistence for chat agents	Learn how chat agent conversations are stored and resumed across sessions.
Best practices for designing AI agents	Get guidance for writing effective prompts and defining tools.
AI agent reference	Review agent types, data connection details, and technical limitations.
Use cases	Explore examples of how to apply AI agents in real-world scenarios.
AI Agents FAQ	Find quick answers to common questions about building and running AI agents.

Feedback