Skip to main content
Feedback

About AI agents

Discover what AI agents are and how they can accelerate productivity and simplify your integration and automation initiatives.

What is an AI Agent?

AI agents are autonomous or semi-autonomous software systems that achieve a defined goal by observing environments, following instructions, using reasoning, and taking action.

Since AI agents are non-deterministic, they can:

  • Adapt to different contexts and unique or evolving scenarios
  • Generate natural, personalized responses
  • Learn over time (when there is access to memory and feedback)

Agent components

An agent relies on the following components:

  • Goal - The agent goal is a high-level statement that defines the agent’s overall purpose/objective. It provides context and boundaries for how the agent should behave and what tasks it will support. For example, “Help users retrieve order statuses and create support tickets.”

  • Model - A Large Language Model (LLM) powers an agent's reasoning, allowing it to understand natural language inputs, determine intent and context, and generate output in natural language.

  • Temperature/ Personality - Personality settings control the agent’s voice and tone as well as the response and reasoning style.

  • Instructions - Instructions are natural language prompts that guide the Large Language Model (LLM) to achieve a task. It influences how the agent interprets user inputs, how the agent responds, and how the agent behaves when performing a task. Instructions can support conditional logic (“if the user does this, do this”) and can prevent unwanted behaviors and responses (“do not do this”). For example, “If the user cannot provide an order ID, offer to search orders by first and last name.”

  • Tools - Tools are functions that extend an agent’s capabilities and help it achieve results related to a task. For example, an agent could use an API tool to call an API endpoint and retrieve an order status. There are four types of tools you can attach to tasks:

    • API tool - Enables the agent to make REST or SOAP API calls.
    • Integration tool - Enables the agent to run Boomi integrations.
    • Prompt tool - Enables the agent to learn how to respond to a certain input specifically for its assigned task through the detailed prompts and examples provided in the tool.
    • DataHub Query tool - Enables the agent to query a DataHub repository and retrieve data. This tool aligns with the Query Golden Records API endpoint.

  • Guardrails - Guardrails are filters and controls that manage agent behavior. It prevents unsafe and off-topic responses to ensure an agent performs within your rules and guidelines. Guardrails allow you to define topics you prohibit the agent from discussing and define text and regex filters that trigger and prevent the agent from responding.

AI agent component diagram

Why does my business need AI agents?

We’ve moved beyond digital transformation into agentic transformation, where software can understand, reason, and take action in dynamic environments. This shift is reshaping how businesses operate, make decisions, and compete.

With AI agents, business can responsibly build custom, intelligent solutions that simplify complex processes and keep organizations connected, efficient, and competitive.

AI agents can:

  • Increase productivity and save time by allowing teams to develop and deliver faster
  • Streamline data analysis and accelerate decision making
  • Improve accuracy and consistency in repetitive processes that involve variation and require judgment

When do I create an AI agent?

Agentic workflows rely on the AI agent’s reasoning capability to take action and solve problems. Create an AI agent to automate a repeatable process involving decision-making or variation, which simple automation cannot streamline. For example, receiving customer support cases, answering questions, and escalating complex cases to humans.

AI agent examples

For AI agent examples:

  • Explore Agent examples for step-by-step tutorials to build agents from real-world use cases.
  • Refer to Agentic use cases to discover how AI agents can drive business outcomes.
  • Find agent templates in the AI agent template gallery on the Agent Garden home page.
On this Page