Boomi Agent Designer
Boomi Agent Designer is a low-code, user-friendly interface for creating goal-driven generative AI agents tailored to your business needs. You can also build and manage agents programmatically using the Agent Garden REST APIs, enabling integration with CI/CD pipelines and automation frameworks. Custom agents accelerate automation and productivity within your organization by carrying out complex tasks using a combination of natural language and tools like APIs and Boomi integrations. With built-in guardrails, you can seamlessly connect the agents and tools to trusted data and ensure responsible development.
AI agents are software components that have a defined objective and personality that guide their actions and decision-making processes. Refer to About AI agents to learn more about what AI agents are, how they can benefit your organization, and when to create an AI agent.
For examples of AI agents, explore the AI agent template gallery and the Boomi Marketplace section on the Agent Garden home page.
The Agent Designer facilitates the Design phase of Agent Management, allowing you to create custom AI solutions you can orchestrate in the Agent Garden and govern in the Agent Control Tower.
Benefits
Agent Designer benefits your organization by:
Agent Designer benefits your organization by:
- Accelerating AI agent deployment with an intuitive, low-code interface or via REST APIs
- Supporting scalable, reusable agent designs through YAML-based sharing (and programmatic management)
- Ensuring safe AI interactions with built-in and customizable guardrails
Use cases
The Agent Designer lets your organization automate business workflows, providing solutions that free up resources for more complex, non-repeatable tasks. Refer to Agentic use cases to discover how AI agents can enhance your organization's workflows.
Prerequisites
To create, edit, and deploy agents and tools, you must have one of the following roles:
- Agent Garden Administrator
- Agent Garden Developer
- A custom role with privileges (Agent Garden Access, Agent Create, Agent Edit, Agent Feedback Submit, Agent Garden Feedback View)
Read Agent Garden for details on adding roles and setting up custom privileges.
Important considerations
- Agents built in the Agent Designer can respond with text, images, and chart visualizations in the Agent Garden's conversational experience. Image links also appear in agent responses in the Message step from processes using Agent step. Videos are currently not supported.
- If your agent performs only simple tasks, such as sentiment analysis, summarization, and data formatting, turn on Fast mode to improve the AI processing speed in the agent's Profile configuration.
- If your agent requires deep step-by-step analysis and reasoning, turn on Extended Thinking. Keep in mind that this setting increases latency. Refer to Choosing an LLM model setting to learn more.
- The Boomi Agent Designer employs a framework that selects the most suitable model for a given function, such as reasoning, summarization, and guardrails. It uses LLMs via Amazon Bedrock's managed service.
How do I access Agent Designer?
Agent Designer is included in the Agentstudio Base edition, which is a part of all Boomi Enterprise Platform editions.
You’ll receive a notification when you reach usage limitations. To expand usage or add additional capabilities and functionality, contact your Boomi account representative.
Navigate to the AI icon in the platform, then click Agent Garden to access the Agent Designer, Agents, and Tools screens.
You can also manage agents and tools via the Agent Garden REST APIs. This enables automated agent creation, bulk tool provisioning, and integration with your development workflows.
Agent components
An AI Agent has several components that guide its behavior and functionality. Refer to AI Agent components for details.
Agent building process
There are four main steps to building agents. Refer to Building an agent to learn more about how to build agents.
Identify tools
Before building an agent, identify which tools or capabilities the AI agent needs to perform its goal. For example, if the agent’s goal is to provide a weather forecast, you’ll need to create a tool that retrieves weather forecast data from a weather API. Create tools manually in Agent Designer or programmatically via the Agent Garden APIs. After you create a tool, you can attach it to multiple agents you build.
Build the agent
After creating tools, you can create your agent in the Agent Designer either manually, from a template, or with AI assistance. Define the agent's goal, tasks, and instructions, and attach tools to the tasks the agent performs. To ground your agent in your organization's knowledge, attach Meta Hub business glossaries or Knowledge Hub knowledge bases to agent tasks so the agent can accurately interpret your organization's terminology and data. Set up guardrails to ensure your agent's responses are safe, compliant, and secure.
Test the agent
Test your agent responses in the Test Agent section available on the right-hand side of the Designer interface after attaching tools and configuring your agent settings. The trace shows you the agent’s reasoning and allows you to identify issues. You can make changes to your agent and test further until your agent is behaving correctly.
Package and deploy the agent
Before you deploy agents, ensure you've linked your regional runtime cloud to an environment. This provides your agent with a location to run. Refer to Linking an agent cloud to an environment for a step-by-step tutorial.
After testing an agent in a regional test cloud, create a package to capture a versioned snapshot of your current agent settings. Agentstudio automatically applies a version number to each agent package. Refer to Packaging and deploying an agent to learn more.
You can deploy your packaged agent to one or more environments. After deployment, users can interact with it via the chat interface. You can also add the agent to an agentic workflow in Integration.
Deployment can be performed via the Agent Garden UI or automated using the Agent Garden REST APIs, enabling CI/CD integration and multi-environment promotion.
If you need to keep agent execution inside your own infrastructure, you can deploy an agent to a self-hosted Flex runtime instead of a Boomi-managed runtime cloud. This is an Early Access feature. Sign up for Early Access to get started, and refer to Using your own models with agents and Deploying an agent to a Flex runtime to learn more.
You can edit your agent configuration without affecting active deployments. When you are ready to release agent changes, deploy a new package version to replace the currently deployed one.
Embedding agents in your applications
The Boomi Agentstudio Embed Kit allows you to embed agents you create in Agentstudio directly into your own applications. Get started with the GitHub repository and explore the Boomi Embedded documentation.
MCP (Model Context Protocol) support
Create agents that can discover and invoke external tools using MCP, enabling seamless integration, consistent interoperability, and scalable automation across diverse systems. Explore the following topics to learn more:
