Overview

Build your own agents with this starter app, which comes with all components of Mendix Agents Kit to help you build  smart, agentic AI apps with Mendix.

The Agent Builder comes with a template for a conversational support agent (MyFirstSupportAgent) which is grounded in private knowledge like static reference guides and can take advantage of live data in the app, like tickets. It serves as a practical example of how to leverage the capabilities of platform-supported modules in a unified use case, providing a solid foundation to explore and kickstart the implementation of your own agent.

• Use any of the supported connectors to leverage a variety of large language models in your agent from OpenAI, Amazon Bedrock, Mendix Cloud or Bring Your Own.
• Take advantage of all the capabilities of Conversational UI, Prompt Management and the GenAI Commons and Agent Commons modules. Agents created with the Agent Builder are fully integrated & compatible with these components.

Explore the full potential of generative and agentic AI in your Mendix applications with this starter app template and start building today!

Contact Us

For support and questions, feel free to reach out via email genai-components-feedback@mendix.com or Community Slack.

Documentation

Introduction

This starter app contains Agent Commons and all other dependencies needed to create agents. It is set up with a Support Agent template to show how it works. It allows developers and prompt engineers to collaborate and build agentic systems.

Try out the Support Agent

Run the app (locally or in the cloud). There are two user roles:

- admininstator: set up the technical connections to LLMs and knowledge bases. Define and test Agents and app, knowledge base and chat interactions.

- user: try out the end-user chat for the defined Agent which is grounded in data and autonomously performs in-app actions while keeping the human in the loop.

Define Agents

1. Run the app (locally or in the cloud).
2. Use the demo user switcher to login as demo_administrator. Create and edit agents at runtime. Write the prompts, use variable placeholders, add microflows as tools and connect knowledge bases to define the tasks and capabilities of the agents.
3. Configure the deployed model (LLM) that the agent should use, and connect the agent to it.
4. Create various versions of the agents and test in an isolated setup to rapidly iterate, compare and evaluate the agentic behavior
5. Set a version as "in use" to allow it to be called from the actual logic in the app.
6. Use the user switcher to login as a demo_user account and try out the agent in the app!