A preview release of Retool Agents is currently available to self-hosted organizations for deployment into a non-production environment. This preview release is intended to allow customers to preview and create proof-of-concepts that show how agents may work in their environment.

As Retool is continuously working to develop and improve Retool Agents to meet the high standards required for production environments, this preview release is not intended for production use and this build should not be deployed in an existing Retool installation or deployment. Retool recommends that self-hosted organizations create a new deployment in a private network alongside resources to which you intend to connect. Retool reserves the right to make changes to the agents preview without notification.

Retool Agents makes it simple for builders to automate work using large-language models (LLMs) by creating agents. Agents are systems that can complete or delegate tasks based on LLM reasoning.

Agents call tools—for example, workflows, functions, or other agents—to gather information and complete or delegate actions. When invoked, an agent:

1. Receives a task, or input, as natural language. Tasks are provided as input to agents via written instructions.
2. Uses an LLM to decide whether to respond to the input, get more information, or take action in another system.
3. Provides the result of the tool call back to the LLM, and the LLM reasons in an open-ended cycle called an agentic loop without a pre-defined stopping point.
4. Finally, the agent responds to your original message or question once it reaches a conclusion.

You can invoke an agent using any of the following trigger methods:

• The built-in chat experience in Retool Agents.
• Sending an email to the agent.
• The Agent Chat component in apps.
• The Invoke Agent block in workflows.

You can then test, deploy, evaluate, and monitor your agent directly from Retool.