- Getting started
- Prerequisites
- Building agents
Agents user guide
Prompt arguments
Prompt arguments allow an agent to take in information about a business case and return a result, just as activities or processes do. This means you can pass information from a trigger in Orchestrator or use the output of an agent to launch another business process.
In order for input arguments to be visible to an agent, you must:
- Create arguments in the Arguments tab. This lets the agent know that it needs to gather these values, but doesn't pass it as part of the prompt.
- Reference the arguments in the
user prompt using the
{{argumentName}}syntax. This performs a substitution of the argument value into the prompt so that the agent has it in its context window.
The agent always uses the user prompt, but it only sees arguments if they are explicitly mentioned. Refer to the examples for System prompts and User prompts to learn how to use arguments in an actual prompt.
You must provide a description for both input and output arguments. An accurate description ensures the agent can use an argument effectively.
EXAMPLE_ARG, it should be substituted using the following
syntax: {{EXAMPLE_ARG}}.
Use the Input schema and Output schema tabs to define your input and output arguments.
For each argument, you can configure the name, type, description, and whether it is required or not.
Enable the Edit raw schema toggle button to define your arguments in JSON format.
The following image shows how a list of input arguments for a Generate Email agent:
The following image shows the raw schema of the same input arguments, when you enable Edit raw schema:
