A conversational agent action step executes a specific agent action within the system. The agent action can be either one of the built-in actions that have been carefully prepared by the Prospera team, or it can be a custom defined action which executes another smart-chain.
| Note |
|---|
Note that this Step does not record the action you selected into the conversation history, except if you are executing a |
Options
| The module ID of the action that needs to get executed |
| The action ID of the action that needs to get executed |
| The parameters to be used with the action, which are usually auto-generated by an LLM to match the schema provided for the action parameters. |
| Custom actions to include in the tool selection. These must be provided with a smart_chain_binding_name that indicates which smart chain to execute for the action. The 'text' field on the output from the smart-chain will be used as the action result. |
Output
| The module ID of the action that was selected | True or false on whether this action should be followed up by executing another action. Usually this is the case with tool actions because you want the agent to follow up by sending a message. |
| This is an ActionResult object that contains all of the details of the action that was selected.executed | |
| The parameters that the LLM generated for the action. | This will match the schema provided for the action parameters. |
| The raw text of the prompt that was sent up to the LLM provider. | |
| If the selected action includes text, such as a message send, then this is text of the response to be said back to the user. Otherwise blankcontain the raw text of the action result |
Properties
type | system |
needs conversation | true |
uses content template | true |
uses options template | true |
customizable output schema | false |