Dialogue evaluation

This action allows you to send the client a link for quality evaluation at the appropriate moment in the conversation.

Configuration

1. Go to the "Workflows" tab and then click the "Add" button.

1. Select the "Dialogue evaluation" action.

1. Go to step configuration.

Two evaluation options are available:

Like/Dislike

Star rating from 1 to 5

Select the option that suits you best.

Specify the function name and its description.

The function name should reflect the action it will perform. The description helps the agent understand the exact purpose of the function. These two fields enable the agent to use the configured action more reliably. Avoid names that do not reflect the function’s meaning and unclear descriptions.

In the agent’s main instructions, it is mandatory to include a line in the following format after describing the conditions for calling the function:

Call the evaluation_request function and return its result to the user.

An alternative way to use the workflow

Call an action via follow-up:

We select generation by an existing bot and write the generation instructions:

Ask the client to rate the quality of the conversation, invoke the dialogue_evaluation function, and send the result of this function to the user in the chat, unpacking the {rate} variable.

Additionally, you can write an LLM instruction to check the trigger conditions before invoking the follow-up.

For example, you can write a code so that the dialogue evaluation request is not sent if the client has been negative or aggressive in the dialogue:

If the client showed aggression or obvious dissatisfaction during the dialogue, then Return false Otherwise, return true EndIf

Evaluation result

You can see the evaluation result in your personal account in the corresponding dialogue.