Get started with Quality AI

Preview

This product or feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. You can process personal data for this product or feature as outlined in the Cloud Data Processing Addendum, subject to the obligations and restrictions described in the agreement under which you access Google Cloud. Pre-GA products and features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

This page walks you through the steps to set up and start using Quality AI.

Prerequisites

The following steps ensure you can access Quality AI:

1. Enable Contact Center AI Insights for your project and ensure you have access to the Contact Center AI Insights API.
2. Enable Dialogflow runtime integration.

Use Quality AI

1. Open Contact Center AI Platform and select your project where Contact Center AI Insights is enabled.
2. Click Insights > Quality AI.

Make a scorecard

You can create different scorecards for different business units.

1. Click Scorecards > + Add scorecard.
2. Click Untitled Scorecard edit and add a scorecard name > Unspecified description edit and add a scorecard description.

3. Click + Add question > Add a question to evaluate agent performance, an abbreviation, and an optional tag. For each question, you can select one of the three tags: business, customer, or compliance.

   Example

   Question: Did the agent understand the customer's needs by asking thoughtful questions throughout the conversation?

   Abbreviation: Thoughtful questions

   Tag: Customer

4. Add instructions to define the interpretation of each answer choice.

   Example

   Instructions:

   Yes: The agent asked thoughtful questions. OR The agent demonstrated active reading skills.

   No: The agent did not ask thoughtful questions. The customer had to repeat themselves multiple times due to the agent's lack of understanding toward the customer's needs. The agent only asked necessary questions, such as their zip code or product name.

   NA: Unable to ask questions. The interaction was for transfer or was a non-sales related interaction.

5. Select an answer type, enter the answer choices and their corresponding scores, and check the box to include N/A. Click + Add answer choice to include additional answer choices and their scores.

   Example

   Answer type: Yes/No

   Answer choice and score: Yes 1, No 0

   check_box Add 'N/A' (not available) as an answer choice. If selected, the question will not be included in the total score calculation.

6. Click Save.

7. Repeat steps 3-6 for each of your questions > Click Next.

Train the model

You train models using training samples, which consist of conversations, associated questions, and expected answers.

1. Click + Add training samples and add the path to your Cloud Storage bucket > Import.
2. Click Begin training to initiate model training > Launch new version.