Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window.

Support call next steps

Summarize actions taken during a custom support call and agent next steps.

You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly.

For an example of using the Vertex AI API, see Quickstart using the Vertex AI API.
To view this sample in the Cloud console: Go to Google Cloud console

Prompt Freeform

Considering the conversation below, what are the pending actions by the Agent.

Agent: Thank you for calling Google Cloud support. How may I assist you today?

Customer: Hi, I'm trying to create a Google Cloud account and use the available credits, but I'm not sure how to get started.

Agent: Sure, I'd be happy to assist you with that. Have you already created a Google account?

Customer: Yes, I have.

Agent: Great. You can start by going to the Google Cloud website and clicking on the "Get Started for Free" button.

Customer: Okay, I see that.

Agent: Once you click on that, you'll be prompted to create a new project. You can give your project a name and then select your preferred billing account. If you don't have a billing account set up yet, you'll need to create one before you can proceed.

Customer: Alright, I think I can do that.

Agent: After you've created your project and selected your billing account, you can click on the "Activate" button to activate your free trial credits. Once you've done that, you'll be able to start using the Google Cloud services.

Customer: That sounds straightforward enough, I can do that by myself. Is there anything else I should know?

Agent: Yes, just be sure to keep an eye on your usage during your free trial period. Once your credits are used up, you'll start being charged for any additional usage. But don't worry, you'll receive notifications when you're approaching your credit limit.

Customer: I also want to test BigQuery. Can you give me some advice on how to use it?

Google Cloud Agent: Of course! BigQuery is a powerful tool for analyzing large datasets. If you're new to BigQuery, I'd recommend starting with some of our online documentation and tutorials. You can find these on the BigQuery website, or we can engage a specialist who can guide you through the process. Would you like me to connect you with a specialist?

Customer: Yes, please.

Agent: Okay, I'll connect you with a specialist who can help you get started with BigQuery.

Response

Pending Actions for the Agent:

Connect the customer with a BigQuery specialist: The agent offered to connect the customer with a specialist to help them get started with BigQuery. This connection needs to be facilitated.
(Potentially) Follow up: Depending on the support structure and protocols, the agent may need to follow up with the customer after a certain period to ensure their issue was resolved and they received the necessary assistance with BigQuery.

Model:	gemini-1.5-pro-preview-0409
Temperature:	0.2
Max output tokens:	256
TopK:	40
TopP:	0.8