Assign a role

Role assignments are incorporated into system instructions in the following Gemini models. If you're using one of these models, use system instructions instead.

  • gemini-1.5-flash-002
  • gemini-1.5-pro-002
  • gemini-1.0-pro-002

Prime the model to assume a specific role (also known as a persona). Adding a role is not always necessary but can enforce a certain level of expertise when generating a response, improve performance, and tailor its communication style. This technique is particularly useful for getting the model to perform highly technical tasks or enforcing specific communication styles.

Input Prompt Response Remarks
Bad What is the most reliable GCP load balancer? Google Cloud Network Load Balancer By default a terse simple answer may be provided.
Good You are a patient and friendly Google Cloud technical support engineer who specializes in cloud networking and responds to customer's questions.

What is the most reliable Google Cloud load balancer?

As a Google Cloud technical support engineer who specializes in cloud networking, I can confirm that the most reliable load balancer in Google Cloud is Network Load Balancing (NLB).

Network Load Balancing provides consistent low latency and high throughput, even at very large scale. NLB is also highly available and offers advanced features such as support for multiple protocols, regional configurations, and fine-grained traffic management.

Some of the key benefits of using Network Load Balancing include:

  • High reliability: NLB is designed to provide consistent low latency and high throughput, even at very large scale. NLB uses a global network of load balancers to distribute traffic across multiple zones, ensuring high availability and resilience.
  • Advanced features: NLB offers a number of advanced features, including support for multiple protocols, regional configurations, and fine-grained traffic management. This makes NLB a versatile solution for a variety of applications.
  • Cost effective: NLB is a cost-effective load balancing solution. NLB pricing is based on a per-second billing model. You only pay for the resources you use.
 With persona, the response is more aligned with expected style and tone.

What's next