Select “Yes” to [stop this Zap step](https://help.zapier.com/hc/en-us/articles/20505304170637-Review-Zap-run-statuses#h_01HD20969HPZ01ENM30NQR79X5) if the app returns an error and enable automatic authentication refresh. Select “No” to run the Zap step regardless of errors. Learn more about [API Request action error handling](https://help.zapier.com/hc/en-us/articles/12899473501453#h_01JKRBY68EDXBB1V817DSTRZ0N).

Requests can only be made to domains associated by this application. Read more about [API Request Setup](https://help.zapier.com/hc/en-us/articles/12899607716493).

Any parameters added to a URL will be URL-encoded and appended to the request URL to pass additional data to the API request.

These headers and values will be applied to the request in addition to any headers created as part of authentication. Authentication headers are added automatically.

Zapier will pass this along raw. If you would like to provide complex JSON, try a "Code by Zapier" step to build the structure and pass it along here. For example, `{"foo": "bar"}` is perfectly valid.

Jira Service Management is help desk software that enables support agents to receive, track, manage and resolve requests from help seekers.

Jira Service Management

Provide system-level instructions to guide the model behavior. These instructions help set the context and constraints for how the model should respond.

The most recent message the chatbot responds to.

If provided, this unique value will allow the assistant to continue a conversation from previous messages. Use something that won't change over the course of a conversation (like a user's email address). If blank, the assistant will not remember this conversation going forward.

Controls the randomness of the output. Values can range from [0.0,1.0], inclusive. A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model.

The maximum cumulative probability of tokens to consider when sampling. 

The maximum number of tokens to consider when sampling. 

The set of character sequences (up to 5) that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response.

When testing the action, it will run for 50 seconds. If the entire response is not available, the `was_cancelled` output field will be `true`.

The model to use for generating content. Using the Gemini model(`gemini-pro`) is recommended for most users

Writing a good prompt is important. Start by creating a clear goal & ask a specific question. Make sure the prompt is well structured & provides enough context to generate a useful response.

The maximum number of tokens to use for the response. Max Output Tokens depends on the model. You can find info about the max output tokens for each model in the [Models](https://ai.google.dev/gemini-api/docs/models) section of the Gemini API docs.

Google AI Studio is a fast, easy way to start prototyping generative AI ideas using Google's Gemini model.

Google AI Studio (Gemini)

When a new request arises in Jira Service Management, kick off an immediate conversation in Google AI Studio (Gemini). With this workflow, handle incoming queries or issues promptly, ensuring a streamlined response system. Enhance your customer service strategy and keep your team on the same page effortlessly.

Google AI Studio (Gemini) + Jira Service Management

Initiate conversations in Google AI Studio (Gemini) for new requests in Jira Service Management

Supported triggers and actions

New Request

Create Request

Conversation

Updated Request

API Request (Beta)

Send Prompt

About Google AI Studio (Gemini)

Related categories

About Jira Service Management

Related categories