Connect to OpenAI

Use a code-free OpenAI step to analyze text and images, generate content, and give the model built-in tools such as web search, file search, and code interpreter.

​

Before you begin

• In your Next Matter portal, go to Automations library, click Connect in the OpenAI app tile, and enter your OpenAI API key.

​

Analyze or generate text

1. Click Workflows > + Create new… > Create a new workflow and give your workflow a name. If you have a workflow ready, click … > Edit workflow.
2. Click + Add step and select Integrations > OpenAI.
3. Click the step and click Configure integration.
4. Select Process/generate text with AI in OpenAI action.
5. Enter the prompt and select the AI model and the output type.

6. (Optional) If needed, you can tweak the request by providing data in the Advanced AI configuration dropdown.
7. Select the output text as a variable you can refer to later on.
8. Save your changes.

​

Use cases

• You can use the no-code step to, for example, analyze customer emails for the support team, surface the email’s main points, and measure the sentiment.
• You can analyze customer emails to automatically input data into insurance claim forms that customers can review and confirm.

​

Process images

1. Click Workflows > + Create new… > Create a new workflow and give your workflow a name. If you have a workflow ready, click … > Edit workflow.
2. Click + Add step and select Integrations > OpenAI.
3. Click the step and click Configure integration.
4. Select Process images with AI in OpenAI action.

5. Enter the prompt and select the AI model and the output type.
6. Select the data reference to the images uploaded in any of the previous steps. PDF files aren’t supported.
7. (Optional) If needed, you can tweak the request by providing data in the Advanced AI configuration dropdown.
   You can use decimals to set Temperature. In German and other European locales, use a comma (,) instead of a point (.) as the decimal separator.
8. Select the output text as a variable you can refer to later on.
9. Save your changes.

​

Use web search, file search, and code interpreter

Give the model access to OpenAI’s built-in tools when you need up-to-date answers, need it to search files you’ve already indexed with OpenAI, or need it to run code.

1. Click Workflows > + Create new… > Create a new workflow and give your workflow a name. If you have a workflow ready, click … > Edit workflow.
2. Click + Add step and select Integrations > OpenAI.
3. Click the step and click Configure integration.
4. Select Process/generate text with OpenAI Responses API in OpenAI action.
5. Enter the prompt and select the AI model and the output type.
6. In the Tools field, add any of the following:
   • Web Search — lets the model search the web for current information. You can set the search context size and, optionally, a country, region, or city to focus the results.
   • File Search — lets the model search vector stores you’ve already created in OpenAI. Enter the vector store IDs to search, and optionally set a maximum number of results and metadata filters.
   • Code Interpreter — lets the model write and run Python code, for example to analyze data or do calculations. You can set a memory limit for the container that runs the code.
7. (Optional) Use the Files field to attach documents or images by URL as extra context for the model. This is separate from the File Search tool, which searches vector stores instead.
8. (Optional) If needed, you can tweak the request by providing data in the Advanced AI configuration dropdown.
9. Select the output text as a variable you can refer to later on.
10. Save your changes.