For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
You create AI requests to interact with AI models. You can choose any OpenAI-compatible model, whether it’s from OpenAI, Anthropic, Google, or an alternative provider such as HuggingFace. Use your requests to experiment, test, and evaluate different AI models, including fine-tuned, self-hosted, and local ones. Choose the model that best fits your security requirements, budget, and workflow.
Open the Prompt tab, enter your user prompt, and (optional) enter your system prompt.
Click Send.
Postman adds your Message (user prompt) and the Response to the open conversation. You can use the steps in the following section to save your new AI request to a collection.
Save your new AI request
If you don’t have any multi-protocol collections in your workspace, Postman opens a save request dialog that asks you for a request and collection name. Otherwise, Postman displays more options, such as the option to add your new AI request to an existing collection.
To save your new AI request, do the following:
Click Save. Postman opens a save request dialog.
Name your new AI request.
If you don’t have any multi-protocol collections in your workspace, name your collection and skip to the last step.
(Optional) Click Add description and describe your new AI request.
To save your new request to an existing collection, select a collection. To save your request to an existing folder, select a folder. If you want to search for a collection or folder, enter your search term in the search box.
If you want to create a new collection, click New Collection, name your collection, and click Create. If you want to create a new folder, click New Folder, name your folder, and click Create.