AI Steps
Last updated
Was this helpful?
Last updated
Was this helpful?
Relay.app has three kinds of AI actions:
Built-in actions — Common tasks like extraction, summarization, translation, and transcription.
Prompt any model — Flexible steps that can take any input and produce a desired structured output.
— Let AI decide which actions to perform (and how often) based on a set of actions you give it access to
You can learn more about these different types of AI features in Relay.app .
There are two main ways to connect a model to an AI step in Relay.app.
Recommended: Use Relay.app's AI credits: You can use various OpenAI, Google, and Anthropic models via the that come with your plan in Relay.app. This means that you don't need to connect an account with an underlying model provider, connect any API keys, or purchase credits through that model provider. Simply select one of the AI credit model options and start using AI in your workflows.
Advanced: Use direct connection: If you already have an account with OpenAI, Anthropic, or another model provider, and you've already purchased credits there, you can choose to call models directly via those accounts by selecting one of the Connected Models in the dialog below. Note that OpenAI platform credits are separate from ChatGPT Plus subscriptions. Read more about purchasing credits .
AI steps are capable of emitting structured data rather than just plain text, that can then be passed into other automation steps.
When emitting structured data, providing instructions to help the AI know what to extract can be very helpful. When prompting, it can be helpful to know that the date, time and duration formats output by the AI should all be in the ISO 8601 format.
While AI is getting better by the day, it can still be unpredictable. In most cases, if you have a step that is resulting in an error or not producing the output you want, you'll need to adapt your prompt. We'll be adding prompt tips here in the future, but for now you can email support@relay.app for assistance.
Relay.app's built-in Human-in-the-Loop tools make it very easy to ensure that a human first reviews the output of an AI step before the workflow proceeds.
