---
title: GenAI quickstart
description: A high-level overview of steps for using DataRobo GenAI with or without your own data.
section_name: Generative AI
maturity: public-preview
platform: cloud-only

---

# GenAI quickstart {: #genai-quickstart }

With DataRobot GenAI, you can generate text content using a variety of pre-trained large language models (LLMs). Or, the content can be tailored to your domain-specific data by building vector databases and leveraging them in the LLM prompts. The following describes, at a high level and with links to complete documentation, the basic steps for the GenAI workflow.

1. In Workbench, [create a Use Case](wb-build-usecase#create) and add a playground via the **Playgrounds** tab or the **Add** dropdown:

	![](images/playground-1.png)

2. Select an LLM from the [configuration settings](playground#set-the-configuration) dropdown to serve as the base model.

	![](images/playground-3.png)

3. Optionally, modify configuration settings and/or add a system prompt.

	![](images/playground-4.png)

4. To tailor results using domain-specific data, select an existing [vector database](vector-dbs).

5. Send a prompt. For example: `Write a Python program to run DataRobot Autopilot`.

	![](images/playground-9.png)


6. Because the LLM blueprint is history-aware, optionally follow-up with additional prompts to continue the "discussion."

7. Save the draft as an LLM blueprint or make changes:

	![](images/playground-6.png)

8. If you built more than one LLM blueprint in your playground, use the [**Comparison** tab](compare-llm) to compare them side-by-side.

9. When satisfied with the results of your blueprint, save it and optionally register it so that you can [deploy it to production](deploy-llm).

	![](images/playground-7.png)
