> For the complete documentation index, see [llms.txt](https://docs.paradime.io/app-help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.paradime.io/app-help/products/dino-ai/copilot/use-cases/researching-with-perplexity.md).

# Researching with Perplexity

Access the latest technical information, best practices, and examples to improve your analytics engineering.

Staying up-to-date with rapidly evolving technologies and implementing best practices in your project can be challenging. DinoAI can search the web for current information and examples, and help you implement the findings directly in your project.

### Example Prompt

> *I want to implement unit tests in my dbt project. Can you find me examples of how to configure these?*

<figure><img src="/files/ZihNSqjetnX6a5hnKCt7" alt=""><figcaption></figcaption></figure>

***

### Step-by-Step Instructions

1. **Open DinoAI** by clicking the DinoAI icon (🪄) in the right panel
2. **Select the** [**Perplexity tool**](/app-help/documentation/dino-ai/tools-and-features/perplexity-tool.md) from the tools menu or dropdown
3. **Formulate a clear prompt**
4. **Review the response** with cited sources
5. **Optional*****:*** Ask follow-up questions to get more specific information

{% @arcade/embed url="<https://app.arcade.software/share/U7l4NdOK3UZmcfK1o4SR>" flowId="U7l4NdOK3UZmcfK1o4SR" %}

***

### How It Works

After you enter your prompt:

1. DinoAI generates a search query based on your request
2. It searches the web using Perplexity AI to find relevant, up-to-date information
3. It analyzes and synthesizes the search results into a coherent response
4. It provides citations and references to the original sources
5. If configured, DinoAI follows your [.dinorules](/app-help/documentation/dino-ai/dino-rules.md) preferences when generating recommendations

{% hint style="info" %}
**Note**: When researching technical topics, being specific about your use case helps DinoAI provide more relevant information. For example, mention your data warehouse type or project structure when asking about optimizations.
{% endhint %}

***

### Key Benefits

* **Up-to-date Information**: Access the latest documentation and community discussions
* **Verified Sources**: Get information with proper citations
* **Implementation Guidance**: Receive specific code examples relevant to your query
* **Continuous Learning**: Stay current with evolving best practices
* **Reduced Research Time**: Get answers faster than manual web searching


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.paradime.io/app-help/products/dino-ai/copilot/use-cases/researching-with-perplexity.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.