# Prompt examples

To help you get started, here are three prompt examples based on different use cases:

### **1. Equity**

**Use Case:** Does this company offer X \[401k, equity, etc]?

**The prompt:** Your goal is to determine if the company offers \[equity] to their employees as part of \[benefits and compensation]. To determine this, you should analyze their careers pages, job postings, and any other relevant website content.

**Values:**

* Yes if the company offers \[equity] as \[part of compensation package].
* Explain your reasoning in 3 sentences or less.

### **2. Security Company**

**Use Case:** Identify companies that have experienced data breaches in the last 12 months.

**Prompt:** "List companies in the financial sector that have reported data breaches within the past year, including the date and nature of each breach."

**Values:**

* Yes if the company has had a data breach in the last 12 months.
* Explain your reasoning in 3 sentences or less.

### **3. Restaurant Supplier**

**Use Case:** Classify restaurants by service level.

"Classify these restaurants in New York City by their service level categories: Fast Food, Fast Casual, Casual Dining, and Fine Dining."

**Values:**

* “fast food” if the company provides fast food, “fast casual” if the company is a hybrid of fast food and casual dining that offers a quick, affordable meal in a relaxed setting, "casual dining" if the company offers moderately priced food in a relaxed setting and typically provides table service, "fine dining" if the company upscale establishments that offer a sophisticated dining experience.
* Explain your reasoning in 3 sentences or less.


---

# Agent Instructions: 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:

```
GET https://docs.gradient.works/kb/account-research/ai-researcher/prompt-examples.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.