> For the complete documentation index, see [llms.txt](https://angoor-ai.gitbook.io/angoor-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://angoor-ai.gitbook.io/angoor-ai/basics/configuration/tools/gpt-tools.md).

# GPT Tools

AI-powered utilities that leverage language models to process, analyze, and generate content based on your specific business requirements.

## **Creating GPT Tools**

**Step 1:** Click "New" and select "GPT Tool" to initiate creation.

**Step 2:** Define your tool's logic in the Core tab using structured prompts and instructions.

**Step 3:** Configure AI model settings in the Settings tab for optimal performance.

**Step 4:** Connect knowledge bases and forms for enhanced functionality.

**Step 5:** Test thoroughly in the Playground tab before deployment.

<figure><img src="/files/NGaSwI7rqAEcFBmfu8ep" alt=""><figcaption></figcaption></figure>

## GPT Tool Configuration

### **Core Tab**&#x20;

<figure><img src="/files/haHdDC62NcplLLzqUuMx" alt=""><figcaption></figcaption></figure>

#### Prompt Engineering

Write comprehensive instructions in the main prompt area using structured sections like "## Purpose", "## Process", and "## Output" to define your tool's behavior and input/output logic.

#### Knowledge Integration&#x20;

Connect one or multiple knowledge bases using "Refer Knowledge Base" button to provide domain-specific accuracy, with changes automatically reflecting in tool responses.

#### Variable Management

Insert dynamic placeholders using "Refer Variable" for text, numbers, dates, and custom formats that transform during tool execution based on your defined logic.

#### Form Connection

Link forms using "Connect Form" dropdown to structure input/output data with field mapping and validation rules ensuring data integrity.

### **Settings Tab**&#x20;

<figure><img src="/files/dxRAX693FI1rO9S69Ddq" alt=""><figcaption></figcaption></figure>

#### Metadata

Configure tool name, description, and tags for clear identification and organization across your workspace.

#### Model Selection&#x20;

Choose from GPT 4.1, GPT 3.5, or custom models with token capacities of 8K, 16K, 32K, or 100K and Standard or Fast response times.

#### Parameter Tuning&#x20;

Select Creative (0.7-1.0), Balanced (0.4-0.6), Precise (0.1-0.3), or Custom modes to control response variation and consistency.

#### Advanced Parameters

Fine-tune Temperature (0-1) for randomness, Top P for word diversity, and Max Token Limit for response length control.


---

# 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://angoor-ai.gitbook.io/angoor-ai/basics/configuration/tools/gpt-tools.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.