> 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.