> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Deep Research CLI

> CLI commands for deep research in PraisonAI TypeScript

The `praisonai-ts` CLI provides the `research` command for comprehensive research.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    User([User]) --> CLI[CLI]
    CLI --> Research[Research]

    classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef tool fill:#189AB4,stroke:#7C90A0,color:#fff

    class Research agent
    class User,CLI tool
    classDef agent fill:#8B0000,color:#fff
    classDef tool fill:#189AB4,color:#fff

```

## Quick Start

**1. Simple Usage**

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai-ts research "What are the latest AI trends?"
```

**2. With Configuration**

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai-ts research "TypeScript best practices" --depth 5 --json
```

***

## Basic Research

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Research a topic
praisonai-ts research "What are the latest AI trends?"

# Research with depth control
praisonai-ts research "TypeScript best practices" --depth 5

# Limit sources
praisonai-ts research "Machine learning" --max-sources 10

# Get JSON output
praisonai-ts research "AI history" --json
```

**Example Output:**

```json theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
{
  "success": true,
  "data": {
    "answer": "The latest AI trends include...",
    "citations": [
      { "title": "AI Research Paper", "url": "https://..." }
    ],
    "reasoning": [...],
    "confidence": 0.85
  }
}
```

## Research Options

| Option | Description |
| - | - |
| `--depth` | Research depth (iterations) |
| `--max-sources` | Maximum sources to use |
| `--verbose` | Enable verbose output |

## SDK Usage

For programmatic research:

```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import { DeepResearchAgent } from 'praisonai';

const agent = new DeepResearchAgent({
  llm: 'openai/gpt-4o-mini',
  maxIterations: 5
});

const result = await agent.research('What is machine learning?');
console.log('Answer:', result.answer);
console.log('Confidence:', result.confidence);
console.log('Citations:', result.citations.length);
```

For more details, see the [Deep Research SDK documentation](https://praison.ai/docs/js/deep-research.md).

## Related

> [card] [Deep Research](https://praison.ai/docs/js/deep-research.md)
>
> SDK research agent

> [card] [Citations](https://praison.ai/docs/js/citations.md)
>
> Source tracking


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.