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

# Task API: Market Research Reports

> Generate comprehensive market research reports.

```python market_research.py theme={null}
"""
Task API — Market Research Reports
==================================

Generate comprehensive market research reports.

USE CASE:
- Industry analysis and trends
- Competitive landscape
- Market sizing
- Key players and their positioning

The Task API synthesizes information from multiple sources
into a cohesive report with citations.

Prerequisites:
- pip install parallel-web
- export PARALLEL_API_KEY=<your-api-key>
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.parallel import ParallelTools

# =============================================================================
# MARKET RESEARCH CONFIGURATION
# =============================================================================
# Use "text" schema for long-form reports with citations.
# Use "pro" processor for deeper analysis.

research_tools = ParallelTools(
    enable_search=False,
    enable_extract=False,
    enable_task=True,
    default_processor="base",
    default_output_schema={"type": "text"},
)

# =============================================================================
# RESEARCH AGENT
# =============================================================================

research_agent = Agent(
    model=OpenAIResponses(id="gpt-5.4"),
    tools=[research_tools],
    markdown=True,
    instructions="""You are a market research analyst.
    Use create_task() to research industries and markets.
    Provide comprehensive analysis with data points and trends.""",
)

# =============================================================================
# STRUCTURED MARKET REPORT
# =============================================================================
# For structured market data, use JSON schema.

structured_research_tools = ParallelTools(
    enable_search=False,
    enable_extract=False,
    enable_task=True,
    default_processor="base",
    default_output_schema={
        "type": "json",
        "json_schema": {
            "type": "object",
            "properties": {
                "industry": {"type": "string"},
                "market_size": {"type": "string"},
                "growth_rate": {"type": "string"},
                "key_trends": {
                    "type": "array",
                    "items": {"type": "string"},
                },
                "major_players": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "company": {"type": "string"},
                            "market_share": {"type": "string"},
                            "positioning": {"type": "string"},
                        },
                    },
                },
                "challenges": {
                    "type": "array",
                    "items": {"type": "string"},
                },
                "opportunities": {
                    "type": "array",
                    "items": {"type": "string"},
                },
            },
            "required": ["industry"],
        },
    },
)

structured_research_agent = Agent(
    model=OpenAIResponses(id="gpt-5.4"),
    tools=[structured_research_tools],
    markdown=True,
)

# =============================================================================
# RUN
# =============================================================================
if __name__ == "__main__":
    # Generate a market research report
    research_agent.print_response(
        "Create a market research report on the AI infrastructure industry. "
        "Include market size, key players, trends, and growth projections.",
        stream=True,
    )
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai parallel-web
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      export PARALLEL_API_KEY="your_parallel_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      $Env:PARALLEL_API_KEY="your_parallel_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `market_research.py`, then run:

    ```bash theme={null}
    python market_research.py
    ```
  </Step>
</Steps>

Full source: [cookbook/91\_tools/parallel/market\_research.py](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/parallel/market_research.py)