Parallel Examples
Task API: Company Data Enrichment
Enrich CRM records or company databases with web intelligence.
"""
Task API — Company Data Enrichment
==================================
Enrich CRM records or company databases with web intelligence.
USE CASE:
You have a list of company names. You want to add:
- Funding information
- Employee count
- Key executives
- Recent news
The Task API researches each company and returns structured data
that matches your schema.
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
# =============================================================================
# COMPANY ENRICHMENT SCHEMA
# =============================================================================
# Define exactly what fields you want for each company.
enrichment_tools = ParallelTools(
enable_search=False,
enable_extract=False,
enable_task=True,
default_processor="base",
default_output_schema={
"type": "json",
"json_schema": {
"type": "object",
"properties": {
"company_name": {"type": "string"},
"website": {"type": "string"},
"founding_year": {"type": "string"},
"headquarters": {"type": "string"},
"employee_count": {"type": "string"},
"total_funding": {"type": "string"},
"latest_round": {
"type": "object",
"properties": {
"type": {"type": "string"},
"amount": {"type": "string"},
"date": {"type": "string"},
},
},
"key_investors": {
"type": "array",
"items": {"type": "string"},
},
"executives": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {"type": "string"},
"title": {"type": "string"},
},
},
},
"description": {"type": "string"},
},
"required": ["company_name"],
},
},
)
# =============================================================================
# ENRICHMENT AGENT
# =============================================================================
enrichment_agent = Agent(
model=OpenAIResponses(id="gpt-5.4"),
tools=[enrichment_tools],
markdown=True,
instructions="""You enrich company records with web data.
Use create_task() to research a company, then get_task_result() to retrieve the data.
Return the structured data for database insertion.""",
)
# =============================================================================
# RUN
# =============================================================================
if __name__ == "__main__":
# Enrich a company record
enrichment_agent.print_response(
"Enrich this company record: Anthropic",
stream=True,
)create_task returns a provider run_id, not the finished report. Call get_task_result(run_id) to retrieve content and its citation basis; this can block for up to default_timeout (1,800 seconds by default). Agno’s stream=True does not make that tool call stream report tokens. A timeout does not cancel the provider task; retain the ID to check status or retry retrieval.
The script researches one company and prints an agent response. It does not update a CRM or database. The Parallel schema constrains the tool’s research output; the outer Agno response has no output_schema. Validate returned content before inserting it into your own database.
Run the Example
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateInstall dependencies
uv pip install -U agno openai parallel-webExport your API keys
export OPENAI_API_KEY="your_openai_api_key_here"
export PARALLEL_API_KEY="your_parallel_api_key_here"Run the example
Save the code above as company_enrichment.py, then run:
python company_enrichment.pyFull source: cookbook/91_tools/parallel/company_enrichment.py