Skip to main content
A startup intelligence agent that performs comprehensive due diligence on companies by scraping their websites, analyzing public information, and producing investment-grade reports.

​
Analysis Framework

The agent follows a structured due diligence process:
  1. Foundation Analysis: Company basics, team, mission
  2. Market Intelligence: Target market, competition, business model
  3. Financial Assessment: Funding, revenue indicators, growth
  4. Risk Evaluation: Market, technology, team, financial, regulatory risks

​
Prerequisites

  • Python 3.12+
  • OpenAI API key
  • ScrapeGraph API key

​
Setup

1

Clone the repository

git clone https://github.com/agno-agi/agno.git
cd agno
2

Create and activate virtual environment

uv venv --python 3.12
source .venv/bin/activate
3

Install dependencies

uv pip install -r cookbook/01_showcase/01_agents/startup_analyst/requirements.in
4

Get ScrapeGraph API key

Sign up at ScrapeGraph to get an API key.
5

Set environment variables

export OPENAI_API_KEY=sk-***
export SGAI_API_KEY=your-scrapegraph-api-key

​
Run the Agent

​
Analyze Startup

Perform comprehensive analysis on a company: 
python cookbook/01_showcase/01_agents/startup_analyst/examples/analyze_startup.py
Demonstrates:
  • Website crawling and data extraction
  • Team and product analysis
  • Risk assessment

​
Competitive Intel

Compare multiple companies: 
python cookbook/01_showcase/01_agents/startup_analyst/examples/competitive_intel.py
Demonstrates:
  • Multi-company analysis
  • Competitive positioning
  • Market comparison

​
Quick Scan

Fast overview of a company: 
python cookbook/01_showcase/01_agents/startup_analyst/examples/quick_scan.py

​
Agent Configuration

startup_analyst = Agent(
    name="Startup Analyst",
    model=OpenAIResponses(id="gpt-5.2"),
    system_message=SYSTEM_MESSAGE,
    output_schema=StartupReport,
    tools=[
        ScrapeGraphTools(
            enable_markdownify=True,
            enable_crawl=True,
            enable_searchscraper=True,
        ),
        ReasoningTools(add_instructions=True),
    ],
    add_datetime_to_context=True,
    add_history_to_context=True,
    num_history_runs=5,
    enable_agentic_memory=True,
    markdown=True,
)
ParameterPurpose
modelGPT for analysis and synthesis
output_schemaStructured due diligence report
ScrapeGraphToolsWebsite crawling and extraction
enable_crawlMulti-page site analysis
enable_markdownifyClean content extraction
enable_searchscraperExternal information search
ReasoningToolsPlan research approach

​
How It Works

​
Analysis Workflow

1. Crawl company website (10 pages, depth 3)
2. Extract team, products, pricing from key pages
3. Search for funding news and executive backgrounds
4. Analyze business model and market positioning
5. Identify competitive advantages and risks
6. Generate investment thesis
7. Compile comprehensive report

​
ScrapeGraph Tools

ToolUsage
CrawlComprehensive site analysis (first step)
SmartScraperExtract specific data from pages
SearchScraperFind external news and information
MarkdownifyConvert pages to clean markdown

​
Risk Categories

CategoryExamples
MarketCompetition, market size, timing
TechnologyTechnical debt, scalability
TeamKey person dependencies
FinancialRunway, burn rate
RegulatoryCompliance, legal exposure

​
Troubleshooting

Verify your API key:
echo $SGAI_API_KEY
Check your ScrapeGraph dashboard for usage limits.
Some websites block crawlers. The agent will report what it could access and note limitations in the confidence score.
Funding data relies on public sources. Private companies may have limited information. Check the due_diligence_focus field for areas needing manual research.

​
Source Code