AI Agent Due Diligence: Automate Company Research with SEC, News, and Financial Data

Due diligence is one of those tasks that everyone agrees is important and nobody enjoys doing. Whether you’re evaluating an acquisition target, vetting a potential partner, or researching a company before a sales call, the process is the same: gather data from multiple sources, cross-reference it, identify red flags, and write up a summary. The process is thorough by necessity and tedious by nature.

A single company review can take a full day. You start with their website, move to news coverage, check their SEC filings if they’re public, pull financial metrics, and look at their stock performance. Each data source lives in a different place, returns data in a different format, and requires different navigation skills. EDGAR alone has a learning curve.

What an Agent Can Automate

An AI agent cannot replace human judgment in due diligence. It can replace the hours of data gathering that precede that judgment. The pattern is clear: fetch structured data from known sources, extract the relevant pieces, and compile them into a readable format. This is exactly what agents with tool access do well.

The agent handles:

  • Searching and retrieving SEC filings
  • Pulling standardized financial metrics
  • Gathering recent news coverage
  • Looking up company details and key personnel
  • Fetching stock price and performance data
  • Compiling everything into a structured report

You handle: reading the report, asking follow-up questions, identifying concerns, and making the decision.

The Workflow

Step 1: SEC Filings

Start with the authoritative source. SEC filings are legally required disclosures, which makes them more reliable than press releases or marketing materials.

“Search SEC filings for Datadog. Pull their most recent 10-K annual report and their latest 10-Q quarterly report.”

The agent queries the SEC EDGAR database, finds the relevant filings, and extracts key sections: revenue, operating expenses, risk factors, and management discussion. The risk factors section is especially useful for due diligence because companies are required to disclose material risks.

Step 2: Financial Metrics

SEC filings give you raw numbers. Standardized financial metrics put those numbers in context.

“Pull financial metrics for Datadog. I need revenue, revenue growth, gross margin, operating margin, net income, and free cash flow for the last 4 quarters.”

The agent retrieves structured financial data and presents it in a table. You can see trends at a glance: is revenue accelerating or decelerating? Are margins expanding or compressing? Is free cash flow positive?

Step 3: News Coverage

News coverage fills gaps that financial statements don’t cover. Product launches, executive departures, customer wins, regulatory issues, and competitive moves all show up in the news before they appear in filings.

“Search for Datadog news from the past 90 days. Focus on product announcements, partnerships, competitive developments, and any negative coverage.”

The agent scans news sources and returns a chronological list of articles with summaries. Patterns often emerge: a cluster of hiring announcements might indicate expansion into a new area, while multiple articles about customer complaints could signal a problem.

Step 4: Company Details

Basic company information rounds out the picture.

“Look up Datadog’s company details. I need their headquarters, employee count, founding date, key executives, and industry classification.”

The agent pulls company data from business information sources. This is useful for verifying what you already know and catching things you might miss, like a recent headquarters relocation or a change in C-suite.

Step 5: Stock Performance

For public companies, stock performance tells you how the market values the business and how that valuation has changed over time.

“Pull Datadog’s stock quote. Include current price, 52-week range, market cap, P/E ratio, and recent performance.”

The agent fetches current market data and historical performance metrics.

Step 6: Compile the Report

With all data gathered, ask the agent to synthesize:

“Compile a due diligence report on Datadog using all the data you’ve gathered. Structure it as: Company Overview, Financial Summary, Recent Developments, Risk Factors, Stock Performance, and Overall Assessment.”

Example Output

A section of the compiled report might look like this:

Financial Summary

MetricQ4 2025Q3 2025Q2 2025Q1 2025
Revenue$680M$645M$612M$580M
Revenue Growth (YoY)26%28%29%27%
Gross Margin79.2%78.8%79.1%78.5%
Operating Margin22.1%21.4%20.8%19.6%
Free Cash Flow$195M$178M$162M$148M

Assessment: Revenue growth is steady in the mid-to-high 20s with expanding operating margins. Free cash flow conversion is strong and improving. The business demonstrates operating leverage, with margins expanding faster than revenue is growing.

Risk Factors (from 10-K):

  • Customer concentration: top 10 customers account for 15% of ARR
  • Competition from cloud providers bundling monitoring with their platforms
  • Macroeconomic uncertainty affecting enterprise IT budgets

That level of detail, produced in minutes, with every data point sourced from an actual API call rather than the agent’s training data.

Tools Involved

This workflow uses tools from AgentPatch:

  • sec-search for finding and retrieving SEC filings from EDGAR
  • sec-financials for pulling standardized financial metrics
  • google-news for recent press coverage and developments
  • company-lookup for basic company information
  • stock-quote for current market data and stock performance

Setup

Connect AgentPatch to your AI agent:

The AgentPatch CLI is designed for AI agents to use via shell access. Install it, and your agent can discover and invoke any tool on the marketplace.

Install (zero dependencies, Python 3.10+):

pip install agentpatch

Set your API key:

export AGENTPATCH_API_KEY=your_api_key

Example commands your agent will use:

ap search "web search"
ap run google-search --input '{"query": "test"}'

Get your API key from the AgentPatch dashboard.

Claude Code

Install the AgentPatch skill — it teaches Claude Code when to use AgentPatch and how to use the CLI:

/plugin marketplace add fullthom/agentpatch-claude-skill
/plugin install agentpatch@agentpatch

MCP Server (Alternative)

If you prefer raw MCP tool access instead of the skill:

claude mcp add -s user --transport http agentpatch https://agentpatch.ai/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with your actual key from the AgentPatch dashboard.

OpenClaw

Install the AgentPatch skill from ClawHub — it teaches OpenClaw when to use AgentPatch and how to use the CLI:

clawhub install agentpatch

MCP Server (Alternative)

If you prefer raw MCP tool access instead of the skill, add AgentPatch to ~/.openclaw/openclaw.json:

{
  "mcp": {
    "servers": {
      "agentpatch": {
        "transport": "streamable-http",
        "url": "https://agentpatch.ai/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_KEY"
        }
      }
    }
  }
}

Replace YOUR_API_KEY with your actual key from the AgentPatch dashboard. Restart OpenClaw and it discovers all AgentPatch tools automatically.

Wrapping Up

Due diligence is a data assembly problem. The judgment is yours. The gathering does not have to be. An AI agent with access to SEC filings, financial data, news, and company information can produce a first draft of a due diligence report in minutes. You review it, ask follow-up questions, and dig deeper where needed. The agent handles the busywork. Visit agentpatch.ai to connect the tools and run your first company research session.

← Back to blog