Building a Competitive Intelligence Dashboard with Claude Code

If you’re building a competitive intelligence feature or just need competitive context while developing a product, Claude Code can now research competitors directly — pulling search results, news, and trend data — and turn those findings into something useful in the same session.

Why This Matters

Competitive intelligence tools are common in SaaS, but building them well requires real data to develop against. You need to know what the actual output of a competitor search looks like before you can design the data model, the refresh cadence, or the UI.

With AgentPatch connected, Claude Code can run live competitive research during development. Ask it to look up competitors and it uses real tools — not its training data — so you’re working with current, realistic output.

Setup

Install the AgentPatch CLI (zero dependencies, Python 3.10+):

pip install agentpatch

Set your API key:

export AGENTPATCH_API_KEY=your_api_key

Then use it:

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

Get your API key from the AgentPatch dashboard.

Run this command to add AgentPatch as an MCP server:

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. Claude Code discovers all AgentPatch tools automatically.

Example

You’re building a competitive monitoring feature and want to test what a real snapshot looks like before designing the data layer. You tell Claude Code:

“Run a competitive intelligence pass on Notion, Obsidian, and Logseq. Pull search results, news, and trends for each, then design the CompetitorSnapshot data type based on what the real output looks like.”

Claude Code runs the research:

Searching Google for each competitor's recent updates...
Pulling Google News for Notion, Obsidian, Logseq...
Checking Google Trends for brand searches...

Research complete. Summary:

Notion: Heavily covered. AI features dominating press. Trends: +35% YoY.
Obsidian: Niche but loyal. Plugin ecosystem news. Trends: flat, stable base.
Logseq: Open-source community coverage. Recent database version launch. Trends: +8%.

Based on actual research output, here's the data type:

interface CompetitorSnapshot {
  name: string;
  category: string;
  trendChangePercent: number;
  trendPeriod: '3mo' | '6mo' | '12mo';
  recentNews: {
    title: string;
    source: string;
    date: string;
    sentiment: 'positive' | 'neutral' | 'negative';
  }[];
  topSearchTopics: string[];
  lastUpdated: string;
}

Writing this to types/competitive.ts and seeding fixtures/competitive.json with the real data.

Claude Code researched three competitors and designed a data type grounded in what real data actually looks like. That’s a better starting point than guessing at the schema.

Wrapping Up

With AgentPatch connected, Claude Code can do competitive research inline during any session. Search, News, and Trends are three tools — the same connection also unlocks Maps, email, image generation, and everything else on the marketplace. Explore at agentpatch.ai.

← Back to blog