Competitor Intel Agent

The Problem

Sales and product teams need fresh competitor intel, but gathering it manually is a time sink. By the time someone compiles a report, it's already stale. Most teams either skip it or assign it to a junior analyst who spends hours on what should take minutes.

Why AI

Rule-based automation fails because competitor content is unstructured: press releases, blog posts, and pricing pages all look different. An LLM can read, synthesize, and extract meaning from messy web content that would break traditional scrapers.

How It Works

1
Pull competitor names from a shared Google Sheet
2
Research each company via Brave Search (what they do, products, positioning, recent news)
3
Pass raw findings through a two-stage LLM chain:
Stage 1: Research agent synthesizes raw search data into structured summaries
Stage 2: Strategic analyst extracts patterns, threats, opportunities, and recommended actions
4
Convert markdown output to styled HTML
5
Email formatted report to stakeholders automatically
Competitor Intel Agentic Workflow diagram showing the n8n workflow with Google Sheets input, Brave Search, two-stage LLM chain, and Gmail output

How We Built It

Decision Alternative Why I Chose This
Google Sheets input Custom form / UI Non-technical teammates can update the competitor list without asking me
n8n workflow Custom Python Visual debugging and fast iteration; easier to maintain and demo
Two-stage LLM chain Single mega-prompt Separates research from analysis, producing sharper and more reliable output
Think tool for planning Direct execution Agent plans its approach before acting, reducing errors on multi-step tasks
Tuned tool descriptions Generic descriptions Guides agent behavior on when to search, read from Sheets, or reason
Email output Dashboard Meets stakeholders where they are; no new tool to adopt or login required
Claude Sonnet 4 GPT-4 / Haiku Best balance of cost, speed, and reasoning quality for multi-step tasks
Actionable insights Raw data dumps Focus on threats, opportunities, and recommended actions stakeholders can act on

What I Learned

  • 💡 Even a powerful model guesses when prompts are vague. A clear prompt on a smaller model often works better because it follows directions instead of inferring what you want.
  • 💡 The order in which the agent calls tools comes from two places: the agent prompt and each tool's description. Both need to be specific for routing to work.
  • 💡 In this case, a two-stage LLM chain was important because research needs to be complete before analysis begins. One LLM doing both tends to skip gathering facts and jump to conclusions.