42 Agency × MKT1
All Resources
MKT1 Workshop

Building a Competitive Intel Agent

How to build a Claude Code agent that scrapes ad libraries, analyzes competitor messaging, and generates branded PDF reports in minutes.

The output: A 10-20 page competitive analysis with ad screenshots, messaging themes, and strategic recommendations. What used to take days now takes ~5 minutes of human review.

What the Agent Does

LinkedIn Ad Library

Scrapes all active ads from competitor LinkedIn pages with screenshots.

Meta Ad Library

Pulls Facebook/Instagram ads with creative and copy analysis.

Google Ads Transparency

Captures search and display ads from Google's transparency center.

Competitor Discovery

Finds competitors via G2, TrustRadius, and category pages automatically.

Messaging Analysis

Extracts themes, value props, CTAs, and positioning across all ads.

Branded PDF Report

Generates a polished PDF with your branding, ready to share.

# Run the agent with one command
$ claude
> run CI agent for snowflake.com

# ~5 minutes later: 11-page PDF with competitor analysis

How It Works

1

Input company URL — Agent scrapes the site to understand product, ICP, and positioning

2

Find competitors — Searches G2, TrustRadius, and category pages for alternatives

3

Scrape ad libraries — Uses Browser Base to capture LinkedIn, Meta, and Google ads

4

Analyze messaging — Extracts themes, CTAs, value props, and creative approaches

5

Generate PDF — Compiles everything into a branded report with WeasyPrint

The Stack

CC

Claude Code

Terminal-based Claude that runs commands and accesses files

BB

Browser Base

Cloud browser for screenshots and JavaScript page scraping

WP

WeasyPrint

Converts HTML/CSS to polished, branded PDFs

V

Vercel

Optional: host interactive versions of reports

Download Example Reports

See what the Competitive Intel agent actually produces.

Two real examples: Snowflake (data warehouses) and Glyphic (AI sales tools).

Here are your example reports:

From the MKT1 Newsletter

This workshop was created for Emily Kramer's MKT1 community. It covers how 42 Agency built a reusable agent that compresses multi-day competitive research into minutes of human review. The key insight: agents are just text files with instructions — no code required.

42 Agency MKT1

Want Us to Build This For You?

42 Agency builds AI-powered demand gen for B2B companies.

Talk to 42 Agency