Build Your Complete TAM Database From Scratch Using Claude Code
Building a comprehensive Total Addressable Market database used to require complex workflows across multiple tools and months of maintenance. Marketing teams would patch together scrapers, enrichment services, and CRM integrations, only to watch the whole system break when one piece changed. Telmo Crespo has condensed this entire process into a single Claude Code command that handles everything from initial data collection to final CRM push. Read the original here.
The workflow starts with three primary data sources, each serving different market segments. LinkedIn data works best for large and mid-sized tech companies because the information stays current and accurate. French companies can leverage SIREN data for normalized company names, industry codes, and employee counts. Public directories offer another path, though they require careful selection since some providers resist scraping and the data often goes stale without regular refreshes.
The enrichment layer separates this approach from basic list building. Instead of collecting standard firmographic data, you gather actionable intelligence your sales team can actually use as conversation starters. This includes HR employee counts, growth rates, current competitors, technology stacks, and open job postings. The key insight is doing the research manually once to map the exact data collection path, then handing that process to Claude Code to replicate across your entire target market.
The Five-Step Pipeline
Map companies from your chosen data source. Pull contacts based on your Ideal Customer Profile using specific job titles, functions, and seniority levels. Enrich each record with email addresses, phone numbers, LinkedIn URLs, and your custom data points that matter most for sales conversations. Deduplicate against your existing CRM to avoid creating duplicate records. Map everything to the correct object structure and import directly into your CRM system.
The automation advantage becomes clear when you compare this to previous approaches. Six months ago, building this workflow required n8n with every step automated separately and constant maintenance. Now the entire pipeline runs from a single command that handles data collection, enrichment, deduplication, and CRM integration. Claude Code manages the full sequence and sends a completion notification when finished.
“Six months ago I was building this entire workflow in n8n. Now I run one command and Claude Code handles the full pipeline.”
— Telmo CrespoWhat Telmo Crespo demonstrates here is something every marketing team can learn from. The best AI workflows are not about replacing your voice or your process. They are about finding the right framework that lets AI meet you where you are, and then building on it over time.
Ready to try this kind of thinking in your own workflow? These step-by-step recipes will walk you through related techniques you can start using today.
