One Saturday. A competitive market analysis that major consulting firms charge hundreds of thousands of dollars to deliver. One developer, a web crawling API, and Claude.
A practitioner detailed their workflow for producing in-depth competitive intelligence research using Firecrawl - an API that extracts clean, structured text from websites rather than raw HTML code - combined with Claude for synthesis and analysis. The result is the kind of structured competitive assessment that previously required a team of analysts and months of project time.
The Workflow
Firecrawl handles data collection. You point it at competitor websites, pricing pages, case study archives, and industry publications. It returns readable, structured text rather than the messy tangle of HTML, CSS, and JavaScript that makes web scraping painful. That cleaner input is what makes the combination work - Claude can process 50 competitor pages worth of content in a single session, compare positioning across all of them, and surface patterns a human analyst would spend days identifying.
The output is the kind of structured competitive assessment consultants format into slide decks: who's targeting which customer segments, what the pricing tiers look like, how companies differentiate themselves, where the gaps are. Claude handles the synthesis. You handle the questions.
Strategy consulting has always bundled three services: data gathering, analysis, and presentation. AI tools are now capable at all three, and the cost difference is real. API calls don't bill at consultant hourly rates.
Where the Limits Are
A senior consultant brings things this workflow doesn't: access to non-public information, industry relationships, context built from years of similar engagements, and the credibility to defend conclusions to a board under pressure.
The workflow also has a hard ceiling - Firecrawl can only surface what's publicly accessible. Private company financials, undisclosed pricing strategies, and internal metrics stay out of reach regardless of prompt quality. The output is solid for competitive benchmarking based on public information. It's not a substitute for due diligence on an acquisition.
What has genuinely shifted is the floor for smaller teams. A solo founder or three-person operation can now produce competitive research that previously required either a consulting budget or months of manual effort. The practitioners getting the most out of this are the ones who understand their domain well enough to spot when the output is superficial or missing a critical angle. Claude synthesizes what you point it at. Knowing what to point it at - and what to be skeptical of in the results - is still a skill you bring yourself.