Scored 1,200 independent tour guides for outreach in two days for a tourism marketing agency
Client snapshot
A small marketing agency that builds websites and booking pages for independent tour guides and small tour operators. Four people. They sell by outreach, and their best prospects are guides who are good at their job and bad at being found online.
The problem
Knowing who to contact took longer than contacting them. For each guide, someone checked whether they had a website, whether it took bookings, how many reviews they had and where, whether they were on the big tour marketplaces, and how active their social accounts were. Done by hand, that was 10 to 15 minutes a guide. The agency had a list of about 1,200 names and never got through it.
Without that research, outreach was generic, and generic got a 2% reply rate.
What we built
A scraper and a scoring step that fill in a sheet.
The agency drops a list of guide names, cities and any known URL into a sheet. n8n sends each row to a Python scraper that finds and checks the guide's website, review profiles, marketplace listings and social accounts. Claude fills 13 fields per guide: website yes or no, booking on site, review count and average on each platform, marketplace presence, last social post, languages offered, and a few more agreed in discovery.
From those fields, each guide gets a fit score and one line about what to say: "strong reviews on two marketplaces, no website of their own" is a different pitch from "website with no booking button". Results go to Google Sheets, and the agency's existing Excel tool reads the same file without any change.
Results, first run
- Researching 1,200 guides: around six weeks of manual checking → two days.
- Fields per guide: 4 checked by hand → 13, each with a source link.
- Reply rate on outreach that used the opening line: about 2% → about 9%.
- The agency now reruns the list each quarter to catch guides whose situation changed.
Quote
"We stopped emailing guides who already had a good site. Everyone we contact now has the problem we fix." Agency founder
Build snapshot
- Timeline: 5 business days
- Stack: n8n, Python, Claude, Google Sheets, Excel
- Investment: $1,800
- Who owned it: the founder set the scoring criteria; an account manager runs the quarterly refresh.
The pattern
This is the pattern we ship in the Lead Scraper + Enricher engagement: a list of names or URLs in, a scored list with an opening line out. The build is the same, with your ICP and fields swapped in.
This is an illustrative composite drawn from operator engagements. Names, identifying details, and exact metrics are anonymised. The workflow, stack, and approach are real.
Looks like your situation?
A 30-minute call tells us whether the same pattern fits your operation, and what it would cost to ship it.