vendor-directory-builder

Vendor Directory Builder

What this produces

A filterable Excel workbook the user can actually work from:

• Directory tab: one row per provider, with contact info, service area, a "Serves " flag, ratings, license/credential status, strengths, the source signal (who recommended them / how they surfaced), cautions, a confidence read, and a top-pick star.
• Top Picks tab: the single best, verified, market-serving option per category, plus runners-up and a small summary block.
• Methodology tab: how the list was built and a reusable vetting playbook, so the user (or their team) trusts the list and can keep filling it.
• Optional reference tab(s): domain-specific "obscure but critical" data the job needs (e.g., the utility districts that own the water main and set tap fees, permit offices, licensing boards). Add these whenever the use case has a hidden layer.

scripts/build_directory.py generates all of this from one JSON config, so the format is consistent every time and you never hand-format a spreadsheet.

Why this method works (read this, it drives every decision)

Two weak signals combine into one strong one:

1. Community recommendations are social proof from people who actually paid. When an investor in a local Facebook group answers "who's a good plumber?" by naming a company, that's a referral backed by a real transaction, far better than an ad. The single strongest signal is cross-validation: when two or more different people independently name the same provider, call that one first.
2. Public records are independent verification. Reviews, license boards, BBB, and the company's own site confirm the provider exists, is licensed where required, is still in business, and serves the target area, none of which a forum post proves.

Neither alone is enough. A forum name with no paper trail might be someone's cousin; a 5-star Google result might be a national lead-gen shop that never picks up. The value of this skill is doing both and being honest about what couldn't be confirmed.