Trawl

The businesses most likely to need a website are the hardest ones to find, because by definition they do not have one to find. They exist as a maps listing, a phone number and a stack of reviews.

The reviews are the interesting part. A restaurant with forty comments complaining that you cannot see the menu online has told you exactly what to build, in its own customers' words. That is a far better opening than a cold template.

Trawl scrapes listings for Singapore businesses with no real web presence, pulls their reviews, and runs those through the Claude API to extract recurring, concrete complaints — not a sentiment score, but the specific operational problem a website would actually solve.

What comes out is a dashboard of qualified prospects with the evidence attached, so any outreach can reference something real.

A 60-second ceiling. The scrape endpoint runs on a hosting tier that terminates a function at 60 seconds, which is well short of a full crawl. So the endpoint starts the job, returns a run ID immediately, and a separate poll-and-import path collects the result later. Nothing blocks on the crawl.

Cost per lead. Enrichment reads review text from the database and never re-hits the scraping API, so re-running analysis on a prospect costs nothing extra. Getting that boundary wrong is how a lead tool quietly turns into a monthly bill nobody budgeted for.

Small, trusted user base. Sign-in is username and password rather than email, because it is an internal tool with a handful of operators and nobody wants an inbox round-trip to log in. New accounts sit pending until an admin approves them, and a policy check prevents the last remaining admin from deleting themselves out of the system.

This is a working internal tool, not a product. It was built in a concentrated burst on top of patterns I already had, and it carries 42 tests over the paths that would cost real money if they broke.

It is here because it is the clearest example of using a language model as a component rather than as an assistant — structured extraction inside a pipeline, with a defined output shape, a cost ceiling and tests around it. That is a different discipline from asking a chatbot for help, and it is the one clients are actually asking about now.

• Next.js 15 (App Router), TypeScript
• Supabase — Postgres, Auth, row-level security
• Apify — Google Maps listing crawler
• Anthropic Claude API — structured extraction
• Vitest and Playwright