The company
An invented example. A custom pool builder that designs and builds inground pools and outdoor living spaces. A project is roughly sixty-six thousand dollars of work, and homeowners research builders for a long time before they call. There are only a few serious builders in the market.
Why the early questions matter
With few competitors and long research, a homeowner may ask an assistant three or four questions before shortlisting anyone: who builds custom pools here, what a pool costs, who offers financing, who can design the whole backyard. Those answers shape the shortlist.
Step 1: the free Snapshot
Ten questions for the market across three assistants. In this example the builder is named in [X of 30] checks. A real Snapshot also shows who was named instead.
Step 2: build the data set first
One accurate record of the company: what it builds (gunite, fiberglass, spas, water features, outdoor living design), where it works, licensing it chooses to publish, how pricing works and what financing exists. From it we publish llms.txt, project and service docs, plain pricing, FAQs, schema and an agent-queryable endpoint.
Step 3: the questions
With the foundation in place we write the pages the Snapshot found missing, such as cost and timeline questions, and make sure the portfolio is described in text, not only in photos an assistant cannot read.
Step 4: re-check weekly
Pool research is seasonal, so the same questions are re-asked every week to see what moves as the season changes.
What this example does not show
No outcome. It shows the sequence: measure, foundation, questions, weekly re-checks.
This is a worked example. The company is invented and bracketed numbers such as [X of 30] are placeholders. No result on this page belongs to a real client. Real results will be published only with a client’s written permission.