AI SEARCH (GEO)

Map question coverage across a topic

Use when you want to see which questions in a topic your site answers and which it does not.

topic-coverage-map.md

Download .md

You are mapping question coverage for a topic so we can see where assistants have nothing of ours to cite.

Topic: {{TOPIC}}
Our audience: {{AUDIENCE}}
Pages we already have, with URLs and one-line summaries: {{EXISTING_PAGES}}

Steps:
1. Generate the question set a buyer works through on this topic, from first awareness to post-purchase. Aim for 35 to 50 questions, phrased as a person would type them.
2. Map each question to the existing page that answers it, if any.
3. Score the answer quality 0 to 3 where 0 is not covered, 1 is mentioned in passing, 2 is answered but buried, 3 is answered directly and self-containedly.

Output:
| Stage | Question | Best matching page | Score | What is missing |

Then give:
- The ten highest value gaps, ranked by how directly they precede a buying decision.
- Five questions currently answered across multiple pages that should be consolidated into one.

Constraints:
- Judge coverage only from {{EXISTING_PAGES}}. If a summary is too thin to judge, score it "unknown" rather than guessing.
- Do not invent questions that only make sense if our product exists.
- Do not recommend a new page where an existing page could answer the question with an added section. Say which.

Fill in before running

Replace each placeholder with your own detail. The more specific you are, the less the model invents.

{{TOPIC}}
{{AUDIENCE}}
{{EXISTING_PAGES}}

Getting a better result

Score 2 entries are usually faster wins than score 0 entries; the content already exists.
Consolidation matters because split answers compete with each other for citation.
Redo the map quarterly rather than after every publish.

Questions about this prompt

When should I map coverage rather than build an FAQ?

When you want the shape of a topic before commissioning anything. The FAQ prompt works from questions you already collected. This generates the question set a buyer works through from awareness to post-purchase and maps it against pages you have, which suits a gap you suspect is coverage rather than phrasing.

What do I need before running it?

Your existing pages with URLs and a summary of each substantial enough to judge. Coverage is scored only from {{EXISTING_PAGES}}, so one-word summaries return unknown rather than a finding. Writing those summaries honestly, from the pages rather than from memory, is most of the work in this one.

What comes back, and which rows do I act on?

A scored question table by buying stage, the ten highest value gaps, and five questions answered across several pages that should be consolidated. The score 2 rows are the quick wins, since the answer exists and is merely buried. Zeros need writing from scratch and take an order of magnitude longer.

What is the mistake here?

Turning every gap into a new page. The prompt is told to prefer adding a section to an existing page and to say which, and that recommendation is the first thing overridden by anyone with a content calendar to fill. Splitting one answer across three thin pages lengthens next quarter's consolidation list.