Query weight
w(q) = demand(q) × value(q)
Each query weighted by how often it is asked and the value of the work behind it.
Diagnosis · Query & Intent Modelling
Know the queries before you write the answers.
We build a weighted model of the commercial queries in your market, cluster them by meaning and intent, and score how well your existing pages match each cluster.
The retrieval problem
You describe your services one way. Your buyers search for them another.
A firm writes about its commercial dispute resolution practice. A buyer asks who can recover money a supplier owes them. Retrieval systems match the buyer's words and meaning, not the firm's. Where the two differ, the firm is not retrieved, however good its work.
What we measure
The numbers this work is built on.
Each is calculated for your pages and your competitors', against the same buyer queries, before anything is changed.
Cluster cohesion
mean cos(qᵢ, qⱼ) within a cluster
How closely the queries in an intent group share meaning, and so whether one page can serve them all.
Weighted coverage
Σ w(q) · [sim(q) ≥ τ] / Σ w(q)
The share of total query value your current pages match above the retrieval threshold.
The work
What we do.
Query collection
Gather queries from search data, sampled AI prompts and enquiries, in your buyers' own words.
Intent classification
Label every query by purchase stage: problem, discovery, comparison or supplier selection.
Semantic clustering
Represent each query as a vector and group queries by meaning rather than by shared keywords.
Page mapping
Match every cluster to the page that should answer it, or record that no page can.
Deliverables
What you receive.
Weighted query model
Every commercial query in scope, with its demand, value and intent.
Intent cluster map
Queries grouped by meaning, each cluster mapped to a target page.
Coverage scores
For each cluster, how well your best page matches, against the best competitor's.
Missing-page list
Clusters with commercial value and no page able to answer them.
How it starts
From application to roadmap.
-
01
Apply
Answer six short questions about your business. We read every application.
-
02
15-minute consultation
Free. We show you two or three verified retrieval weaknesses in your market.
-
03
Retrieval Opportunity Report
A measured diagnosis of one service category, and a prioritised roadmap.
-
04
Implementation
The roadmap carried out, then re-tested against the same measures.
Common questions
How is this different from keyword research?
Keyword research lists phrases and search volumes. This models meaning: queries are clustered by what they ask, weighted by commercial value, and scored against your pages with the same kinds of measure retrieval systems use.
Where do the queries come from?
Search demand data, sampled AI prompts, and the language your customers use in enquiries and calls.
The rest of the roadmap
Free 15-minute consultation
Find out where your business stands.
- How search and AI systems currently interpret your business
- Where competitors are better understood than you
- Specific retrieval weaknesses, checked before we speak
- Whether there is work worth doing, and what it is worth to you
Apply for a free 15-minute consultation
We reply within one business day, and usually within the hour.