strategyplaybook.aiSqwyz
Sign in
← All 124 tools
Customer · Diagnose

Voice of the customer synthesis

Takes the feedback you already hold — tickets, reviews, calls, surveys — and finds the pattern in it. Cheap, because the evidence exists; uncomfortable, because it usually contradicts an internal belief.

The printable canvas and the handoff into Claude Code are part of a paid plan. See what a plan includes. It needs the Claude desktop app on this machine, and your team and the prompt library already installed in that project — we cannot see your disk, so open it there.

Stage
01 Diagnose
Works at
Business, Department
Maturity
Early startup → Large organisation
Time
Two days if the data is accessible

What it is

A structured synthesis of feedback customers have already given you, across every channel it arrives through, to find the patterns that individual items obscure. It is secondary research on primary evidence — the data exists, it has simply never been read together.

Sources
Support tickets, reviews, survey comments, sales call notes, churn interviews, complaints, social mentions. Each is biased differently, which is why breadth matters.
Coding
Tagging each item to themes consistently, ideally by someone without a stake in the outcome. Done well, this is most of the work.
Frequency and severity
How often a theme appears and how much it matters when it does. These rank differently and both are needed.
Weighting by value
Complaints from your largest customers and from your cheapest arrive in the same inbox and should not carry the same weight.
Verbatim evidence
The actual sentences. They survive summarisation badly and persuade far better than the count that supports them.
The contradicted belief
What the organisation currently believes that this evidence does not support. The finding, as distinct from the findings.
The mistake people makeFeedback channels are self-selecting — you hear from the delighted and the furious, rarely from the quietly unimpressed, who are usually the largest group and the ones about to leave. Say what the data cannot see as clearly as what it can.
What it’s forYou have raw customer feedback and need the pattern in it.
What it’s not forYou have no data. This synthesises evidence; it cannot conjure it.

How you run it

  1. Gather everything before reading any of itTickets, reviews, NPS comments, sales call notes, churn reasons, complaints. Reading as you collect anchors you on whatever you saw first.
  2. Code before you concludeTag every item by theme without judging importance. The order themes emerge in is not their order of importance.
  3. Count and weightFrequency alone over-represents whoever complains most readily. Weight by customer value and by severity as well as by volume.
  4. Keep the verbatimA theme summarised loses its force. One well-chosen customer sentence changes more minds in a leadership meeting than a chart of the same finding.
  5. Name the contradictionFind the internal belief this evidence undermines and state it plainly. That is the whole reason the exercise was worth doing.

The prompt

Two ways to run it

Run this tool in your own Claude

The short prompt starts your partner against the library on your disk. The long one carries everything with it and needs nothing installed.

🔒 Prompt locked

Everything above is free — what this tool is, what it is for, what it is not for, and how to run it as a workshop. Three tool prompts a month are free with an account; beyond three, and for the printable canvas, it is the paid part.

See plans — from £19 a month

Your playbook

It lands in the earliest stage this tool suits. Move it on the Playbook page.

You’ll need

  • Raw feedback in whatever form it exists
  • Enough volume for a pattern rather than anecdotes
  • Somebody without a stake in the answer

You’ll end up with

  • Themes ranked by frequency and severity
  • Verbatim quotes supporting each
  • The belief this evidence contradicts

Runs well with

AI risk classification and governanceAnalysis planBusiness Model CanvasCapability maturity assessment