strategyplaybook.aiSqwyz
Sign in
← All 124 tools
Research · Diagnose, Explore

Evidence review

Establishes what is already known before you commission anything new. Frequently the cheapest research you will do, and the step most often skipped in the enthusiasm to gather primary data.

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, 02 Explore
Works at
All levels
Maturity
Any
Time
Two to three days

What it is

A systematic review of existing published evidence on a specific question, assessing what is established and where the gaps are. It exists to stop businesses commissioning expensive primary research into questions somebody has already answered.

The question
Specific and answerable, not a topic. Determines everything about the search.
Source types
Academic, industry, trade body, governmental, consultancy, journalistic. Each carries different bias, and knowing which is which is most of the skill.
Quality assessment
Funder, sample, method, date. A well-presented study with a self-selected sample of eighty is weaker than an unglamorous government dataset.
Established findings
Where multiple independent sources agree. The part you can build on.
Contested findings
Where they disagree, with the disagreement described rather than resolved by preference.
The gap
What is genuinely unknown, and therefore what primary research should be scoped to answer.
The mistake people makePublished evidence describes markets in general and will not know your customers in particular. It sets context and eliminates known questions; it does not answer anything specific to your business.
What it’s forYou want to know what is already established before commissioning anything new.
What it’s not forThe question is specific to your business. Published evidence will not know your customers.

How you run it

  1. Write the question, not the topic"What affects trade purchasing decisions" is a topic. "Does online research before purchase change brand choice in trade tools" is answerable.
  2. Search deliberately across source typesAcademic, industry, trade body, government, consultancy. Each is biased differently, and consultancy research is marketing with a methodology section.
  3. Assess each source's qualityWho funded it, how large the sample, when it was conducted, whether the method fits the claim. Most citation failures are quality failures rather than fabrication.
  4. Separate established from contestedWhere sources agree, say so. Where they disagree, say that too rather than picking the convenient one.
  5. Name the gapWhat remains genuinely unknown after reading everything available. That is what primary research should target, and now it can be scoped properly.

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

  • A specific question, not a topic
  • Access to published research, trade data and academic sources
  • Discipline to record what you did not find

You’ll end up with

  • What is established, with sources
  • Where the evidence is contested or thin
  • The gap that genuinely needs primary research

Runs well with

Acquisition screen and synergy thesisAdjacency mapAI opportunity mapAnsoff matrix