Create intermediate Works with: Any AI

Affinity Mapping Facilitation

Structured brief Has example

Find patterns in qualitative data.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Facilitate affinity mapping. Research data (notes, quotes): [RESEARCH_DATA]. Team: [TEAM]. Time: [TIME].

Provide a step-by-step plan: prepare data as one observation per note with participant ID; individually read and cluster silently (15 minutes); group and name clusters with descriptive phrases (not topics: "People re-enter data because they distrust the import"); merge and split clusters; look for relationships; identify insights and implications; and prioritize.

Include rules (no premature naming, avoid mixing interpretations with observations, count participants per cluster, not notes), instructions for remote whiteboards, a template for each insight (statement, evidence count, quotes, confidence, implication), and a sanity check (can an outsider understand the insight from the quotes?). Apply the process to a sample of my data and produce a first-pass cluster list with counts.

Define the output as a table with the cluster name, participant count, strongest quote, and implication, and set the rule for the number of clusters (aim for 6 to 12) and what to do with orphan notes.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Data: 62 notes from 8 interviews.
Cluster 1, named "People double-check because they distrust the numbers" (5 of 8 participants). Notes: "I export to a spreadsheet to be sure" (P2), "I recount manually every Friday" (P5).
Cluster 2, "Setup takes longer than the first benefit" (6 of 8).
Cluster 3, "Colleagues ask for screenshots instead of links" (3 of 8).
Insight: Users export data not because the charts are weak but because they cannot see where numbers come from. A source trail would let them skip exports.
Sanity check: could someone outside the team see the insight from the quotes? Yes.
Confidence: medium, because the cluster is based on eight people.

• affinity-mapping
• structured-brief