Define: Collecting

# Collecting AI Skill Define Area · Collecting Block · Decision Map · Oct 23, 2026 (v1.1) --- ## 1. What the Skill Does The Collecting skill helps teams gather evidence about their audience openly, before anyone has a hunch. It is the third block in the Define area of Glare's Decision Map, after User Needs and Audience and before Situations. Collecting reaches the defined audience through sources that can represent them, gathers more than one kind of evidence, and records where each piece came from. It works in four steps. | Step | What it does | Output | |---|---|---| | 1. Name what you want to learn | Keep the learning open, but aimed at a need or an audience | An open learning goal | | 2. Choose sources | Find sources that can reach these people, and rate each one | Named sources, with gaps | | 3. Gather | Collect more than one kind of evidence, each tied to its source | Gathered evidence | | 4. Map what you know | Record what was gathered and how far to trust it | A Source Map, handed to Situations | Techniques come in two kinds: open-ended gathering (interviews, a day in the life, diary studies, needfinding surveys, community listening, support tagging, Glare MCP evidence) and ongoing monitors (funnel review, drop-off mapping, feature adoption, retention reviews, and more). Pair at least two kinds of evidence, such as what people do and what they say. ### The No-Hunch Rule Collecting comes before any hunch. If the team already believes something about a concept, it isn't Collecting; write it as a hunch in Measure and test it. An interview with no hunch behind it is Collecting; an interview that probes a hunch is Testing. An analytics feed is Collecting; reading it against a hunch is Testing. ## 2. Business Benefit Most teams form beliefs from whatever is closest: one loud customer, last quarter's survey. Collecting widens the base on purpose, so the hunches that follow rest on more than one anecdote. This helps teams: - see what they already know before spending on new research - trace any later signal back to where it started - catch changes early through ongoing monitors - use evidence from the Glare MCP to learn more for less ## 3. Skill Output When used correctly, the skill produces a Source Map. It holds what was gathered and how far to trust it, not hunches or signals. The example below shows how this works for a mobile banking dashboard. | Field | Example Output (Mobile Banking Dashboard) | |---|---| | Learning Goal | What gets in the way when habitual users check their money on mobile? | | Audience | Habitual mobile bankers (from Audience) | | Sources | Product analytics, session recordings, support tickets, app store reviews, Glare MCP evidence on mobile banking | | Kinds of Evidence | What people do (analytics, recordings) and what they say (tickets, reviews) | | What We Know | 38% of home screen sessions end without an action; recordings show scrolling past promos; tickets ask where the balance went | | Trust | Analytics and recordings: strong. Reviews: weaker, skewed to unhappy users | | Gaps | Nothing yet from users who rely on shortcuts | | Failure Mode to Watch | Writing "the promo cards are the problem" into the Source Map. That is a hunch; it belongs in Measure. | | Next Step Handoff | → glare-define-situations to read the evidence for recurring conditions | ## 4. Prompt Strategies The prompts below show different ways to use this skill. Each example uses a mobile banking dashboard update. ### Prompt 1: Open Entry: Plan open learning *"We want to understand how habitual users check their money in our mobile banking app, and we have no hunch yet. Using the glare-define-collecting skill, write the learning goal, pick sources that reach these users, and tell us which two kinds of evidence to pair."* **Why this works:** It keeps the learning open while aiming it at a real audience and need. **Best for:** - new products or audiences - teams that jump to testing too early ### Prompt 2: Inventory Entry: Map what already exists *"We have analytics, a year of support tickets, and app store reviews for our mobile banking dashboard. Using glare-define-collecting, build a Source Map: what each source tells us, how far to trust it, and where the gaps are."* **Why this works:** Most teams have more evidence than they think. Mapping it first avoids paying for research they already have. **Best for:** - teams with scattered data - before commissioning a study ### Prompt 3: Boundary Entry: Is this Collecting or Testing? *"We want to interview mobile banking users about the new home screen. Using glare-define-collecting, tell us whether this is Collecting or Testing, and how to set it up either way."* **Why this works:** The line is the hunch. The skill routes the work to the right place so the interview answers the right question. **Best for:** - interview and survey planning - mixed research plans --- *Glare Framework · glare-define-collecting · Define Area. Handoffs: glare-define-audience · glare-define-situations · glare-measure-hunches (a belief has formed) · glare-measure-questioning (Testing)*

Open skill ↗⬇ Download glare-define-collecting-v1-2.zip