Measure: Hunches

# Hunches AI Skill Measure Area · Hunches Block · Decision Map · Oct 23, 2026 (v1.1) --- ## 1. What the Skill Does The Hunches skill helps teams turn a belief about a concept into something they can test, and write the questions that would prove it. It is the second block in the Measure area of Glare's Decision Map, after Concepts and before Testing. A hunch is an informed guess, written as a hypothesis: **We believe that** [this change] **for** [this group] **will** [have this impact] **because** [supporting reason]. The reason after "because" should point at something the team has seen. A hunch and its questions belong together: a hunch is only testable once someone writes down what they would need to see. Every hunch attaches to a concept. Hunches about people, such as what users need or the situation they are in, belong in Define. The skill gives each hunch a type and a perspective. | Hunch Type | What it is about | UX metrics it usually tests | |---|---|---| | Business | Whether the experience serves its goal for the right audience | Intent, Desirability, Brand Score, Completion Rate | | Presentation | Whether people understand what they see | Comprehension, Expectations, Appeal, Sentiment | | Interaction | Whether people can use it, and whether it works | Usability, Success, Effort, Error Rate, Time on Task | | Perspective | Who answers | Measured with | |---|---|---| | External | Users, in a test | UX metrics | | Internal | The team and the business function that owns the number | Product KPIs and Business KPIs | ### The Falsifiable Rule A hunch must be able to be wrong. Each one cites its observations, lists what it assumes, and names the metric that would prove it. If a hunch fits two types, split it into two. Untested assumptions carry the risk, so the questions test those first. The skill writes the questions too. Each question has a type (People, Process, Product, or Problem), a mode (Exploratory, Evaluative, or Comparative), a bias check, and a UX metric. Ready-made instruments such as SUS or SEQ are not written here; Testing picks them and runs them as written. ## 2. Business Benefit Teams get stuck waiting for perfect data or leaping to solutions. Hunches give them a place to start that can be proven wrong cheaply, before anyone builds. This helps teams: - focus on the beliefs that carry the most risk - turn expert audit issues into testable hypotheses - write questions that aren't leading or loaded - test internal concerns, like launch cost or support load, with the business's own numbers - keep the reasoning next to each hunch, so nobody rebuilds it later ## 3. Skill Output When used correctly, the skill produces a hunch ready to test, with a status: Draft, Ready to test, Supported, Challenged, or Refuted. The example below shows how this works for a mobile banking dashboard. | Field | Example Output (Mobile Banking Dashboard) | |---|---| | Concept | Dashboard home screen redesign | | Observations | Analytics: 38% of home screen sessions end without an action. Session recordings: users scroll past two promo cards before reaching their balance. | | Hunch | We believe moving balance and recent transactions above the promo cards for habitual users will raise first-click success on balance because users currently scroll past promos to find it. | | Type and Perspective | Interaction · External | | Assumptions | Users leave because the balance is hard to find, not because the numbers are wrong (untested) | | Questions | Product, Evaluative: "Where would you tap to check your balance?" (Success). Problem, Exploratory: "What, if anything, slowed you down?" (Effort) | | Metric | Success (leading, in Helio); sessions ending without an action (lagging, after launch) | | Status | Ready to test | | Failure Mode to Watch | "Users like a cleaner home screen": a preference, not a falsifiable hunch tied to a metric | | Next Step Handoff | → glare-measure-questioning (Testing) to pick the technique, Stack, and tool | ## 4. Prompt Strategies The prompts below show different ways to use this skill. Each example uses a mobile banking dashboard update. ### Prompt 1: Observation Entry: Form a hunch from what you've seen *"Analytics show 38% of sessions on our mobile banking home screen end without an action, and recordings show users scrolling past promo cards. Using the glare-measure-hunches skill, write one or two hunches with their type, perspective, assumptions, and metric."* **Why this works:** Starting from observations keeps the "because" grounded in evidence instead of opinion. **Best for:** - turning analytics or recordings into testable beliefs - early rounds on a new concept ### Prompt 2: Audit Entry: Turn audit findings into hunches *"Our expert audit of the mobile banking dashboard flagged that the balance is buried below promotions. Using glare-measure-hunches, rewrite this audit finding as a hypothesis, add the impact metric, and write unbiased questions to test it."* **Why this works:** Most audit findings stop at the fix. Adding the impact metric is what makes them testable. **Best for:** - expert audits and heuristic reviews - backlogs of design opinions ### Prompt 3: Internal Entry: Test a business concern *"Our support team worries the new mobile banking home screen will raise calls about missing shortcuts. Using glare-measure-hunches, write this as an internal hunch, name the function that holds it, and tie its questions to a Product or Business KPI."* **Why this works:** Internal concerns become hunches the team can check with its own numbers, instead of objections that stall the work. **Best for:** - stakeholder concerns about cost or risk - changes that touch support, marketing, or sales --- *Glare Framework · glare-measure-hunches · Measure Area. Handoffs: glare-measure-concepts · glare-measure-questioning (Testing) · glare-measure-findings · glare-define-user-needs · glare-define-situations*

⬇ Download SKILL.md