# Variables AI Skill Focus Area · Variables Block (formerly Methods) · Decision Map · Oct 23, 2026 (v1.1) --- ## 1. What the Skill Does The Variables skill helps teams name the one thing that changes between measurements. It is the second block in the Focus area of Glare's Decision Map, after Initiatives and before Comparing. Measure runs one test. Focus runs that test again, and the variable says what is different from one run to the next: a new version, a competitor, a different audience, a later month. Everything else stays the same, so the team can tell what moved the number. The skill still runs as glare-focus-methods so existing installs keep working. This block used to be called Methods. The skill works from 12 variables. | Variable | What changes between runs | |---|---| | Iteration | Versions of the same design | | Competitors | Your experience vs. others, on the same measure | | Timeline | The same measure across time periods: baseline, launch, +90 days | | Segments | Audiences, roles, cohorts, or need states | | Journeys | Steps or touchpoints, with the same metric at each | | Platforms / Devices | Mobile, desktop, tablet, or channel | | User Goals / Tasks | Different tasks on the same experience | | Feature Usage | Features compared on value, adoption, or use | | Geographies | Regions, markets, or languages | | User Lifecycle | New, returning, or expanding users | | Behavioral Triggers | Prompts or conditions that cause action | | Season | Timing or cycles that change needs, such as holidays or renewal windows | ### The One-Variable Rule Change one thing at a time. If the team wants to change two things, such as the layout and the audience, split it into two comparisons or name the confound up front. Start from the decision, not the test: ask "what would we need to see change to make this call?" The answer is usually the variable. ### Where the old methods went Methods used to mix four kinds of tool. The skill routes each named method to where it belongs now. | Kind | Examples | Where it lives now | |---|---|---| | Measuring: collects one data point you can repeat | Task success, first click, SUS, funnel review | Measure → Testing, or Define → Collecting for ongoing monitors | | Comparison designs: set up the repeat | A/B test, before and after, competitor benchmark, segment split | Focus → Comparing | | Mapping: shows what to vary, measures nothing | Journey mapping, JTBD, empathy mapping, service blueprint | Here, as ways to find the variable | | Prioritizing: ranks options once evidence is in | RICE, ICE, MoSCoW, Eisenhower, Now/Next/Later | Focus → Bets | ## 2. Business Benefit Most teams default to the method closest to their craft: another prototype test, another survey. Naming the variable first makes the team ask what the decision actually turns on. The right comparison might be a competitor, a segment, or a season, not another version. This helps teams: - pick comparisons that answer the real decision - avoid tests where two things changed and nobody can say which mattered - use data they already have before collecting more - stop running prioritization exercises when they need a measurement ## 3. Skill Output When used correctly, the skill produces a variable choice the team can hand to Comparing. It shows: - the decision the variable serves - the one variable, and the options along it - what stays fixed - data the team already has along this variable - any named methods, routed to where they belong The example below shows how this works for a mobile banking dashboard. | Field | Example Output (Mobile Banking Dashboard) | |---|---| | Initiative | Optimize Navigation & Discovery on the home screen, for habitual users | | Decision It Serves | Which home screen to take into the next release | | Variable | Iteration | | Options | Current home screen and redesigned home screen | | Held Fixed | Task (find your balance), audience (habitual users), metric (first-click success), Prefer question | | Data Already in Hand | Analytics show 38% of sessions on the current home screen end without an action; use it as the baseline | | Methods Routed | Team asked for a RICE score: that ranks bets later, in Bets, once the comparison is in | | Failure Mode to Watch | Testing the redesign on new users and the current version on habitual users. That changes two things at once. | | Next Step Handoff | → glare-focus-comparing to set up the repeat and pick the comparison design | ## 4. Prompt Strategies The prompts below show different ways to use this skill. Each example uses a mobile banking dashboard update. ### Prompt 1: Decision Entry: Find the variable *"Our initiative is to help habitual users find their balance faster on the mobile banking dashboard. We need to decide what to ship next quarter. Using the glare-focus-methods skill, ask what we would need to see change to make that call, name the variable, and list what must stay fixed."* **Why this works:** Starting from the decision keeps the team from defaulting to another version test when the real question is about a segment or a competitor. **Best for:** - kicking off a Focus round - teams that always run the same kind of test - initiatives with more than one possible comparison ### Prompt 2: Routing Entry: Sort a list of methods *"Our team wants to run journey mapping, an A/B test, a SUS survey, and a RICE exercise for the mobile banking dashboard. Using glare-focus-methods, tell us where each one belongs now, which one helps us find the variable, and what order to run them in."* **Why this works:** Teams often list methods that do different jobs. Sorting them shows which ones measure, which set up a comparison, which find the variable, and which rank bets afterwards. **Best for:** - research plans with a long list of methods - stakeholders who ask for a specific framework - untangling a plan that mixes measuring and ranking ### Prompt 3: Confound Entry: Check a planned comparison *"We plan to compare the redesigned mobile banking dashboard on iOS against the current version on Android. Using glare-focus-methods, check whether more than one thing is changing, and tell us how to split this into clean comparisons."* **Why this works:** It catches a comparison where two variables change together before any data is collected, when it is still cheap to fix. **Best for:** - reviewing a test plan before launch - comparisons across devices or regions - results nobody can explain --- *Glare Framework · glare-focus-methods (Variables) · Focus Area. Handoffs: glare-focus-initiatives · glare-focus-comparing · glare-focus-decisions (Bets) · glare-measure (Testing)*