# Collecting Data AI Skill Define Area · Collecting Block · Decision Map --- ## 1. What the Skill Does The Collecting Data skill helps teams gather the right information from the right people at the right time. It sits inside the Define area of Glare's Decision Map. This is where teams decide how to capture signals before they get lost in opinions and guesswork. Most teams collect too much or collect the wrong thing. They run research without a clear goal, use tools they are comfortable with instead of tools that fit the question, and share findings that nobody acts on. The Collecting skill fixes that by pairing every collection method with a specific user need, a business goal, and a metric. The skill uses five steps to move from intent to insight. | Step | What happens | |---|---| | 1. Start with Intent | Pair a user need with a business goal to define what data matters | | 2. Choose Your Stack | Pick the right research mode: Exploratory, Evaluative, or Comparative | | 3. Identify the Approach | Make sure the question is testable — it defines a gap, points to behavior, and can be measured | | 4. Apply the Techniques | Match the collection method to the approach and the metric | | 5. Connect the Data | Share findings at the right level: project, cross-team, or leadership | Each step connects to the next. Skipping intent means picking techniques that answer the wrong question. Skipping the connect step means findings stay in a deck and never reach a decision. **The Collection Rule** Teams often jump to tools before they know what they are trying to learn. That leads to data that looks thorough but does not change anything. The rule is simple: start with the question, not the tool. Write the hypothesis first. Then choose the approach. Then pick the technique. Then choose the tool. Running these in the wrong order is the most common reason research does not get used. --- ## 2. Business Benefit Good data collection gives teams evidence that replaces opinion in decision-making. One clear signal can stop weeks of debate. Ten can build confidence. A hundred can pressure-test a strategy. This helps teams: - stop running research that nobody acts on - pick the right method for the question they are actually asking - share findings in a way that each audience understands - connect research to metrics that matter to leadership - move faster because decisions are grounded in evidence Research becomes easier to trust and easier to present. --- ## 3. Skill Output When used correctly, the skill creates a clear collection plan for a product or workflow. The plan shows: - which research mode fits the current stage - which techniques to use and why - which tools to run them in - how to share findings at each level of the organization The example below shows how this works for a mobile banking dashboard. | Field | Example Output (Mobile Banking Dashboard) | |---|---| | Research Mode | Evaluative — the dashboard design exists and we need to know if it works | | Technique | First Click Testing + Task Success Rate — does the user find the balance and transaction history without help? | | Tool | Helio — collect completion and comprehension signals from 100 participants in hours | | Feedback Pairing | See what users do (task recordings) + Hear what users say (post-task survey) | | Metric Tied To | Completion Rate, Comprehension, Time on Task | | Sharing Level | Cross-team — findings shared in Glare workspace by concept and metric so product and engineering can act on them | | Failure Mode to Watch | Collecting data without a metric attached. A task success test without a defined completion criterion is just observation — it cannot guide a decision. | | Next Step Handoff | → glare-measure to turn collected signals into findings tied to user value and business outcomes | The output connects directly to the other Define blocks: - User Needs tells you what question to answer - Audience tells you who to collect data from - UX Metrics tells you what numbers to watch for --- ## 4. Prompt Strategies The prompts below show different ways to use this skill. Each example uses a mobile banking dashboard update. --- ### Prompt 1 — Diagnostic Entry: Start from a research gap "We are updating our mobile banking dashboard and we have not done any user research yet. We have a hypothesis that users cannot find their transaction history quickly enough. Using the glare-define-collecting skill, walk the five-step collection process and help us build a research plan — including the right mode, technique, tool, and how to share the findings with our product team." **Why this works:** Starting from a hypothesis forces the skill to apply the five-step process in order. It stops teams from jumping to a familiar tool before they have confirmed what question they are actually trying to answer. **Best for:** - starting a new research sprint from scratch - any situation where the team has a hunch but no data - planning research at the beginning of a design phase --- ### Prompt 2 — Technique Entry: Choose the right method for the question "We are comparing two versions of our mobile banking dashboard home screen. Version A shows balance and recent transactions up front. Version B uses a summary card that users tap to expand. We need to know which performs better. Using glare-define-collecting, identify the right research mode for this decision, recommend two techniques to use together, and explain which UX metrics each one produces." **Why this works:** Comparison questions need a different approach than discovery questions. This prompt uses the mode framework to match the research question — which version works better — to the right technique and metric, instead of defaulting to whatever method the team used last time. **Best for:** - A/B or preference testing decisions - any sprint where two design directions need a tiebreaker - connecting a technique choice to a measurable outcome --- ### Prompt 3 — Sharing Entry: Make findings usable across teams "We ran a first-click test on our mobile banking dashboard with 100 participants. Task success on finding transaction history was 61%. We need to share this with our product manager, our engineering lead, and our VP of product. Using glare-define-collecting, help us apply the three-tier sharing model to present this finding at the right level for each audience." **Why this works:** Research findings often go unused because they are shared the same way to every audience. This prompt uses the three-tier sharing model to translate the same data into the right format — project detail for the team, cross-team insight for the PM, leadership rollup for the VP. **Best for:** - preparing a research readout for multiple stakeholders - any situation where findings need to travel beyond the design team - building a habit of showing sources alongside results --- *Glare Framework · glare-define-collecting · Define Area* *Handoffs: glare-define-user-needs · glare-define-audience · glare-define-ux-metrics · glare-measure*