Focus: Bets

# Bets AI Skill Focus Area · Bets Block (formerly Decisions) · Decision Map · Oct 23, 2026 (v1.1) --- ## 1. What the Skill Does The Bets skill helps teams commit to one of several compared options. It is the last block in the Focus area of Glare's Decision Map. By now the initiative is framed, the variable is named, and Comparing has measured every option the same way. Bets judge **desirability**: of the options, which outcome is worth committing to? They own **Prefer** signals, which show which option people would choose. A bet names the option it backs, the evidence behind it, what it costs, and the outcome it expects. The skill still runs as glare-focus-decisions so existing installs keep working. This block used to be called Decisions. Bets need options. One option tested once is not a bet; it is a next move in Measure → Findings, which owns the five decision types (Implement, Refine Design, Test Iteration, Revisit Later, Do Not Pursue). ### The Prefer Rule No Prefer signal, no bet. Prefer must be measured the same way for every option, as a side-by-side choice, likely to choose (top-two box), trust, or pull-away. Desirability words or the Desirability UX metric alone don't count. Without Prefer, the next move is another comparison round with the Prefer question added. ### The Winner Rule The readout has a Use line (which option worked better) and a Prefer line (which option people would choose). The call comes from both: | Prefer | Use | Call | |---|---|---| | Wins | Wins or ties | Implement is open | | Ties | Wins | May go ahead, labeled "won on Use, preference tied"; the bet carries that risk | | Wins | Loses | A split: Refine Design or Test Iteration, never Implement | | Loses | Any | Not this option | | Doesn't separate | Doesn't separate | No winner: Test Iteration, or the business goal decides and the bet says so | A strong signal on its own is not enough. The call comes from the rule. ## 2. Business Benefit Without a bet, comparisons stay in decks and the same options come back to every meeting. A bet ends the loop: it says what the team backs, what it gives up, and what it expects to happen, with a date to check. This helps teams: - commit to a direction backed by what users chose, not only what they could do - name the cost of the choice up front - size the commitment to the evidence - give Lead a predicted outcome it can check later - rank several winning options with real lift, not guesses ## 3. Skill Output When used correctly, the skill produces a bet record. Tactical bets (a version, flow, or message) are judged on design KPIs with a product KPI to watch. Strategic bets (a direction to invest in) need a credible line to business KPIs. When being wrong is expensive, reduce risk first with a smoke test, pilot, or proof of concept. 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 | | Options and Variable | Current vs. redesigned home screen (Iteration) | | Use Line | First-click success on balance: Redesign 79%, Current 61% | | Prefer Line | Likely to choose (top-two box): Redesign 68%, Current 49% | | Call | Prefer wins and Use wins: Implement is open | | Cost | Power-user shortcuts move off the home screen | | Bet Size | Tactical; low risk, reversible in one release | | Business Goal | Reduce session abandonment | | Predicted Outcome | Sessions that end without an action drop from 38% to under 30% within 60 days of launch | | Check Date | 60 days after launch, by Lead → Results | | Owner and Next Step | Design lead moves the redesign into release planning; research tracks the power-user gap | | Failure Mode to Watch | Calling Implement on first-click success alone. That is a Use signal; without Prefer it is not a bet. | When several options clear the winner rule, the skill ranks them with RICE, ICE, weighted scoring, MoSCoW, Eisenhower, or Now/Next/Later, scored with measured Use and Prefer lift. ## 4. Prompt Strategies The prompts below show different ways to use this skill. Each example uses a mobile banking dashboard update. ### Prompt 1: Readiness Entry: Is this ready for a bet? *"We tested the redesigned mobile banking home screen against the current one. The redesign won first-click success, 79% vs 61%. Using the glare-focus-decisions skill, tell us whether we can make a bet yet, and if not, what is missing."* **Why this works:** It checks for a Prefer signal before anyone commits. Here there is none, so the skill sends the team back for one more round with the Prefer question added. **Best for:** - stakeholders pushing to ship on one strong number - reviewing a readout before a decision meeting ### Prompt 2: Split Entry: Use and Prefer disagree *"Version A of our mobile banking dashboard won first-click success, 79% vs 71%. But more people would choose Version B, 66% vs 54%. Using glare-focus-decisions, apply the winner rule, name the call, and tell us what the next round should change."* **Why this works:** A split is not a win. The winner rule says Refine Design or Test Iteration, never Implement, and the skill names what a sharper round would need to show. **Best for:** - results where two metrics point different ways - teams tempted to quote the number they like ### Prompt 3: Record Entry: Write the bet *"We are backing the redesigned mobile banking home screen. Using glare-focus-decisions, write the bet record: the Use and Prefer lines, the call, the cost, the bet size, the predicted outcome with its metric and window, the check date, and the owner."* **Why this works:** A bet without a predicted outcome can't be checked. The record gives Lead → Results something to test later. **Best for:** - closing out a Focus round - handing a decision to product or leadership - building a history of bets and how they turned out --- *Glare Framework · glare-focus-decisions (Bets) · Focus Area. Handoffs: glare-focus-comparing · glare-focus-methods (Variables) · glare-focus-initiatives · glare-measure-findings (single test) · glare-lead-mapping · glare-lead-results (outcome check)*

⬇ Download SKILL.md