Game Designer Assistant-AI-powered design support for game creators.

Example

Design a mobile-first full-screen shop with tabs (Currencies, Consumables, Bundles, Daily Deals, VIP) and visible contextual currency counters; implement mini-shop for new players and expand to full-shop after first purchase.

Scenario

A small studio launching a hybrid-casual title wants a low-friction monetization entry. Assistant supplies a wireframe, suggested tab structure, recommended slot sizes for single-item vs bundle tiles, and a playflow for deep-linking from currency '+' buttons to the correct shop section (practices consolidated from the shop guide) .

Example

Create starter bundles with 1 main item (e.g., permanent cosmetic / no-ads) + 2–3 filler items (currency, short-term boosts); cap perceived value multiplier to 3–4× and make ultra-high-value tiny-price deals one-time only.

Scenario

A midcore game wants to convert non-payers. Assistant proposes three starter bundles: $1.99 starter (small currency + 1-day booster), $4.99 growth (larger currency + rare cosmetic), $19.99 whale bundle (main exclusive hero shard + large currency). Each bundle comes with rationale for main vs filler selection, estimated perceived value, and a recommended A/B test design to validate conversion metrics as outlined in best-practice guidance .

Example

Build a multi-tier price ladder plus localized price points and an automated first-purchase bonus (e.g., 2× on first pack) with fallback rules for players using VPNs or inconsistent pricing.

Scenario

A cross-regional launch requires pricing tuned to purchasing power. Assistant outputs recommended USD-equivalents, localized thresholds, a suggested first-purchase multiplier for each tier, and guardrails to avoid inflation or cross-region arbitrage — following pricing heuristics and first-purchase tactics described in the shop guidance .

Example

Define segments (newbie, likely-to-pay, low-payer, dolphin, whale, resource-deficit) and rules to dynamically sort/override shop slots — e.g., show resource packs matching current in-game deficits and present low-to-high prices for low-payers.

Scenario

An operational LiveOps team wants to increase conversion without client builds. Assistant provides segmentation rules, priority sorting logic (low→high for new/non-payers, adaptive high→low for identified spenders), and a set of override examples (price change, slot visibility) to implement via a remote config/experimentation platform — matching the dynamic shop case study patterns in the uploaded PDF .

Example

Design an event shop with event currency, exclusive items, extended post-event windows for 'late birds', countdown timers, and real-time limited-quantity counters.

Scenario

For a seasonal holiday event, Assistant drafts an event-shop layout, composes five themed bundles (including a premium limited-quantity cosmetic), recommends countdown UI/UX, suggests a post-event 24–72 hour grace period for spending event currency, and defines telemetry to measure conversion spikes — reflecting best practices from event shop design in the shop guide .

Example

Create experiment designs: control vs. variant for bundle composition, price points, badge usage ('Best Value' vs none), and mini→full shop transition; produce measurement plan with KPIs (conversion rate, ARPDAU, ARPPU, retention delta, LTV uplift).

Scenario

A product manager wants to validate whether adding 'Most Popular' badges increases sales of mid-tier packs. Assistant provides a 4-week A/B test plan, sample size calculations, success criteria, instrumentation checklist, and recommended post-test actions (rollout or iterate), aligning to the empirical approach advocated in the best-practices material .