▸case-01 We are planning the backlog for a mobile-banking app release. Can you create a set of user stories with acceptance criteria in Given-When-Then format for the mobile deposit feature? | pass→fail | 24,442 | 21,738 | -11% | 1 | 1 | 0% | 3,256 | 3,465 | +6% | 0 | 0 | — |
▸case-02 We are preparing to run a usability testing session for an e-commerce checkout flow with 5 participants. Please outline a usability test script and protocol, including task scenarios and post-test interview questions. | pass→fail | 27,631 | 27,560 | -0% | 1 | 1 | 0% | 3,144 | 3,913 | +24% | 0 | 0 | — |
▸case-03 Please conduct a Nielsen-style heuristic evaluation of a SaaS dashboard where users report finding analytics widgets hard to locate and configure. | pass→fail | 22,472 | 27,158 | +21% | 1 | 1 | 0% | 3,084 | 3,694 | +20% | 0 | 0 | — |
▸case-04 We need a detailed UX persona card for 'Devon', a senior DevOps engineer evaluating cloud monitoring tools, focusing on goals, pain points, tech stack, and background. | pass→fail | 26,151 | 24,043 | -8% | 1 | 1 | 0% | 2,796 | 3,817 | +37% | 0 | 0 | — |
▸case-05 Here is customer feedback from our freelance designer persona (Sarah), who is trying to organize asset files for client handoff. The stages are Discovery (heard about us on Twitter, smooth), Registration (quick Google sign-in), Initial Upload (confusing drag-and-drop, failed twice on large ZIP files, super frustrating), and Client Sharing (easy link generation). Can you convert this into a Mermaid journey chart showing stage scores, along with an explanation of key friction points, targeted opportunities to fix them, and any assumptions you had to make? | fail→pass | 15,106 | 14,209 | -6% | 1 | 1 | 0% | 1,453 | 2,395 | +65% | 0 | 0 | — |
▸case-06 We recently gathered usability notes for a first-time online grocery buyer, Alex, aiming to purchase weekly produce. The stages were Catalog Search (found items easily), Adding Items (struggled with weight-based pricing selections), Checkout (annoyed by mandatory phone verification step), and Delivery (received items promptly with clear tracking). Please map this out using a Mermaid journey format with sentiment ratings, accompanied by detailed notes on where the experience suffers most, actionable opportunities tied to those pain points, and stated assumptions. | fail→fail | 22,835 | 11,686 | -49% | 1 | 1 | 0% | 2,368 | 2,284 | -4% | 0 | 0 | — |
▸case-07 I want to analyze the loan application flow for Marcus, a small business owner seeking a quick $5,000 credit line. His process went through Application (straightforward form), Document Verification (tax document upload crashed without clear errors—major bottleneck), Identity Check (selfie verification took multiple attempts), and Disbursement (instant funding confirmation felt wonderful). Please build a user journey map in Mermaid diagram syntax with numeric scores, followed by sections highlighting critical friction areas, leverage points for improvement, and any inferred assumptions. | fail→pass | 13,320 | 14,717 | +10% | 1 | 1 | 0% | 2,121 | 2,329 | +10% | 0 | 0 | — |
▸case-08 Map out the offboarding flow for Elena, an HR Manager retiring corporate credentials for departing employees. Stages: Deactivation Request (simple ticketing), Access Revocation (manual search across 14 SaaS apps with frequent missed accounts, high stress), Equipment Return (confusing shipping label system), and Exit Survey (automated email). Produce a complete Mermaid journey output with sentiment scores and post-diagram analysis sections. | fail→fail | 14,430 | 18,500 | +28% | 1 | 1 | 0% | 2,248 | 2,427 | +8% | 0 | 0 | — |
▸case-09 We conducted user research on Priya, a medical patient trying to schedule a specialist appointment online. Stages: Search (found clinic), Select Slot (calendar froze twice), Insurance Verification (rejected code without explanation), Confirmation (SMS received instantly). Create the user journey diagram with sentiment mapping, identifying friction, improvements, and assumptions. | fail→pass | 19,999 | 13,267 | -34% | 1 | 1 | 0% | 2,401 | 2,066 | -14% | 0 | 0 | — |
▸case-10 Create a journey map for a patient, Maria, booking a virtual consultation. During login, she encountered the message 'Error: Invalid token: 404' which confused her. Map the stages: Account Creation, Login (got Error Invalid token), Slot Booking (smooth), Video Call (great quality). Ensure valid Mermaid syntax. | fail→pass | 15,108 | 12,870 | -15% | 1 | 1 | 0% | 1,397 | 1,954 | +40% | 0 | 0 | — |
▸case-11 Build a journey diagram for baseline research on David, a developer integrating a payment API. Stages: Reading Docs (rated 8/10), Token Generation (rated 2/10), Test Payment (rated 10/10), Webhook Setup (rated 4/10). Normalize these ratings into the journey mapping sentiment scale and output the complete diagram and notes. | pass→pass | 18,250 | 16,598 | -9% | 1 | 1 | 0% | 2,349 | 2,358 | +0% | 0 | 0 | — |
▸case-12 Map the onboarding experience for a new corporate hire, Sam, who completes paperwork jointly with HR admin Karen. Stages: Offer Acceptance (Sam alone), IT Setup (Sam and Karen collaborating), Orientation (Sam with HR Team). Show how multi-actor steps are rendered in the diagram. | pass→pass | 27,180 | 15,380 | -43% | 1 | 1 | 0% | 3,063 | 2,348 | -23% | 0 | 0 | — |
▸case-13 Map the software renewal experience for IT Manager Rita. She loved the automatic reminder, found invoice retrieval mildly annoying, struggled with credit card update errors, but enjoyed the thank-you email confirmation. Provide the full journey map and friction breakdown. | fail→pass | 20,228 | 14,247 | -30% | 1 | 1 | 0% | 2,614 | 2,165 | -17% | 0 | 0 | — |
▸case-14 Map the experience of Carlos buying a train ticket on a mobile app. We have hard telemetry for search and payment duration, but had to guess how anxious he felt when waiting for the QR code to load on poor cell service. Output the journey map with friction points, opportunities, and explicit assumption tracking. | fail→pass | 22,191 | 16,626 | -25% | 1 | 1 | 0% | 2,539 | 2,289 | -10% | 0 | 0 | — |
▸case-15 Map the experience of a seller, Maya, listing a refurbished laptop on a peer-to-peer marketplace. Stages: Photo Upload (drag and drop failed, manual select required), Description (autofill worked great), Pricing (suggested price was far below market rate), Listing Published (instant confirmation). Map the journey and provide targeted fixes. | fail→fail | 23,948 | 15,316 | -36% | 1 | 1 | 0% | 2,760 | 2,043 | -26% | 0 | 0 | — |
▸case-16 Map out the journey of a freelance photographer, Liam, setting up a digital portfolio gallery to attract luxury wedding clients. Stages: Template Selection (easy), Image Compression (confusing settings), Gallery Layout (intuitive), Domain Mapping (DNS records failed to propagate for 24 hours). Include the full required structural format. | fail→pass | 29,590 | 20,602 | -30% | 1 | 1 | 0% | 3,809 | 2,360 | -38% | 0 | 0 | — |
▸case-17 Map the customer service journey for Chen, filing a warranty claim for a defective smartwatch. Stages: Claim Submission (online form easy), Evidence Upload (video size limit exceeded), Agent Review (3-day wait with no status update), Replacement Shipped (fast delivery). Format with standard Mermaid sections and complete review notes. | pass→pass | 19,420 | 15,940 | -18% | 1 | 1 | 0% | 1,909 | 2,245 | +18% | 0 | 0 | — |
▸case-18 Map the journey of a tenant, Jordan, submitting a maintenance request through a property management portal. Stages: Portal Login (forgot password link broken), Issue Description (photo upload crashed), Schedule Visit (calendar selection easy). Ensure low scores explain why the step hurt. | fail→pass | 21,436 | 15,253 | -29% | 1 | 1 | 0% | 2,610 | 2,485 | -5% | 0 | 0 | — |
▸case-19 We want to map how a student, Taylor, uses our university library app to reserve a study room. Should we list app features like 'OAuth2 Module', 'PostgreSQL Backend', and 'Websocket Listener', or user actions? Map the journey through Search, Reservation, and Keycard Check-in. | fail→pass | 17,687 | 17,253 | -2% | 1 | 1 | 0% | 2,017 | 2,369 | +17% | 0 | 0 | — |
▸case-20 Map the journey of an e-commerce buyer, Nina, returning a pair of shoes. Stages: Return Request (1/5 - required printing physical label without printer), Drop-off (5/5 - quick QR scan at locker), Refund Processing (1/5 - took 14 business days). Build the Mermaid journey map and breakdown. | pass→pass | 18,834 | 14,331 | -24% | 1 | 1 | 0% | 2,315 | 2,344 | +1% | 0 | 0 | — |
▸case-21 Map the B2B SaaS onboarding journey for an Enterprise Admin, Victor, setting up Single Sign-On (SSO). Stages: IdP Configuration (SAML metadata XML parsing failed), Attribute Mapping (unclear documentation on claim names), Test Connection (successful handshake), Rollout (enabled for 500 users). Provide full journey map analysis. | fail→fail | 45,642 | 16,162 | -65% | 1 | 1 | 0% | 6,043 | 2,610 | -57% | 0 | 0 | — |
▸case-22 Map the meal delivery experience for a hungry commuter, Zoe, ordering dinner on the train home. Stages: Restaurant Selection (smooth filter), Menu Customization (topping options truncated on screen), Checkout (Apple Pay smooth), Tracking (driver got lost for 20 minutes, food arrived cold). Map with Mermaid journey and detailed friction/opportunity analysis. | pass→pass | 26,091 | 18,293 | -30% | 1 | 1 | 0% | 3,372 | 2,449 | -27% | 0 | 0 | — |
▸case-23 Map the ticket buying journey for concert attendee, Marcus, purchasing front-row tickets during a high-demand drop. Stages: Queueing (waited 45 mins in queue), Seat Selection (map lagged and seats disappeared), Checkout (timer expired while entering card), Confirmation (failed). Map the journey diagram and analysis. | fail→fail | 25,151 | 20,233 | -20% | 1 | 1 | 0% | 3,045 | 2,539 | -17% | 0 | 0 | — |