▸case-01 I need to do my routine weekly check-in because my head is completely full of clutter. Here is my current mental dump: I need to prep for the quarterly business review, email back 5 clients, fix the broken deployment pipeline, renew my driver's license, and clean out the garage. My main goal right now is launching our new product feature. The pipeline fix and garage cleanout are totally stalled. Last week I successfully closed a big renewal contract, but I definitely spent way too much time scrolling social media when avoiding deep work. Please organize this into a weekly reset summary that categorizes my backlog, highlights my top focus, gives tiny immediate next steps for the stuck items, notes last week's wins, offers an honest check on where I'm coasting, and outlines a flexible direction for the week. | fail→fail | 11,538 | 12,925 | +12% | 1 | 1 | 0% | 2,169 | 2,339 | +8% | 0 | 0 | — |
▸case-02 Can you help me run my Sunday reset ritual? I'm feeling scattered and need to clear my mind before Monday. Here's what's going on: I'm trying to write a book proposal, but I keep putting off the chapter outlines. My brain is spinning with laundry, team performance reviews, buying flight tickets, and rewriting my portfolio site. Last week I managed to finish three workout sessions, but I relied way too heavily on automated templates instead of actually thinking through my team feedback. Please structure a full reset output for me: sort my mental backlog into basic action categories, identify my single key focus, break down my stalled items into micro first steps, celebrate the wins, call out my autopilot tendencies, and sketch out a light weekly shape. | fail→fail | 20,857 | 15,478 | -26% | 1 | 1 | 0% | 2,630 | 2,741 | +4% | 0 | 0 | — |
▸case-03 I want to do a weekly reset session with you to get unstuck. My overall target is finishing the website redesign. Right now I have a huge list of lingering thoughts: updating brand guidelines, scheduling dentist appointment, organizing digital files, buying groceries, and reviewing pull requests. I've been stuck on the brand guidelines for weeks. Last week went decent because I published two blog posts, but I noticed I was avoiding tough conversations with my contractor. Please synthesize this input by triaging my mental clutter, picking my main priority for the week, providing one tiny action step for what's blocked, summarizing last week's positive moments, giving me a gentle nudge about autopilot behavior, and laying out a loose weekly roadmap. | fail→fail | 15,546 | 13,642 | -12% | 1 | 1 | 0% | 1,890 | 2,506 | +33% | 0 | 0 | — |
▸case-04 I have a big pile of tasks floating around: paying my annual property tax, sorting vacation photos, filing the Q3 team budget, and asking my intern to summarize user research. I'd love you to categorize these by topic like Financial, Personal, and Work, pick my main target, and outline my week. | fail→fail | 13,679 | 15,395 | +13% | 1 | 1 | 0% | 1,515 | 2,520 | +66% | 0 | 0 | — |
▸case-05 I'm juggling five big projects: grant application writing, launching the marketing campaign, hiring a senior engineer, fixing the database latency, and migrating servers. Please give me my top three priorities for this week so I can balance them equally, along with a light weekly outline. | fail→pass | 17,723 | 20,955 | +18% | 1 | 1 | 0% | 2,075 | 3,367 | +62% | 0 | 0 | — |
▸case-06 I've been stuck on my academic literature review paper for three weeks. Can you create a multi-step project breakdown with daily writing milestones and a complete structural outline for the whole paper so I can finally get through it? | fail→pass | 17,935 | 20,555 | +15% | 1 | 1 | 0% | 3,047 | 3,313 | +9% | 0 | 0 | — |
▸case-07 Last week was terrible—I missed two client deadlines and felt totally unproductive. Please review my current list of pending tasks (client outreach, slide deck creation) and give me a strict critique focusing on my mistakes and what I need to fix. | fail→pass | 16,844 | 11,919 | -29% | 1 | 1 | 0% | 1,865 | 2,660 | +43% | 0 | 0 | — |
▸case-08 Here's my task dump: prepare client pitch, review contract, pay utility bills. Lately I've been using automated email scripts to auto-reply to all client inquiries without reviewing them. Just give me a clean task list for the week ahead. | pass→pass | 4,896 | 10,156 | +107% | 1 | 1 | 0% | 895 | 2,710 | +203% | 0 | 0 | — |
▸case-09 I have tasks like finishing code review, updating Jira tickets, and calling my doctor. Please build me a weekly reset that includes a detailed hourly schedule from 9 AM to 5 PM Monday through Friday with 30-minute time slots for every single task. | fail→pass | 30,750 | 12,395 | -60% | 1 | 1 | 0% | 6,699 | 2,925 | -56% | 0 | 0 | — |
▸case-10 I want to do my weekly reset for my software development goals (finishing dark mode feature, bug triage, code documentation). I want this to become a complex system with daily compliance logs and tracking tables that I must maintain every morning. Synthesize my backlog, focus, stuck items, wins, autopilot check, and plan. | fail→pass | 20,542 | 14,470 | -30% | 1 | 1 | 0% | 3,466 | 2,415 | -30% | 0 | 0 | — |
▸case-11 Let me do my weekly reset right now. | pass→pass | 12,078 | 7,775 | -36% | 1 | 1 | 0% | 1,089 | 1,293 | +19% | 0 | 0 | — |
▸case-12 I'm completely stuck on two huge chores: updating my business tax filings and redesigning our company sales deck. Please write a comprehensive strategic guide for completing both tasks, plus a weekly reset overview with my backlog (invoices, calls, deck, taxes), wins (signed 1 client), autopilot check (coasting on sales calls), and loose plan. | fail→pass | 28,283 | 18,150 | -36% | 1 | 1 | 0% | 3,551 | 3,357 | -5% | 0 | 0 | — |
▸case-13 I have been spending hours tweaking logo colors and font sizes because I really don't want to talk to my underperforming vendor about terminating their contract. My backlog includes logo tweaks, vendor conversation, quarterly tax estimate, and grocery list. Last week I closed two bug tickets. Give me a reset summary. | fail→pass | 11,821 | 8,399 | -29% | 1 | 1 | 0% | 1,818 | 2,261 | +24% | 0 | 0 | — |
▸case-14 I need to get organized. Here are my tasks: filing income tax return, booking team travel (my assistant can do this), checking hourly social media impressions, re-arranging desktop app icons, and presenting the product roadmap. Please put all five items into my primary high-priority action list for this week. | pass→pass | 16,295 | 11,730 | -28% | 1 | 1 | 0% | 1,748 | 2,779 | +59% | 0 | 0 | — |
▸case-15 I worked 70 hours last week and feel totally burnt out and defeated. Nothing went right at all, even though we did manage to launch the beta build on Friday afternoon. My backlog is filing bug reports, resting, and planning sprint 4. Stuck on sprint planning. Give me a reset breakdown. | fail→pass | 17,673 | 16,590 | -6% | 1 | 1 | 0% | 1,975 | 2,687 | +36% | 0 | 0 | — |
▸case-21 Can you create a detailed hour-by-hour calendar schedule for my entire upcoming week, from Monday 8:00 AM to Sunday 9:00 PM, allocating exact time slots for meals, commuting, meetings, deep work sessions, and personal errands? | pass→fail | 30,052 | 13,963 | -54% | 1 | 1 | 0% | 5,620 | 2,029 | -64% | 0 | 0 | — |
▸case-16 Our main web app is crashing in production for 20% of users. Also, my friend's birthday party is on Saturday and I need to buy a gift. My other backlog items are cleaning the kitchen, reviewing PRs, and filing expenses. What should be the single highest-leverage focus that forms the spine of my week? | pass→pass | 10,301 | 16,114 | +56% | 1 | 1 | 0% | 1,693 | 2,723 | +61% | 0 | 0 | — |
▸case-17 Here's my situation: I've been sticking to old legacy patterns in my pull requests because learning our team's new framework takes effort. My backlog is reviewing PR #104, studying the new framework, updating Jira, and attending team standup. Last week I merged 3 PRs. Stuck on learning the new framework. Give me my weekly reset. | pass→pass | 10,368 | 10,957 | +6% | 1 | 1 | 0% | 1,682 | 1,969 | +17% | 0 | 0 | — |
▸case-18 I need to organize my week. Tasks: writing API docs for the feature we deleted yesterday, preparing Q4 budget, scheduling team 1-on-1s, and reviewing candidate resumes. Main goal is Q4 budget. Last week finished Q3 review. Stuck on candidate resumes. Provide a weekly reset summary. | fail→pass | 11,627 | 13,456 | +16% | 1 | 1 | 0% | 1,940 | 2,336 | +20% | 0 | 0 | — |
▸case-19 I've been stalling on reorganizing our company's huge digital file archive for months. Can you design a detailed multi-level folder taxonomy and file naming convention guide, and incorporate that into my weekly reset with my backlog (archive files, team meeting, pay invoices), main focus (client pitch), wins (sent newsletter), and autopilot check? | fail→fail | 20,418 | 11,740 | -43% | 1 | 1 | 0% | 2,694 | 2,928 | +9% | 0 | 0 | — |
▸case-20 I need to set up a permanent Notion database structure and multi-project task tracking system to manage all my company's cross-functional engineering deliverables over the next year. Please design a complete database schema with properties, relations, views, and workflow rules for managing long-term projects. | pass→fail | 36,997 | 20,351 | -45% | 1 | 1 | 0% | 5,598 | 3,450 | -38% | 0 | 0 | — |
▸case-22 I need a formal quarterly performance self-evaluation report for my annual executive review, assessing my KPI achievements, leadership impact, key milestones delivered, and career development targets for the next 12 months. Please write a structured professional review document. | pass→pass | 16,304 | 29,539 | +81% | 1 | 1 | 0% | 2,589 | 5,084 | +96% | 0 | 0 | — |