Prompt Cards

Propose a federated learning setup for {{health_use_case}}. Cover: on-device feature extraction, secure aggregation, bias checks, consent UX, and fallbacks for low-resource devices. Define model+data drift monitoring and participant incentives.

Integrate {{product_concept}} with local renewable availability. Design features for: flexible task timing, user consented deferral, battery/thermal storage coordination, and user-visible carbon savings. Include a demand response API spec and UX flows.

If hardware is involved, propose a modular design and service model. Include: parts commonality, teardown steps, spare parts catalog, refurbishment flows, take-back logistics, and warranty terms that encourage repair. Add KPIs for reuse rate and landfill diversion.

Create a co-design program for {{city_or_region}} involving residents and SMEs. Plan: recruitment, consent, workshops, surveys, walk-alongs. Synthesize pain maps (heat, noise, walkability, green access) and propose app interventions. Define success metrics and equity checks.

Define features for {{product_concept}} that support healthy behavior: - Movement nudges, posture checks, digital well-being timers - Low-blue-light themes and sleep-friendly notifications - Opt-in physiological metrics and strict data minimization Add a misuse/overuse risk table and guardrails.

For {{flow}} identify dark patterns to avoid and sustainable patterns to adopt. Produce microcopy and UI nudges that lower energy usage, promote breaks, and encourage active choices (opt-in tracking, low-bitrate by default). Provide accessibility/wellness notes and an A/B test list.

Create an LCA-first plan for {{product_concept}} across stages: materials → manufacturing → distribution → use → end-of-life. Include: hotspots, avoidance strategies, modularity, repairability, recycled content, packaging. Define 10 metrics (incl. emissions avoided) and a quarterly review ritual.

Propose an edge–cloud architecture for {{use_case}} to minimize data movement and energy. Deliver: - What runs on-device vs edge vs cloud - Compression/feature extraction strategy - Federated learning or distillation plan - Privacy + wellness impacts - Energy and latency budget per stage Output a diagram description and deployment checklist.

Design a carbon-aware scheduling policy for {{workload_type}} on {{cluster_desc}}. Include: - Grid carbon intensity inputs ({{region_codes}}) + renewable forecasts - GPU tactics: mixed-precision, quantization, sparsity, gradient checkpointing - Job classes: deferrable vs latency-critical - SLA-safe shifting windows and priority queue rules - Emissions accounting: Scope 2 location vs market-based Provide a pseudocode scheduler and test scenarios.

Map {{product_concept}} to SDGs (3,7,9,11,12,13,15). For each feature idea: - Which SDG target(s) does it serve? - Expected planetary impact (qual/quant) - Human health impact (sleep/stress/activity/diet proxies) - Risks/harms + mitigations Output a prioritization matrix (impact x effort) and a 90-day plan.

Generate a Twitter/X thread prompt starting with 'If you’re in CS (or any tech field), listen up:' explaining why C/C++ + fundamentals = strong foundation, and Python = career booster. Make it witty, yet caring for the reader’s growth.

Write a prompt in the style of a caring mentor who says: 'Learn C/C++ and fundamentals to know how the machine really works, then learn Python to ride the future wave of AI and automation.' Keep it fun, motivating, and reassuring.