Prompt Cards

Design a time-decay model that boosts fresh, authoritative sources. Include publisher priors, sitemap/news bias, and re-crawl triggers. Output evaluation with time-split test sets.

Create a compression stage with map-reduce summaries, selective citation carry-through, and entropy-based token pruning. Provide metrics (coverage, faithfulness) and an ablation plan.

Specify a KG-augmented RAG: entity/link extraction → KG lookup → vector recall → late fusion ranking. Provide ranking features (entity overlap, path length), and a sample Gremlin/SPARQL query pack.

Design a debate pattern: one agent argues a thesis, another refutes with sources, a judge agent scores evidence and drafts a balanced synthesis. Provide rubric, tie-breaker rules, and output template.

Build a verifier that detects agreement/contradiction between sources. Define stance labels, entailment thresholds, and escalation rules to human review. Output a confusion matrix target and fallback messaging.

Create an algorithm that decomposes complex prompts into sub-questions, selects tools per hop, and merges evidence. Provide pseudocode, scoring for hop-utility, and examples for science, law, and finance queries.

Design a retrieval pipeline that enforces source-anchored answers. Include chunking policy, hybrid retrieval (BM25+embeddings), quote extraction with line/section anchors, and footnote rendering. Output a reference implementation outline and QA checklist.

Act as a principal architect. Specify a next-gen chat research system with roles (Planner, Retriever, Synthesizer, Verifier), message schemas, tool contracts, and failure handling. Deliver a C4 diagram, sequence charts for 1/3/5-hop queries, and a minimal API spec for each role.

Develop a cross-industry launch narrative and visual identity for a concept aircraft, car, and magazine feature package. Provide logotype sketches, motion rules, and a press-ready asset checklist.

Create a unified token system (color, type scale, spacing) that maps to vehicle HMI, avionics UI, and magazine digital styles. Provide naming, theming, and accessibility tests.

Propose a simulation-first strategy: CFD for wings and exteriors, multibody for suspension, click-models for magazine UX. Define model fidelity tiers and validation plans.

Define a weekly critique: aircraft (aero/perf), car (HMI/safety), magazine (legibility/flow). Provide checklists, scoring rubrics, and decision logs.