Design or audit a feature store — serving, freshness, and sharing across models. Use when asked "do we need a feature store", "design a feature store", or "share features across models".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design and configure model serving infrastructure — endpoint scaling, batching, GPU allocation. Use when asked to "serve this model", "design an inference endpoint", or "size GPU allocation for serving".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design embedding pipelines — model selection, batching, normalization, index refresh strategy. Use when asked to "design an embedding pipeline", "which embedding model should we use", or "how should we batch embeddings".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit cloud spend — identify waste, rightsizing opportunities, and reservation gaps. Use when asked "our cloud bill is too high", "find cloud waste", or "where can we rightsize".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design eval harnesses — task schemas, metrics, dataset versioning, eval-as-code patterns. Use when asked to "build an eval harness", "set up eval-as-code", or "version our eval datasets".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Spec or critique custom illustrations — style, composition, and brand alignment. Use when asked to "spec an illustration", "critique this illustration", or "define an illustration style".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Cold outbound sequence builder — produces multi-touch email + LinkedIn sequences (5-7 touchpoints) personalized by persona type (technical buyer, economic buyer, champion). Use when asked to "write cold emails", "build an outbound sequence", "create prospecting emails", "write my LinkedIn outreach", or "design a cold email campaign".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Write sales playbooks — outbound sequences, discovery call guides, objection handling scripts, and demo frameworks. Use when asked to "write a sales playbook", "build an outbound sequence", "help me handle objections", or "design a discovery call".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design pricing strategy and packaging — tiers, value metrics, enterprise pricing, freemium design, and pricing page copy. Use when asked to "design our pricing", "should we change our price", "how do we package the product", or "what should we charge enterprise".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
B2B proposal generator — takes deal context (ICP, pain, pricing tier, timeline) and produces a complete proposal document with executive summary, problem statement, solution, pricing table, implementation timeline, ROI case, and next steps. Use when asked to "write a proposal", "draft our deck for this deal", "build a proposal for this customer", or "generate a proposal".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
MEDDPICC-based deal qualification worksheet — guide Deal through structured qualification of any opportunity and produce a filled card + recommended next action. Use when asked to "qualify this deal", "run MEDDPICC on this opportunity", "should we pursue this", or "is this deal real".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Revenue reconnaissance — audit current sales pipeline, deal patterns, ICP definition, and revenue motion to understand what's working and where the constraint is. Use when asked to "audit our sales", "where is revenue stuck", "what's our pipeline state", "before designing a playbook".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Close a specific deal — diagnose why a deal is stalling, answer an objection reply, write a tailored proposal, design the closing sequence, or navigate procurement. Use when a specific deal is stuck, "how do I close this", "write a proposal for this customer", "help me get to yes", or "how do I answer this objection".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan and execute canary releases for model updates — traffic splitting, rollback triggers, success metrics. Use when asked to "canary the new model", "roll out this model safely", or "set up a traffic split for a model update".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit current model deployment topology — serving config, latency profile, version inventory. Use when asked "what models are deployed", "audit our serving setup", or "inventory our model versions".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Information architecture — design navigation structure, content hierarchy, sitemap, and taxonomy for a product or feature set. Use when asked to "organize the navigation", "information architecture", "how should content be structured", "sitemap", "nav redesign", "where should X live", or "content hierarchy".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Hi-fi interactive HTML prototype — single-file, double-click-to-open, Playwright-verified. Use when asked to "make it clickable", "build a prototype", "hi-fi mockup", "interactive demo", "iOS prototype", "app mockup", "ui demo", or "prototype this". Goes beyond wireframes into visually finished, state-driven HTML with device frames and real images. Not production code — a design artifact for testing flows and pitching ideas.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
UI and UX reconnaissance — scan existing frontend routes, components, navigation, and flows to understand the current UX state before designing. Use when asked to "understand the current UI", "what UX patterns exist", "map the navigation", "what screens exist", or before starting any flow or wireframe work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Usability review — evaluate an existing flow or UI against usability heuristics, flag friction points, and recommend fixes. Use when asked to "review the UX", "usability audit", "what's wrong with this flow", "UX feedback", "critique this design", or "why are users dropping off here".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
UX designer — user flows, information architecture, wireframes, and interaction design. Use when asked to "design a user flow", "map the IA", "wireframe this screen", or "review UX before shipping".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design drift alerts and escalation — thresholds, runbooks, and retrain triggers. Use when asked to "alert on model drift", "when should we retrain", or "write a drift escalation runbook".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design a drift monitoring system for a production ML model. Use when asked to "monitor this model in production", "detect data drift", or "set up ML monitoring".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit existing ML monitoring — find gaps in drift coverage and missing alerts. Use when asked to "audit our ML monitoring", "are our models monitored", or "find drift coverage gaps".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Feedback synthesis — cluster support tickets, NPS verbatims, app store reviews, and churn surveys by theme, separate signal from noise, and produce an actionable insight report. Use when asked to "synthesize this feedback", "analyze support tickets", "what are users complaining about", "NPS analysis", "churn feedback synthesis", or "what's the feedback telling us".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.