Curated AI prompts for business, creative, and technical use cases.
Works well with Claude Sonnet 5 or GPT-5.4. Any model with strong long-context reasoning handles the segmentation step; shorter-context models can still draft individual messages one contact at a time.CareerYou've been at the same company for four years, have quietly started exploring a Director-level move, and realize your LinkedIn network is 300+ people — half of whom you haven't spoken to since a conference or a previous job — and you have no idea where to even start reactivating it without looking like you only show up when you need something.
Um prompt estruturado que segmenta seus contatos profissionais desatualizados por valor estratégico e grau de proximidade, depois gera mensagens específicas e nada genéricas para reconexão, e ainda regula o ritmo da sua abordagem para que nada pareça transacional.
Careerjob-search
Works well with Claude Opus 4.8 or GPT-5.4 for nuanced tone-matching across channels; Claude Sonnet 5 handles shorter transcripts fine at lower cost.marketingYou just finished five 30-minute customer interviews for a case study project. You have five raw transcripts, roughly 45 minutes of usable content buried in filler words, tangents, and repeated phrasing, and marketing needs three strong quotes for a landing page redesign by Friday.
Um prompt que pega transcrições bagunçadas de entrevistas com clientes, anotações de chamadas de suporte ou textos de avaliações e extrai citações de depoimentos prontas para uso, organizadas pela objeção ou caso de uso específico que cada uma aborda.
prompt-engineeringmarketing
Works best with Claude Opus 4.8 or GPT-5.4 for the reasoning depth needed to rank causes by plausibility; Claude Sonnet 5 is a solid faster/cheaper alternative for routine metric checks.Data AnalysisYour weekly signup dashboard shows conversions dropped 18% starting Tuesday. You don't know if it's a pricing page bug, a marketing campaign that ended, a competitor promotion, seasonality, or a tracking error — and your team is about to spend the next two days randomly checking each one.
Um prompt estruturado que pega uma anomalia métrica (pico, queda ou platô em qualquer KPI) mais o contexto sobre seus sistemas e mudanças recentes, e retorna uma lista ranqueada e ponderada por evidências de causas prováveis com uma verificação específica seguinte para cada uma.
prompt-engineeringdata analysis
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — any model that follows structural constraints reliably)Developer ToolsAn on-call engineer has a payments API outage from 2am with only scattered Slack timestamps and half-remembered details, and needs to turn that into a clear, professional postmortem before Monday's leadership review — without spending two hours writing it from scratch or accidentally writing something that reads like it's blaming a specific teammate.
Um prompt estruturado que transforma anotações caóticas de incidentes em um postmortem profissional e sem culpa — com uma timeline real, uma causa raiz distinta e no máximo cinco action items atribuíveis.
incident-responsesre
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — any model with strong structured reasoning)learningA backend engineer with four years of Python and PostgreSQL experience wants to move into a Machine Learning Engineer role within four months, has 8 hours a week to study, and has no idea whether to start with math fundamentals, a specific framework, or a portfolio project first.
Um prompt estruturado que mapeia exatamente a lacuna entre suas habilidades atuais e um cargo alvo, e então constrói um plano de aprendizado semana a semana com checkpoints reais — não apenas uma lista de leitura.
career-developmentlearning-plan
Claude Opus 5 (also works well with GPT-5.4 and Gemini 3 Pro)creativeYou have 4 minutes on the agenda at next week's board meeting to explain why the company's new fraud-detection model reduces false declines, and the board has finance and legal backgrounds with zero machine learning experience — a slide full of precision and recall numbers will lose them in the first 20 seconds.
Um prompt que gera cinco metáforas visuais distintas e testadas em audiências para qualquer conceito complexo, completo com visuais de slides, frases faladas e uma classificação de risco para cada uma — para que você não fique adivinhando qual analogia funcionará com seu público específico.
communicationpitch-deck
Claude Opus 5 (also works well with GPT-5.4 and Gemini 3 Pro — any model with a large context window for pasting full contract text)finance-negotiationYour company's project management SaaS vendor sends a 22-page renewal agreement three business days before the auto-renewal deadline. Legal review normally takes a week, but you need to know today whether anything in the contract needs to be pushed back on before you sign or let the renewal window close.
Um prompt que lê um contrato de fornecedor, sinaliza as cláusulas que realmente criam risco e redige o texto de redline exato e os pontos de negociação para cada uma — em vez de um resumo genérico de "leia este contrato".
Negotiationlegal risk
Works with any capable model with a large context window (Claude Sonnet/Opus, GPT-5 tier, Gemini 3 Pro) — needs enough context length to hold a full meeting transcript, so avoid small/fast tiers for long recordingsWriting & CommunicationA product manager just left a 45-minute cross-functional planning meeting between engineering, design, and marketing about a delayed Q3 feature launch, and needs to send a decision recap within the hour — before people's memories of who-agreed-to-what start to diverge — but manually re-listening to the recording or notes to reconstruct exactly what was agreed would take 20+ minutes and still risk missing a contradiction between two speakers.
Pare de deixar que 'vamos resolver depois' seja registrado em uma ata como uma decisão firme. Este prompt separa o que foi realmente acordado daquilo que apenas pareceu acordado.
prompt-engineeringproductivity
Works with any frontier reasoning model (Claude Opus/Sonnet, GPT-5 tier, Gemini 3 Pro) — pair with a quick web check for current per-token pricing, since the model's training data may lag real-time rate changesArtificial IntelligenceA support-team lead needs to route 40,000 monthly customer tickets into 12 categories with a suggested first-response draft, must stay under 3 seconds per ticket, keep costs under $2,000/month, and cannot send EU customer PII outside the EU — but has no AI infrastructure background to know which model tier fits those constraints without expensive trial and error.
Pare de usar o modelo mais caro como padrão para todas as tarefas. Este prompt cria uma comparação de custo/latência/qualidade entre diferentes níveis de modelos e oferece uma recomendação fundamentada, não um palpite.
prompt-engineeringinfrastructure
Claude Opus 4.7 (works well with GPT-5.4 and Gemini 2.5 Pro; needs a model with strong structured-table output)Startups & BusinessA 12-person SaaS company just wrapped a quarterly strategy offsite with a completed SWOT analysis on a whiteboard — churn is flagged as a weakness, rising AWS costs as a threat, a competitor's weak enterprise tier as an opportunity — but the founder has to walk into Monday's all-hands with a concrete 30-day plan, not a photo of a whiteboard nobody will look at again.
Um prompt que pega uma análise SWOT completa e a converte em um plano de ação semana a semana de 30-day action plan com owners, prazos e métricas de sucesso — para que a sessão de estratégia realmente mude o que seu time faz na segunda-feira.
prompt-engineeringstartup-strategy
GPT-5.4, Claude Sonnet 5, or any reasoning-capable model — works best with one that can hold both weeks' context and reason about relative priority, not just summarizeproductivityIt's Monday morning, you have 15 minutes before your first meeting, and you have a messy calendar export plus a half-remembered sense of what mattered last week — you need an honest read on where your time actually went, not just a to-do list for the next five days.
Transforme uma semana bagunçada de tarefas e reuniões em um scorecard honesto contra suas prioridades reais, além de uma lista classificada para a semana seguinte — não apenas mais uma to-do list.
prompt-engineeringproductivity
GPT-5.4 or Claude Sonnet 5 — any frontier model with a large context window handles this well; feed it the full article text, not a summarymarketingYou just published a 1,500-word blog post analyzing a major industry report, and your social calendar for the week is due in 20 minutes — you need 10 genuinely different posts, not the same headline copy-pasted across five platforms.
Transforme qualquer post de blog em 10 posts sociais genuinamente distintos e nativos de plataforma em uma única passada — não o mesmo título copiado e colado cinco vezes.