AIO APEX

Prompts

Curated AI prompts for business, creative, and technical use cases.

The Self-Review Builder: Turn Rough Accomplishment Notes Into Polished Performance Review Bullets
Works well with any current-generation model (Claude Sonnet/Opus, GPT-6 Sol/Astra, Gemini 3) — the task is structured rewriting and gap-flagging, not deep reasoning, so a mid-tier model is sufficient.It's the week before performance review season, and you have a scrappy list of six months of Slack standups and sprint notes but no idea how to turn “helped ship the new onboarding flow” into something that reads well in a formal review.

The Self-Review Builder: Turn Rough Accomplishment Notes Into Polished Performance Review Bullets

A prompt that applies the XYZ formula to messy work notes, producing both a conservative bullet you can use today and a stretch bullet that flags exactly which metric you're missing.

prompt-engineeringCareer
The Customer Discovery Interviewer: Turn a Product Hypothesis Into Questions That Can Actually Kill It
Works well with Claude Opus 5.5 or GPT-6 Astra for nuanced follow-up question design; a lighter model like Claude Haiku or GPT-6 Luna handles the base question generation fine once you already have a validated hypothesis to start from.You're a solo founder or product manager about to run eight customer discovery calls this week to test a new B2B feature idea, and you need a question set that won't just produce polite, meaningless validation.

The Customer Discovery Interviewer: Turn a Product Hypothesis Into Questions That Can Actually Kill It

A structured prompt built on the Mom Test methodology that generates 20 discovery interview questions designed to surface real signal — not polite agreement — before you build anything.

prompt-engineeringstartups
The Illustration Brief Builder: Turn a Vague Visual Idea Into a Precise, On-Brand AI Image Prompt
Works with any text-to-image model — Flux, Nano Banana Pro, Midjourney, DALL-E — since it outputs a structured natural-language prompt rather than model-specific syntax. For models with strict token limits, explicitly ask it to keep the final prompt under 50 words.creativeYou run a two-person fintech content team and need a hero image for tomorrow's blog post about AI-powered bookkeeping for small businesses. You have no designer, no stock-photo budget, and all you can articulate is 'something about AI helping small businesses' — not nearly specific enough to get a usable result from an image model on the first try.

The Illustration Brief Builder: Turn a Vague Visual Idea Into a Precise, On-Brand AI Image Prompt

A prompt that turns 'something about AI helping small businesses' into a fully structured, ready-to-paste image prompt — plus an explanation of every ambiguous decision it made for you.

prompt-engineeringflux
The AI Vendor Claims Auditor: Turn a Sales Pitch Into a List of Questions That Expose Overselling
Works well with Claude Opus or GPT-5-class models for the strongest critical reasoning on ambiguous claims; a lighter model (Claude Haiku, GPT-5-mini) is usually sufficient for a short pitch deck rather than a full RFP response.Artificial IntelligenceYour operations team is three weeks into evaluating an AI-powered customer support platform for a 200-person SaaS company. The vendor's deck claims '95% ticket resolution without human intervention,' 'seamless integration with your existing helpdesk in under a week,' and 'enterprise-grade accuracy.' Nobody on the five-person buying committee has an AI engineering background, so no one in the room can tell which claims are standard industry performance and which are marketing inflation designed to close the deal before technical due diligence catches up.

The AI Vendor Claims Auditor: Turn a Sales Pitch Into a List of Questions That Expose Overselling

A prompt that extracts every testable claim from an AI vendor's pitch and turns it into a verification question, so a non-technical buying committee can catch overselling before signing a 12-24 month contract.

prompt-engineeringenterprise-ai
The A/B Test Interpreter: Turn Raw Experiment Results Into a Ship-or-Kill Decision
GPT-5.4 or Claude Opus 5 — requires strong statistical reasoning. Provide raw sample sizes and conversion counts, not just percentages; a model given only rounded percentages cannot compute a valid p-value or confidence interval.Data AnalysisA product manager runs a two-week A/B test on a new checkout flow, sees the treatment converting at 5.7% versus 5.0% for control — a promising-looking 14% relative lift — and needs to know before Monday's roadmap review whether that result is real or noise before recommending a full rollout.

The A/B Test Interpreter: Turn Raw Experiment Results Into a Ship-or-Kill Decision

A prompt that takes raw A/B test data and outputs a rigorous verdict — statistical significance, pitfall checks for peeking and sample ratio mismatch, and the exact additional sample size needed if the result is inconclusive.

prompt-engineeringdata analysis
The SEO Content Brief Builder: Turn a Target Keyword Into a Complete Writer-Ready Brief
GPT-5.4 or Claude Opus 5 — works with any frontier model that can process pasted competitor content. For the best competitor-gap analysis, paste actual scraped text from competitor pages rather than just URLs, since most models cannot fetch live pages.marketingA content marketer at a project-management SaaS startup gets assigned the keyword "asana alternatives for small teams" during Monday sprint planning, with nothing but the keyword and links to three ranking competitor articles, and needs a brief a freelance writer can execute the same day without a clarifying call.

The SEO Content Brief Builder: Turn a Target Keyword Into a Complete Writer-Ready Brief

A prompt that takes a keyword and competitor URLs and outputs a full content brief — search intent, outline, competitor gaps, word count, and SEO metadata — so writers never have to guess.

prompt-engineeringcontent-strategy
The Steelman Briefing: Turn a Position You Hold Into the Strongest Possible Case Against It
Works best with reasoning-focused models like Claude Opus 4.7 or GPT-5 Thinking, which can construct genuinely adversarial arguments instead of defaulting to agreement. Faster models like Claude Sonnet or GPT-5 mini tend to soften the counter-case unless explicitly pushed.learningYou're a product manager about to present a recommendation to skip building a competitor's flagship feature to your leadership team next Tuesday, and you've been inside your own reasoning for three weeks. You need to know what the sharpest person in that room is going to say before they say it — not a generic devil's-advocate pass, but the actual strongest version of the case against your call.

The Steelman Briefing: Turn a Position You Hold Into the Strongest Possible Case Against It

A prompt that builds the real counter-argument to your decision before someone in the room builds it for you — ranked by actual damage, not padded with weak objections.

decision-makinglearning
The SOP Extractor: Turn Messy Process Notes Into a Procedure Nobody Has to Guess About
Works best with reasoning-focused models like Claude Opus 4.7 or GPT-5 Thinking, which track structure across long, messy input without losing the thread. Claude Sonnet or GPT-5 mini handle shorter note sets fine.productivityYou're an operations manager at a 40-person logistics company, and the warehouse shift lead who has personally run the end-of-day inventory reconciliation for three years just gave two weeks' notice. The only existing documentation is a half-finished Google Doc from 2023 and a Slack thread where she explained parts of the process to a coworker six months ago. You need a real SOP before her last day, built from whatever fragments of explanation you can gather — not written from scratch.

The SOP Extractor: Turn Messy Process Notes Into a Procedure Nobody Has to Guess About

A prompt that pulls a real, followable procedure out of scattered notes, chat threads, and half-remembered explanations — and flags every gap instead of quietly filling it in.

productivitysop
The Budget Optimizer: Turn a Line-Item Budget Into Short-Term vs Long-Term Tradeoffs
Works well with Claude, GPT-4o/5, or Gemini — models strong at structured financial reasoning and multi-step tradeoff analysis. A longer-context model helps if your budget has many line items.finance-negotiationFinance just asked you to find $80,000 in savings from your department's budget for next quarter. You have a spreadsheet with 22 line items — software licenses, contractor spend, a training budget, a deferred infrastructure upgrade — and you need a defensible recommendation by end of day, not just a list of the biggest numbers.

The Budget Optimizer: Turn a Line-Item Budget Into Short-Term vs Long-Term Tradeoffs

A prompt that evaluates every budget line on two axes — immediate savings and hidden long-term cost — and flags cuts that look good now but cost more later, with the breakeven point spelled out.

prompt-engineeringfinance
The Tone Transformer: Turn One Message Into Four Ready-to-Send Versions
Works well with Claude, GPT-4o/5, or Gemini — any model strong at maintaining consistent tone across variants. A longer-context model helps if the original message is lengthy.Writing & CommunicationYou need to tell a long-standing client their project is delayed by two weeks. The client has pushed back hard on deadlines before, and you have five minutes before a scheduled call to decide how bluntly to deliver the news.

The Tone Transformer: Turn One Message Into Four Ready-to-Send Versions

A prompt that rewrites any high-stakes message in four distinct tones — Direct, Diplomatic, Enthusiastic, Formal — so choosing the right register takes seconds instead of 15 minutes of second-guessing.

prompt-engineeringproductivity
The Unlikely Explainer: Turn a Complex Topic Into a Dialogue Between Two Characters Who Would Never Meet
Claude Opus 4.8 or GPT-5.4 (both hold character voice consistently across a full dialogue); avoid smaller/faster models for this one, they tend to flatten the two characters into the same voicecreativeA developer relations writer at an AI company has been asked to add a plain-English explanation of why language models hallucinate to the new-hire onboarding doc, after the third all-hands where a non-technical new employee asked why the AI just made something up. The existing explanation is three paragraphs of next-token-prediction jargon that nobody reads past the first sentence, and leadership wants something people will actually remember when a customer asks them the same question.

The Unlikely Explainer: Turn a Complex Topic Into a Dialogue Between Two Characters Who Would Never Meet

A prompt that forces an explanation to earn its keep through character voice and real analogies, instead of a jargon-dense paragraph nobody actually reads twice.

communicationonboarding
The Source Contradiction Mapper: Turn Conflicting Research Into a Clear Picture of What's Actually Known
Claude Opus 4.8 (best for long-context synthesis across many sources); GPT-5.4 and Gemini 3 Pro also handle this well up to 5-6 sourceslearningA product manager at a mid-size software company has been asked by leadership to recommend whether to expand AI coding assistant licenses from a 20-person pilot team to all 400 engineers. They have pulled five research reports and internal surveys that reach opposite conclusions about whether the tools actually help experienced developers, and need to brief the VP of Engineering by Friday without just picking whichever study confirms what leadership wants to hear.

The Source Contradiction Mapper: Turn Conflicting Research Into a Clear Picture of What's Actually Known

A structured prompt that refuses to average out disagreement between sources — it maps exactly where they agree, where they conflict, and why, so you can make a defensible call.

decision-makinglearning