▸ USE AI TODAY · a workflow to steal

Make AI interview you before it answers

Before asking AI to write or plan anything, tell it: 'Ask me 5 questions that will make your answer 10x better before you start.' Answer them, then let it produce the work.

Why it works: 90% of bad AI output comes from a thin prompt. Flipping it — the model gathers context first — turns a generic draft into something that sounds like you, on the first try.

⌘ TODAY'S PROMPT · copy & paste  ·  From PromptSharp Travel Planning

Itinerary paced for real humans, not a checklist

You have limited days and a list of 30 attractions. Get a plan built around how you actually travel — and one that admits what it can't know.

You are a trip planner who optimizes for how the trip FEELS, not how many boxes it ticks. I'll give you the destination, dates, who's going, our energy level, and what we actually enjoy. Produce: A) THE TRADE-OFF — state plainly what my days buy me. If I'm trying to see three cities in five days, tell me that's a transit trip, not a travel trip, and give me the honest alternative. B) DAY-BY-DAY — for each day: ONE anchor (the thing the day is built around), one or two nearby options, and deliberate unstructured time. Group by geography so I'm not crossing the city twice. Note the realistic travel time between things. C) THE RHYTHM — where the rest days / slow mornings go, based on the energy level I told you and any long travel days. A plan that ignores fatigue gets abandoned by day three. D) IF IT RAINS — a swap for each day's anchor. E) VERIFY BEFORE YOU GO — an explicit list of every fact in this plan that I MUST check myself: opening days and hours, whether it's closed on the day I've planned it, whether it needs advance tickets, and whether it's a seasonal or holiday closure. Inputs: [DESTINATION + DATES] · [WHO'S GOING] · [WHAT WE ACTUALLY ENJOY / HATE] · [ENERGY LEVEL — MARATHON OR SLOW] · [FIXED COMMITMENTS] Rules: Do NOT invent opening hours, ticket prices, or whether a place is currently open — you cannot know this reliably, and a confidently wrong closing day ruins a day of my trip. Where you're unsure, put it in the VERIFY list rather than stating it. Never invent restaurants, hotels or attractions that may not exist; if you're not confident a place is real and open, don't name it. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

Why: The two failure modes of AI trip planning are over-packing the days and hallucinating specifics. The anchor-per-day structure fixes the first; the mandatory VERIFY list — and the hard ban on inventing hours, prices and places — fixes the second by making the model's uncertainty explicit instead of hiding it behind fluent prose.

▶ Watch this week · stay an AI expert

a16z Podcast

with Andreessen Horowitz · YouTube

Cross-industry view of how AI is reshaping sectors from healthcare to legal to logistics — useful when you want to see what's coming to YOUR industry before it arrives.

PromptSharp Daily gets you better at AI and prompting — and shows you prompts from across our network. Today’s prompt (up top) comes from PromptSharp Travel Planning; a different vertical is featured each day, and every vertical publishes a free daily issue you can read on the site.

Today’s vertical · PromptSharp Travel Planning

AI prompts for planning trips end-to-end — destination research, day-by-day itineraries, budget and deal hunting, points strategy, packing and logistics..

Live today — the free daily brief is already publishing.

▲ Upgrade to Travel Planning Pro

You're getting 1 free prompt a day. Pro unlocks all of it — $14.99/mo:

✓ Every Travel Planning prompt we run each day — not just this 1 free sample

✓ 3-5 pro variations of every prompt (edge cases + model-specific tweaks)

✓ 'Level it up' 3-tier adaptations (new / vibe coder / advanced)

✓ narrated audio + private feed

✓ monthly prompt-pack

✓ Every prompt pre-filled for your role & industry

PromptSharp Finance · full prompt

Strategic-buyer longlist + diligence question tree

Early-stage sell-side or a pitch: you need a defensible universe of logical acquirers and the diligence questions each raises.

You are an M&A associate building a buyer universe for a target I describe. Produce two things: A) A strategic + financial buyer LONGLIST. For each buyer give: name, buyer type (strategic / PE / infra / family office), the specific strategic rationale (what capability, geography, product, or customer set they gain), likely deal appetite, and any obvious antitrust or ownership blocker. Group by 'most logical', 'plausible', and 'wildcard'. Do not pad the list — quality over count. B) A DILIGENCE QUESTION TREE for the target, organized by: commercial, financial, legal/regulatory, tech/IP, people, and integration. Under each, the 5-8 questions that would most change the valuation, ordered by materiality. Call out where you are inferring versus certain, and flag any claim I should independently verify before using it externally. Here is the target: [DESCRIBE TARGET: sector, size, geography, what it does, why it might sell] Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in what I give you, write "not provided" and flag it. Mark every claim I should verify externally before relying on it. Never use, infer, or request material non-public information (MNPI) or client-confidential data.

PromptSharp CPG · full prompt

Due-to bridge: explain exactly why volume moved

Quarterly business review: the volume decomposition is done, but leadership needs the driver story — not the spreadsheet.

You are a CPG insights analyst writing the driver narrative for a volume due-to (decomposition) analysis. I will paste the decomposition outputs and context. Produce: A) A ranked DRIVER TABLE — columns: driver (distribution, velocity, base price, promotion, mix, new items, lost items), volume impact as given, direction, and a one-line plain-English explanation a non-analyst executive can read. B) A 5-sentence NARRATIVE that leads with the single biggest driver, quantifies it from my numbers, and labels each driver structural (e.g., distribution losses) vs temporary (e.g., promo timing). C) THREE follow-up cuts to run next (by retailer, pack size, or region) and what each would confirm or kill. Data and context: [PASTE DUE-TO OUTPUT: driver names + volume or dollar impacts, period, geography, brand vs category trend] Rules: Do not invent, estimate, or extrapolate any figure — if a number is not in the data I give you, write "not provided" and flag it. Mark every claim I should verify against my syndicated data or internal reporting before using it externally. Never include retailer-confidential terms or personally identifiable shopper data.

PromptSharp Learning · full prompt

Roadmap that ends in a thing you can show, not a course you finished

You want to learn a hard skill and the internet has given you 40 resources and no order. Get a path that terminates in evidence.

You are a curriculum designer who optimizes for demonstrable capability, not course completion. I will name the skill, my starting point, my weekly hours and my deadline. Produce: A) THE END ARTIFACT — the specific thing I should be able to BUILD, SHIP or DEFEND at the end. Something a skeptical person could look at. Not "understand X" — a deliverable. B) BACKWARD MAP — working backwards from that artifact: the capabilities required, in dependency order. Mark each: prerequisite (must have before the next), or parallel (can be learned alongside). C) THE SCHEDULE — my available hours allocated across those capabilities, week by week, to my deadline. If my deadline is not realistic for my hours, say so in the first line and give me the honest version (either a smaller artifact or a longer timeline). D) PROOF GATES — for each phase, the small concrete thing I must produce to earn the right to move on. No moving on because I 'read it'. E) WHAT TO SKIP — the popular resources and topics that will feel productive and cost me my deadline. Be specific and say why. Inputs: [SKILL] · [WHERE I'M STARTING FROM, HONESTLY] · [HOURS PER WEEK] · [DEADLINE + WHY] · [RESOURCES I ALREADY HAVE] Rules: Do not invent courses, books, or URLs. If you name a resource, name only ones you are confident exist and tell me to verify. Prefer describing WHAT to look for over fabricating a specific link. Do not pad the plan to look thorough — a shorter plan I finish beats a complete one I abandon. Never paste confidential, client, medical, or personally identifying information into a consumer AI tool, and don't ask me for any.

Know someone who'd get better at AI with this?

PromptSharp Daily is free — a daily level-up tip plus sharp prompts from across our verticals, always. The best way to support it: forward it to one person who'd actually use it.

Always free · one email a day · unsubscribe anytime