Practical AI

Give Alexa for Shopping two model names and your floor type. Request a comparison of weight, power source, filter costs and recurring complaints, plus available price history. Allow 20 minutes. Check the manufacturer pages and one other seller. Keep a shortlist with unanswered questions; buying is optional.

In Gemini Notebook, add your exact model’s public manual. Ask for a one-page routine-care checklist using only that document, with citations and safety warnings. Give it 20 minutes. Verify every step and interval; mark missing information as unknown. Save a checked copy beside the appliance.

In Google AI Mode, name your city and waste provider, then ask how to dispose of cardboard, takeout containers, old clothing and small electronics. Request a four-item checklist using current official pages. Allow 15 minutes. Open every link and verify local rules and dates before keeping the list.

Ask AI for a cardboard phone-stand pattern using dimensions you supply. Draw it full-size, check every unit, then make a mock-up from scrap card. Test with a phone-sized, similarly weighted dummy over a soft surface. About 45 minutes with chat, ruler and card. The output is an unverified prototype.

Write one instruction for a fictional workshop’s tone and another for its announcement format. Test each separately, then together, on three invented workshops. About 25 minutes in any text chat. Score factual preservation, format and tone yourself. Keep the winning recipe only if combining instructions preserves every requirement.

Invent an exhibition announcement with six required facts. Ask AI to adapt it into a poster, square card and narrow mobile banner in your existing design tool. Allow 30–40 minutes. Check every fact and view each design at its intended size. Keep the venue fictional; nothing needs publishing.

Make a clearer introduction in 20 minutes. Give ChatGPT Voice a fictional service, its audience and three facts it must preserve. Deliver a two-minute pitch; ask it to play a curious customer with three follow-up questions. Rewrite a 90-second script from the exchange. Use a stopwatch, verify every claim and leave out confidential information.

In about 25 minutes, explore three campaign looks for one product. Open a copy of your own photo in Photoshop desktop, remove its background and generate studio, café and outdoor settings. Save a three-image comparison. Check edges, logos and shadows against the original; reject altered product details. Label these AI-generated concepts. Generation may consume credits.

Test a booking idea before building it. In Claude on the web, with code execution and file creation enabled, describe three screens for a fictional workshop: choose a session, select seats, confirm. Request a clickable artifact using invented data, with no payments or external connections. In 30–40 minutes, aim for a working demo. Try back buttons, empty selections and keyboard navigation; list three fixes.

Give AI six invented filenames and a promised-deliverables list. Include an outdated duplicate and a missing item. Request a client-ready index and a separate exception list, then compare with the planted defects. About 25 minutes using chat or a spreadsheet; no files are moved or deleted.

Create three short fictional business FAQs with conflicting opening hours and turnaround times. Ask AI for a conflict list with exact source references and questions for the owner. Success means surfacing disagreements without choosing an unsupported answer. About 20 minutes in text chat.

Compare a fictional photography request with a draft quote. Ask AI to flag missing quantities, dates and delivery details, citing both texts. Plant three omissions and check how many it catches without inventing terms. About 20 minutes in text chat; nothing is sent.

Pick a low-stakes choice and generate five cards: optimistic, ordinary, difficult, surprising and “do nothing.” Each gets an early warning sign and a reversible next move. About 30–45 minutes with chat and a document template. Omit sensitive health or financial details. Generated probabilities are not forecasts; high-stakes decisions need qualified advice.

Make a one-page label for today’s three Copilot replacements: access, price, benchmark owner, missing tests, safety evidence, deprecation risk and data handling. Highlight unknowns instead of guessing. About 40 minutes with vendor documentation and a document tool. Separate vendor claims from independent measurements; do not upload proprietary code.

Choose a public-domain historical photograph. Ask AI to identify visible clues, build a dated evidence table from archives, maps and newspapers, and propose a modern re-photography angle. Allow 60–90 minutes. Mark uncertain identifications, avoid naming private people from weak clues and never present reconstruction as documentary fact.

Log ten algorithmic nudges in a day, such as routes, spam filters or photo enhancement. Ask AI to classify visibility, reversibility, evidence and the cost of error; extend it over seven days if useful. Allow ten minutes daily and 30 minutes to review. Keep names, locations, health and financial details out.

Run 12 scripted exchanges: four interruptions, four language switches and four noisy-room phrases. Record response timing, correction success and whether the assistant talks over you. About 35 minutes with an existing voice assistant, stopwatch and spreadsheet. Avoid sensitive conversations or other people’s voices. Optional API tests may cost money; one trial is exploratory.

Ask AI to hide a public-domain photograph and extract five constraints: camera height, light direction, geometry, emotional temperature and one forbidden element. Shoot your own frame before seeing the source. Allow 45–90 minutes with chat and a camera. Get consent for identifiable subjects and remove location metadata before sharing.

Give AI ten questions on a subject you know, including two unanswerable ones. Request confidence estimates and evidence that would change each answer, then score accuracy and willingness to admit uncertainty. About 20 minutes with chat and a table. Self-reported confidence is a claim, not a measured probability.

Record 30 seconds of public outdoor ambience. Ask AI for time-stamped observations, a color palette and a six-frame storyboard, then compare its mood with yours. About 25 minutes using audio-capable AI or written sound notes. Avoid identifiable conversations and private locations; label uncertain sound identifications.

Choose 12 low-resolution photos you own. Hide filenames and independently pick three alongside AI, using identical criteria. Compare the choices and disagreements. About 25 minutes with image-capable chat and a contact sheet. Use shareable images, remove location metadata and exclude client identities. Originals stay untouched.

Turn one photograph into a short description and a 60-second audio-guide script about composition, texture and intent. Compare AI’s observations with yours. About 20–30 minutes; optional voice generation may use credits. Separate visible facts from interpretation and avoid inferring identity or private traits.

Build six fictional locations and three witness statements containing one impossible journey. Solve it using distance and time, then make AI solve your version. About 20 minutes with a drawing tool and calculator. Verify distances; no real addresses or location history are needed.

Record a two-minute explanation of how you would dodge and burn one photograph. Ask AI to turn it into a numbered print map with your reasons. Allow 20–30 minutes using annotation and transcription tools. Work from a copy, preserve the original and verify every marked region.