AI Prompt Pack by Profession

23: Accountant, Clinic front desk, Coaching institute, Content creator, Customer support, Designer, Developer, Event photographer, Founder, Freelancer, Gym marketing, HR, Kirana shop, Marketer, Obsidian AI, Project manager, Real estate agent, Researcher, Sales, Salon marketing, Student, Teacher, Travel agency. Pick one at the top of the tool; the page link updates (for example ?v=accountant) so you can bookmark or share that exact view.

Only with anonymised data and within your firm's and regulator's policies. These prompts are designed to work from figures, rule text and situations rather than names — but you remain responsible for what you paste, so strip client identifiers and check the assistant's data-handling terms before using real balances.

Appointment reminders are treated as part of treatment, so a separate authorisation is not normally required, but the minimum necessary standard still applies to what the message says. Keep the reason for the visit, the department and any result out of an SMS or voicemail — date, time, place and a call-back number are enough.

Not without proof. The CCPA's Guidelines for Prevention of Misleading Advertisement in Coaching Sector, 2024 treat success-rate claims made without the underlying enrolment and selection figures as misleading. Publish the count and its denominator — "31 of 118 students in the 2024 batch" — instead of a bare percentage.

About 145 words at a normal conversational pace of 145 words per minute, or roughly 175 words if you deliver it at short-form energy. The formula is words = seconds ÷ 60 × words-per-minute, so a 30-second Reel at 175 wpm needs about 88 words.

Aim for a Flesch-Kincaid grade level of about 6 to 8, which corresponds to a Flesch Reading Ease score in the 60-80 range. That is roughly the reading level of a popular newspaper and it stays readable for people reading on a phone, in a second language, or while frustrated.

Give it four things: a role, the specific artefact, the constraints it must respect, and the exact output format you want back. A prompt that says 'critique this screen' returns taste; one that says 'critique in this order, give observation, user impact and one concrete change, and separate blocking issues from polish' returns something you can act on.

Give it the exact symptom, the stack, what changed around onset, and what you have already ruled out — then ask for ranked hypotheses with a cheap test for each rather than a single answer. The debugging prompt here also asks for the one test that splits the hypothesis space roughly in half, which is the fastest first move.

At a typical event pace of 200 to 300 frames an hour, an eight-hour wedding produces roughly 1,600 to 2,400 raw frames, of which 15% to 25% are usually delivered. At 30 MB per RAW that is about 47 to 70 GiB on the card before any backup copies.

Specific context and an explicit output structure. A prompt that names your stage, customer and the exact sections you want back removes the model's need to guess, which is why every prompt here carries your company details and a fixed deliverable format.

Welcome the idea, restate what the agreement covers as shared fact, then present the impact in hours and dates so the trade-off is the client's to weigh. The scope-creep prompt structures exactly that reply in under 150 words, with a firmer variant for repeat offenders that introduces a change-request process.