Write a 30-second YouTube ad script for a used-car platform

## Role and objective

You are a US-focused advertising copywriter creating a 30-second YouTube advertisement for a used-car platform. Produce a complete spoken-and-visual ad script for prospective customers who may use the platform to find or buy a used vehicle. The script must promote the platform without inventing product capabilities, prices, inventory figures, guarantees, testimonials, or performance claims. Write for the audience and conversion goal specified in the supplied facts; if either is missing, use “[FILL IN: target audience]” or “[FILL IN: conversion goal]” rather than guessing. Deliver a production-ready script whose timed spoken content fits 30 seconds. Completion means every objective claim is supported by supplied evidence, every required slot is either filled from confirmed input or retained, and the final call to action clearly tells viewers what to do next.

## Scope and given facts

In scope:

- A YouTube advertisement.
- A used-car platform.
- A total runtime of 30 seconds.
- Spoken copy, visual direction, on-screen text, audio direction, and a final call to action.
- The audience, platform identity, approved claims, offer, destination, and conversion goal only when supplied or explicitly marked as slots.

Out of scope:

- A general brand strategy, campaign plan, landing page, sales email, product review, or dealership negotiation.
- Claims about vehicle quality, inspection, pricing, financing, delivery, returns, warranties, selection, safety, or savings unless confirmed.
- Statements about competitors or market leadership unless evidence and an approved comparison basis are supplied.

Confirmed input: the requested format is a 30-second YouTube ad script for a used-car platform. No platform name, audience, offer, product features, evidence, legal review status, tone, destination, or call to action was supplied. Use “[FILL IN: platform name]” for the approved brand name, “[FILL IN: confirmed platform feature]” for each verified capability, and “[FILL IN: destination or CTA]” for the viewer’s next step. These slots must be filled only with approved project information, not plausible guesses.

## Working rules

1. Establish the advertising job before writing. Use the supplied conversion goal if present. If it is absent, retain “[FILL IN: conversion goal]” and make the CTA correspondingly non-specific rather than inventing an app download, website visit, inquiry, or purchase action.

2. Treat every factual or objective statement as a claim requiring evidence in hand before publication. This includes prices, percentages, inventory counts, financing terms, inspection statements, delivery promises, guarantees, ratings, time savings, availability, and comparisons. If evidence is absent, remove the claim or mark it “[VERIFY: claim and evidence]”; do not convert it into an unsupported assertion.

3. If the platform’s confirmed capabilities are supplied, select only those relevant to the audience and fit them into the 30-second runtime. If no capabilities are supplied, use an emotional or situational setup and retain “[FILL IN: confirmed platform feature]” where a product benefit is necessary. Do not imply that the platform owns, inspects, finances, delivers, warranties, or guarantees vehicles unless the input confirms that role.

4. Use a simple sequence: identify a used-car search problem, introduce the platform as the confirmed solution, show the supported benefit, and end with the CTA. If the conversion goal is awareness rather than action, replace the action CTA with a brand-recall ending and retain “[FILL IN: awareness sign-off]” if no approved line exists.

5. Follow US advertising safeguards. Apply FTC Act substantiation: every objective claim needs evidence in hand before it runs. If the ad uses paid or incentivised creator content, mark “[VERIFY: FTC Endorsement Guides disclosure]” and specify its on-screen and spoken treatment rather than burying it in hashtags. If the concept touches health, financial, or children’s advertising, mark the applicable regime “[VERIFY: FDA]”, “[VERIFY: FINRA]”, or “[VERIFY: COPPA]” without assuming applicability or stating what it requires.

6. Avoid competitor comparisons unless a named competitor, comparison basis, measurement date, and supporting evidence are supplied. Otherwise, use no comparative wording.

## Output structure

Produce the following sections in this order:

1. **Concept and objective** — one or two sentences identifying the audience, conversion goal, and central promise. Retain missing values as slots.
2. **30-second script table** — use timed rows that total exactly 30 seconds. Include columns for time, visual, voiceover or dialogue, on-screen text, and audio. Allocate enough time for the CTA and any required disclosure. Keep spoken language natural at a pace that fits the assigned duration; revise or shorten lines rather than exceeding 30 seconds.
3. **CTA** — state the final viewer action or brand-recall line. Use “[FILL IN: destination or CTA]” when the action is not confirmed.
4. **Claims and evidence notes** — list every objective claim used and identify its supplied evidence. For unsupported claims, remove them or mark “[VERIFY: claim and evidence]”.
5. **Production and compliance flags** — identify “[FILL IN: platform name]”, missing approvals, disclosure needs, music or footage rights, and any applicable regime marked “[VERIFY]”.

Use a short, clear table for the timed script. Do not fill an unspecified price, discount, vehicle count, feature, guarantee, URL, or legal status with a plausible value.

## Style rules

Use a hybrid style. Present production details, timing, claims, evidence, and compliance notes in itemized or tabular form. Write the voiceover as concise, conversational narrative suitable for spoken YouTube advertising. Keep the register energetic but credible, avoiding hype, pressure tactics, vague superlatives, fear-based selling, and clichés such as “best deal ever,” “revolutionary,” “act now,” or “you won’t believe.”

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the deliverable is specifically a YouTube ad script for a used-car platform, not a general advertisement plan or vehicle sales article.
2. Add the durations in every script row and verify that they total exactly 30 seconds, including the CTA and any disclosure.
3. Read the voiceover aloud or estimate its spoken length and shorten it if it cannot fit its assigned timings.
4. Check that “[FILL IN: platform name]” remains unfilled unless the input supplied an approved name.
5. Check that no price, discount, vehicle count, financing term, inspection promise, warranty, delivery promise, guarantee, rating, or performance figure was added beyond the input.
6. Check that every objective claim has evidence in hand or is removed or marked “[VERIFY: claim and evidence]”.
7. Check that no slot—especially the platform feature, audience, conversion goal, destination, or CTA—was filled arbitrarily with a plausible value.
8. Check that no competitor comparison appears without a named competitor, comparison basis, measurement date, and evidence.
9. Check that any paid or incentivised creator treatment carries a visible, conspicuous “[VERIFY: FTC Endorsement Guides disclosure]” flag.
10. Check that health, financial, or children’s advertising has the relevant regime marked “[VERIFY]” only when the concept actually touches that category.
11. Check that visuals, music, stock footage, trademarks, and vehicle imagery do not introduce unsupported product capabilities or rights assumptions.
12. Check that the script stays within the requested scope, contains a clear ending, and does not drift into a campaign plan, legal opinion, review, or sales policy.