Hire an AI founder video ad shoot planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A grid of buyer problems and angles, ranked in test order, with a first line for each
• Founder scripts that run claim, proof, how it works, proof and call to action, with two to four hooks each
• Every hook scored out of 100, with the best ones to film and rewrites for the weak ones
• A script check with a score out of 100 and rewrites for weak spots from hook to offer
• A shoot list by location and outfit, a hook by body matrix that shows how many ads you get, and edit notes

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You or your founder will go on camera, and you want a batch of ads from one session.

• Ad concept matrix. Buyer problems with an angle, an offer, the proof needed, a first line and a test order.
• Founder scripts. Scripts for the top angles in five parts, each with two to four hooks.
• Hook scores. Each hook scored out of 100, who it attracts, rewrites for weak ones and the hooks to film.
• Script check. A score out of 100 for each script from hook to offer, with rewrites for weak spots.
• Shoot list. Takes grouped by place and outfit, a hooks by bodies count of ads, and edit notes.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Eugene Schwartz and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find the problems to talk about. Reads your buyer words, writes each buyer as a problem, gives each an angle and offer, ranks them in test order and writes a first line for each.
• Write the founder scripts. Starts from the viewer's problem, picks a claim you can prove, and writes the script using only what the founder can truly say, with two to four hooks.
• Score the hooks. Rates each hook for clarity, relevance, novelty, specificity and credibility, checks who it attracts, and rewrites the weak ones.
• Check the flow. Maps each script from hook to body to offer, checks when the product comes in, and rewrites any spot where the viewer would leave.
• Plan the shoot. Sizes the shoot to your hours, groups the takes by place and outfit, writes edit notes and says whether a partnership ad suits you.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id shoot-a-batch-of-founder-ads-in-one-afternoon only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/shoot-a-batch-of-founder-ads-in-one-afternoon/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your product facts (what it is, price, who uses it and what it solves)
• Your customer reviews, survey answers or support emails (at least 20 real lines is best)
• Your brand file, with the founder's origin story, how the product works, and proof such as test results, certificates and reviews
• Who the ad is for (the buyer persona) and what they already know
• Where you can film, and how many hours you have (optional)

Tools and access

• Any good chat AI: Any current chat AI can run the persona loop. Paste your reviews in as plain text.
• Meta Ads Manager: Where you name ad sets and read results per concept.
• Any good chat AI: Any current chat AI can build and swap the script.
• Meta Ads Manager: Run each narrator version as its own ad and read the results.
• Any good chat AI: Any current chat AI can score text hooks. Attach a screenshot of the first frame if you want the visual layer judged.
• Meta Ads Manager: Needs an ad account. Shows early retention for a running video, so you can check scores against results.
• Any good chat AI: Any current chat AI can read a script and plot the awareness map.
• Meta Ads Manager: Shows the retention graph of a running video, so you can see where viewers drop.
• Any good chat AI: Any current chat AI can build the matrix and shoot list.
• A shared folder or note app: Keeps the monthly story material in one place.

Functions and deliverables

• Founder video ad shoot planner: Share reviews, product facts, buyer context and brand guidance. Get ad angles, founder scripts, hook reviews and an afternoon shoot list.
  • A grid of buyer problems and angles, ranked in test order, with a first line for each
  • Founder scripts that run claim, proof, how it works, proof and call to action, with two to four hooks each
  • Every hook scored out of 100, with the best ones to film and rewrites for the weak ones
  • A script check with a score out of 100 and rewrites for weak spots from hook to offer
  • A shoot list by location and outfit, a hook by body matrix that shows how many ads you get, and edit notes
• Ad concept testing planner: Share your product and reviews. Get buyer groups, messages and offers arranged into an ad testing plan.
  • 30 to 40 personas, each a problem plus a situation
  • An angle for each persona, built from named parts, and the offer options for each concept
  • A test order and an ad set name for every concept
  • A first-line hook idea per concept and the proof each one needs
• Founder ad script builder: Turn your true founder story and proof into a founder video ad script. You get a claim-first script, 2 to 4 hooks and narrator-swap versions.
  • A script in the order claim, proof, mechanism, proof, call to action
  • 2 to 4 hooks that fit the body
  • Versions told by a witness, an interviewer or a reader
  • A plan for the same story as face and voice, voice only, evidence, proxy or animation
• Video hook scorer: Score your video ad hooks out of 100, see who each one attracts, and get rewrites for the weak ones before you film.
  • A table with five scores per hook and a total out of 100
  • Who each hook pulls in or turns away, and whether it qualifies the right viewer
  • 3 to 6 rewrites for each weak hook, changing the audio, the words on screen or the visual one at a time
  • The top three hooks to film, the rest to cut, and a note on any claim to check
• Video ad transition reviewer: Check a video ad script before you film it. Find where viewers feel sold to too soon, and get a bridge score out of 100 plus a tighter script.
  • A line-by-line map of how aware the viewer is that they are being sold to
  • Each bridge (hook to body, body to call to action) marked good or abrupt
  • A bridge score out of 100, now and after the fixes, with the sum shown
  • A tighter script, with feature-to-benefit rewrites, pacing notes and a teaching step before the product
• Founder ad shoot planner: Plan a founder ad shoot that makes a month of ads in one day. Give it your hooks and story bank. You get a hook-by-body matrix and a shoot list.
  • A hook-by-body matrix with the ad count
  • A shoot list grouped by location and outfit
  • A monthly checklist for collecting story material
  • Edit notes on cuts, a second camera and overlays
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You or your founder will go on camera, and you want a batch of ads from one session.
• Your ads get views but few sales, and you suspect the opening or the flow is the problem.
• You want a month of new ads without a new shoot every week.

Limits to check before starting

• No founder or team member will go on camera: use the Video ad shot list maker to plan the shots instead.
• You want still image ads, not video: use the Story image ad writer.
• You already have a script and only want the opening scored: use the Video hook scorer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and five skill files, in the order they run: Ad concept matrix builder, Founder ad script builder, Video hook scorer, Video script bridge checker and Founder ad shoot planner.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your reviews and product facts. With fewer than about 20 real lines, it marks personas that rest on a guess.
• Give it the founder's real story and your proof. It will not invent a result, a customer or an expert.
• Read the shoot list and film one afternoon from it. Check any health, weight or money claim with a qualified person before the ads run.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/shoot-a-batch-of-founder-ads-in-one-afternoon for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.