Brand systems · 15 seconds · landscape and portrait
How to make a brand motion film
A brand motion film is not a montage of values — it is one idea moving through consequence. The Beamline grammar takes a single readable protagonist (a word, a mark, a shape), sends it through causal forces that visibly act on it, and resolves on one approved final claim. baz ships it as a matched pair of skills, landscape and portrait, each exactly 450 frames — fifteen seconds — with visual timing authoritative and no voiceover by default.
The shortcut: run a skill instead of starting from scratch
A skill is a context file that teaches an AI agent one specific video style — its structure, pacing, typography, motion grammar and sound design. Hand an agent the skill plus your product, and it rebuilds that video for you. The steps below are what the Beamline Brand System skill already encodes, so you can follow them by hand or let the skill carry them.
baz is a library of video skills: context files that teach an AI agent a specific motion-graphics style, so it can rebuild that video for your product, with your brand, from your inputs. Run a skill inside your own coding agent — Claude Code, Codex — or directly in the baz editor.
What you need before you start
Required
- Your brand context
- The product truth — what is actually, defensibly so about it
- Your audience
- The mechanism — the one thing your product does
- An approved final claim, signed off before you build
Makes it materially better
- Your typographic system, since the film is carried entirely by type
- A decision on format up front — landscape and portrait are separate authored skills, not a crop
How to make a brand motion film: step by step
Get the final claim approved before anything else
The whole film resolves onto one sentence. If that sentence changes after you have built the causal chain leading to it, you rebuild the film. Treat sign-off as a prerequisite, not a review step.
Choose one protagonist and keep it readable
A single element — a word, a mark, a form — travels the entire fifteen seconds. The viewer must be able to track it at every moment. Two protagonists means neither gets followed.
Make the forces causal, not decorative
Things that happen to the protagonist should visibly cause the next thing. Motion that is merely simultaneous reads as animation; motion that is consequential reads as an argument.
Give the consequence physical weight
When a force acts, something should deform, slow, deflect or accumulate. Physical consequence is what separates this from type sliding around a canvas.
Respect the safe margins for the format you chose
Landscape keeps stable copy at least 96px from the sides and 72px from top and bottom. Portrait is tighter and reserves the bottom 280px for mobile UI. Type that ignores these gets covered by interface chrome in the feed.
Author portrait natively — do not crop
The portrait version is a separate skill that uses vertical depth to create contrast between beats. Cropping the landscape film loses that entirely and puts your protagonist in the wrong part of the frame.
What the finished video actually contains
Approximate timings for a 15 seconds cut. Treat them as a shape to hit, not a spec — the exact durations shift with your script and your music.
| Time | Beat | What is on screen |
|---|---|---|
| 0:00–0:03 | Protagonist established | One readable element enters and claims the frame. |
| 0:03–0:08 | Causal forces | Forces act on it; each effect causes the next through a match cut. |
| 0:08–0:11 | Physical consequence | Visible deformation or accumulation — the protagonist is changed by what happened. |
| 0:11–0:13 | Semantic review | The meaning of the journey resolves into language. |
| 0:13–0:15 | Final claim | The approved sentence lands and holds. |
Mistakes that cost you the view
Starting before the claim is signed off
Do this instead: Approve the sentence first. The causal chain is built to arrive at it — changing the destination means rebuilding the route.
Two or more protagonists
Do this instead: One element, tracked throughout. Fifteen seconds is not enough time to establish and follow a second.
Decorative motion
Do this instead: Make every move a consequence of the last. Simultaneous motion is animation; caused motion is a brand argument.
Cropping landscape to portrait
Do this instead: Use the portrait skill. It is authored around vertical depth and a tighter safe area, not a re-frame of the wide cut.
Copy inside the mobile UI zone
Do this instead: Reserve the bottom of the portrait frame. Captions and interface chrome will sit on top of anything you put there.
Run it from your own agent
Skills are designed to run inside a terminal agent like Claude Code or Codex, against a project you control. The same skill produces the same style whether it runs in your agent or in the baz editor.
npm install -g bazaar.it@latest
# Install this skill into your agent (Claude Code, Codex or Cursor)
baz skill add beamline-brand-system-landscape
baz project create --name "Beamline Brand System for my product"
baz prompt "make a brand motion film" --stream-json
baz review --summary --json
baz export start --wait --format mp4 --jsonOperations draw from a prepaid balance. See the CLI reference for the full command set.
Common questions
Why exactly 15 seconds?
It is the length at which a single idea can be stated with consequence and no padding, and it fits the standard ad slot. The default is exactly 450 frames at 30fps — a fixed duration is part of what makes it a system rather than a one-off.
Can I add a voiceover?
It is authored without one — visual timing is authoritative and sound reinforces structure rather than carrying it. If you need narration, a longer narrated format will serve the message better than compressing a voice into fifteen seconds.
Landscape or portrait?
Both exist as separately authored skills. Pick based on where the film runs. If it runs in both places, build both — they are different films, not two crops of one.
Do I need video editing experience?
No. The skill carries the editing decisions — shot order, pacing, type treatment, transitions, sound design. You supply the raw material and the facts about your product; the agent assembles the cut. You review it and ask for changes in plain language.
Can I run this in my own coding agent instead of the baz editor?
Yes. Skills are designed to be run from a terminal agent like Claude Code, Codex or Cursor. Install the CLI with `npm install -g bazaar.it@latest`, then `baz skill add <slug>` to pull the skill into your agent. The same skill produces the same style whether it runs in your agent or in the baz editor.
What does it cost?
baz bills against a prepaid dollar balance rather than a seat subscription — you top the balance up and each operation (generation, voiceover, render, export) draws a listed amount from it. There is no per-seat fee to make a video, and the price of each operation is published.
Can I change the video after it renders?
Yes, and this is the point of doing it as code rather than as a flat render. Every scene is a real component you can edit — ask the agent to re-time a beat, swap a screenshot, rewrite a line, or change the accent colour, and only that part rebuilds. You are not re-rendering from scratch each time.
Will every video from this skill look the same?
The grammar is the same — that is what makes it a skill and not a template. The content is not: your brand colours, typography, screenshots, copy and data all come from your inputs. Reusing one skill across a series is a feature, because episode three lands in the same visual language as episode one instead of being rebuilt from scratch.
Related guides
Pick a skill. Get the video.
Run the Beamline Brand System skill in your own coding agent, or in the baz editor. Usage comes out of a balance you top up, with a listed price per operation — no seat subscription to make a video.