Research and reports · narration-led · landscape 16:9
How to make an isometric data report video
An isometric data video suits a report with several independent findings: a white canvas with a dotted grid, line-art isometric forms in a single accent colour, and one narrated sentence per short scene. The isometric treatment gives abstract numbers physical presence without pretending to be a photograph. baz ships this as the Isometric Line-Art Data Report skill — a hook scene, one scene per claim, and a close, with the runtime driven by the narration rather than a fixed grid.
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 Isometric Line-Art Data Report 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 data points — one distinct claim per scene, with sources
Makes it materially better
- A clear ordering of the findings, strongest first or building to a conclusion
- Your accent colour — the format uses exactly one
- A closing call to action or report download link
How to make an isometric data report video: step by step
Count your distinct claims — that is your scene count
This format is one claim per scene, so the structure falls out of the brief. Nine findings means nine data scenes plus a hook and a close. If two findings are really the same point, merge them rather than padding the reel.
Write one sentence per finding, then cut every one shorter
Each scene runs roughly three to seven seconds, which is one clean sentence. Long sentences force long scenes, and long scenes in a data reel are where attention goes.
Keep the canvas white and the accent single
White ground, dotted grid, line art, one accent. The restraint is what makes the isometric forms read as diagrams rather than decoration. A second accent colour turns it into an infographic.
Build forms that mean something
An isometric cube stack should encode the data — height, count, or volume proportional to the figure. Isometric shapes used purely as ornament are worse than a plain bar chart, because they imply a precision they do not have.
Sort your forms back to front
Isometric scenes need painter ordering — draw far objects before near ones. Get this wrong and shapes intersect incorrectly, which reads as a rendering bug rather than a style choice.
Close on the ask
A report video exists to drive a download or a conversation. End with the specific next step, not a summary of what the viewer just watched.
What the finished video actually contains
Approximate timings for a ~53 seconds for nine findings 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 |
|---|---|---|
| Open | Hook scene | The headline finding, stated before any structure is established. |
| Per finding | Data scene | One sentence of narration, one isometric construction encoding the figure. Roughly 3–7 seconds each. |
| Close | CTA scene | The next step — download the report, book the conversation. |
Mistakes that cost you the view
Isometric shapes that do not encode anything
Do this instead: Make the geometry proportional to the data. Decorative 3D implies precision that is not there, which is worse than a plain chart.
Painter ordering ignored
Do this instead: Draw back to front. Incorrectly intersecting isometric solids look like a bug, and the viewer will read the whole video as unfinished.
A second accent colour
Do this instead: Stay with one. The single-accent constraint is what holds a line-art system together across a dozen scenes.
Padding to hit a runtime
Do this instead: Let the claim count set the length. A report video with two thin findings stretched across a minute is less persuasive than a tight thirty seconds.
Ending on a summary
Do this instead: End on the ask. The viewer just watched the summary.
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 isometric-line-art-data-report
baz project create --name "Isometric Line-Art Data Report for my product"
baz prompt "make an isometric data report video" --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
How many findings is the right number?
Between five and ten. Fewer and the format feels under-used; more and the reel outruns attention. The source example runs nine data scenes in about 53 seconds.
Can this work in portrait?
This skill is authored landscape, which suits isometric constructions because they are wide. For portrait data content, the charts-and-data or earnings-breakdown grammars are better fits.
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 Isometric Line-Art Data Report 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.