Concept explainers · narration-led · portrait 9:16
How to make a concept explainer video
Abstract ideas do not survive being explained abstractly. The format that works is to walk a person — the viewer, addressed as "you", or a small fictional cast — through a worked example with real numbers, then close the loop by returning to the mechanism you opened on. baz ships this as the Explainer Story skill: a portrait reel of about 80 to 90 seconds on a cream canvas, with word-by-word pops synced to the narration and a two-act structure that ends where it began.
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 Explainer Story 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
- The topic and the core concept you are teaching
- A worked example with real numbers — the concrete case the abstraction rests on
Makes it materially better
- An authority figure or named source to anchor the claim
- A defined target audience, so the level of assumed knowledge is right
- Your brand URL, if the reel is for a channel
How to make a concept explainer video: step by step
Reduce the topic to one mechanism
One video, one idea. Not "how inflation works" but "why your savings lose value even when the balance goes up". A mechanism you can state in a sentence is teachable in eighty seconds; a subject area is not.
Build a worked example with real numbers
This is what separates an explainer that lands from one that washes over. £1,000 at 3% over five years is memorable; "compounding grows your money" is not. Pick numbers that are round enough to follow and realistic enough to matter.
Put a person in it
Address the viewer as "you", or invent a small cast. Abstract ideas become concrete the moment someone is experiencing them. This is the single highest-leverage choice in the format.
Sync the type to the narration word by word
Word-by-word pops keep the eye moving at the pace of the voice. This is what stops a talking-head-without-the-head from feeling static — and it only works if the type timings come from the actual voice track, not from estimates.
Structure it in two acts
Act one sets up the mechanism and walks the example. Act two shows the consequence or the counterintuitive result. The break between them is where you can afford your one big visual move.
Loop closed on the opening image
End by returning to the thing you opened with, now understood differently. That closure is what makes an explainer feel complete rather than merely finished, and it is the most reliable driver of a rewatch.
What the finished video actually contains
Approximate timings for a 80–90 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 |
|---|---|---|
| 0:00–0:06 | The mechanism | The thing to be explained, posed as a question or a puzzle on the cream canvas. |
| 0:06–0:30 | Setup with a cast | A person enters the idea; the worked example begins with its first real number. |
| 0:30–0:55 | The walk-through | The example advances step by step, word-by-word type tracking the narration. |
| 0:55–1:15 | Act two — the consequence | The counterintuitive result, given the reel's largest visual move. |
| 1:15–1:30 | Loop closed | Back to the opening image, now meaning something different. |
Mistakes that cost you the view
Explaining the abstraction abstractly
Do this instead: Walk one concrete example. A definition restated three ways is still a definition.
Round numbers with no grounding
Do this instead: Use figures from a real case. "Imagine you have some money" is not a worked example.
Estimating the word timings
Do this instead: Derive them from the voice track. Type that drifts from the narration by even a few frames reads as sloppy across an entire reel.
Covering the whole subject
Do this instead: One mechanism per video. Everything you cut becomes the next reel in the series.
Ending on a summary card
Do this instead: Return to the opening image. The loop is the payoff; a bullet-point recap throws it away.
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 explainer-story-pop
baz project create --name "Explainer Story for my product"
baz prompt "make a concept explainer 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
Does it need a voiceover?
Yes — the format is narration-led and the word-by-word type is synced to the voice track. Without narration you lose the mechanism that drives the pacing.
Can I use a fictional character?
Yes, and it often works better than second person for topics where "you" would be presumptuous. A named character walking through the example gives the viewer someone to watch without implying anything about their own situation.
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 Explainer Story 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.