Big Idea

The argument in one line.

An agentic video editor lets someone who can't operate After Effects describe a visual effect in plain language and get a real, tunable version built directly on their own footage instead of hand-keyframing it.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…

You can describe what you want a shot to look like but don't know which layers, keyframes, or shaders would actually produce it.
You make videos solo and want motion graphics or custom effects without learning a compositing tool like After Effects.
You're deciding whether an AI video editor is worth trying and want to see an agent-built effect before signing up.

SKIP IF…

You already work comfortably in After Effects or DaVinci Resolve and don't need a plain-language shortcut.
You want a technical breakdown of how the underlying shader or prompt-to-effect pipeline actually works.

TL;DR

The full version, fast.

Luuk Alleman calls himself a builder, not a motion designer: he knows what a good effect looks like but not how to build one in After Effects or DaVinci. He tests InVideo's new agentic editor by creating an AI agent and describing a custom effect in plain language: pull the brightest highlights into soft light trails, leave the colors untouched, keep darker areas clean, apply it to every scene. The agent builds the shader directly on his footage and hands back five sliders to fine-tune manually. When he asks for motion graphics, the first pass is text-only; restating what he actually wants in plainer language gets a better second pass. The lesson: prompting replaces keyframing, but you still have to iterate.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →

Chapters

Where the time goes.

00:00 – 00:55

01 · An effect I could never build by hand

Cold open: the gap between knowing what an effect should look like and having no idea how to build it manually sets up the whole video.

00:55 – 01:15

02 · What InVideo Editor is

InVideo sponsors the video; InVideo Editor is introduced as an agentic video editor where AI agents take plain-language editing instructions on a browser-based timeline.

01:15 – 01:40

03 · My plain footage

Starting point is raw, unedited footage from a previous video, already restructured once by an agent, used as the test bed for the effect.

01:40 – 02:07

04 · Creating the agent and writing the prompt

An agent is created and given a detailed plain-language brief: pull the brightest highlights into soft light trails, don't change colors, don't generate anything, and expose named controls.

02:07 – 02:31

05 · Asking for controls

The agent confirms its defaults in plain language and returns five adjustable parameters: highlight threshold, softness, trail length, direction, and mix.

02:31 – 02:57

06 · The light-trail effect

The built effect is inspected clip by clip; a lamp visibly glows and trails in one clip but the effect is absent from the next, showing per-clip inconsistency.

02:57 – 03:18

07 · Putting it on every scene

A single instruction ('keep the darker areas clean, only the brightest light should trail, put on all scenes') propagates the tuned effect across the entire edit.

03:18 – 03:51

08 · Tuning it with the sliders

The five exposed controls are manually adjusted, softness, trail length, direction, and mix, to push the AI-built effect toward the intended look.

03:51 – 04:24

09 · Asking for motion graphics

A voice prompt asks the agent for text and motion graphics keyed to what's being said, with a specific brand color code, restrained to one graphic per point.

04:24 – 05:06

10 · First pass: only text

The agent's first attempt renders as plain text overlays only, missing the visual storytelling graphics that were actually intended.

05:06 – 05:31

11 · Fixing it in plain language

A more specific follow-up request, explaining what's happening on screen and explicitly saying 'not only text,' triggers a reworked, better second pass.

05:31 – 05:54

12 · My honest take

The finished effect is judged against footage and saved effects the creator never used himself, with an open question about how much editing still needs a traditional tool.

05:54 – 06:09

13 · Try it free

CTA: InVideo Editor is free to use, agents cost credits, and viewers are pointed to an affiliate link for up to 50% off annual plans.

Atomic Insights

Lines worth screenshotting.

An AI video editor can build a custom shader effect on your own footage from a single plain-language prompt instead of requiring manual keyframing.
Asking an agent to build an effect AND expose manual controls (threshold, softness, trail length, direction, mix) beats asking for a finished, non-editable result.
The first AI pass on a vague request like 'some motion graphics' defaulted to plain text overlays instead of the visual storytelling that was actually wanted.
Restating a request in more specific plain language, rather than manually fixing the output, is what corrected an underwhelming first pass.
Explicitly telling the agent what NOT to change (colors, footage) kept it from over-applying the effect beyond what was asked.
A single follow-up instruction ('put it on all scenes') propagated one tuned effect across an entire multi-clip edit instead of reapplying it clip by clip.
Even after an AI built the effect, four of five exposed sliders still got manually tuned before the result was accepted.
The agent's build step ran visibly on the actual timeline, letting the editor watch the change happen instead of trusting a black-box render.
Judging AI-built effects against footage and folders of effects you'd already given up on is a much lower bar than judging against professional motion-design work.

Takeaway

How to get After Effects-style results by describing them, not keyframing them.

AI EDITING WORKFLOW

An agentic video editor can turn a plain-language description of an effect into a real, tunable result on your own footage, but only if you prompt for named controls and iterate on vague first passes.

02What InVideo Editor is

InVideo Editor is an agentic video editor: you hand its AI agents editing tasks in plain language and watch them execute directly on a browser-based timeline you can still edit.
The agent doesn't just render a black-box result, it also builds manual controls for whatever it creates, so a plain-language request still ends in an editable parameter set.

03My plain footage

Starting from unedited, plain footage is a fair baseline test for an AI editor, since it isolates what the agent adds rather than what a human editor already fixed.
An agent can also reorder and cut a raw recording on its own, handling structural editing before any visual effect work even begins.

04Creating the agent and writing the prompt

Setting up an agent starts with naming it and giving it a short introduction, the same way you'd brief a freelance editor before handing off work.
A workable effect prompt names the visual outcome, pulling the brightest highlights into soft light trails, states the direction, and adds an explicit constraint: don't touch the colors, don't generate new footage.
Asking for named, adjustable parameters up front turns a one-shot AI output into a tool you can keep tuning after the fact.

05Asking for controls

Requesting explicit sliders instead of a finished look is what separates a reusable AI-built effect from a static render you can't adjust.
The agent explained its own defaults in plain language back to the user before handing over the controls, which is what made the result trustworthy enough to accept.

06The light-trail effect

A single applied effect can behave differently per clip: the same shader visibly glowed on a lamp in one clip while doing nothing to a similar light source in the next.
Watching the agent apply an effect to one clip at a time, rather than trusting an instant global change, is how you catch inconsistencies before they spread.

07Putting it on every scene

Once an effect is dialed in on one clip, a single follow-up instruction can propagate the same settings across an entire multi-clip edit instead of reapplying it manually.
Explicit negative constraints, keep the darker areas clean, only the brightest light should trail, kept the effect from bleeding into parts of the frame that should stay untouched.

08Tuning it with the sliders

Even an AI-built effect benefits from manual fine-tuning afterward: softness, trail length, direction, and mix were all still hand-adjusted after the agent's first pass.
Treating the agent's output as a strong first draft, not a final answer, is what let a generic effect end up looking intentional on its footage.

09Asking for motion graphics

Vague creative requests get vague results; the more specific the described intent, react to what's being said, don't cover the face, the closer the first pass lands.
A follow-up voice or text prompt works the same way a second round of notes to a human editor would: restate what's missing rather than starting over.

10First pass: only text

The agent's first interpretation of 'motion graphics' defaulted to the narrowest reading, plain text overlays, rather than the richer visual storytelling that was actually meant.
A disappointing first AI pass is diagnostic information, not a dead end: it tells you exactly which part of the instruction needs to be made more specific.

11Fixing it in plain language

The fix for an underwhelming AI pass was a clearer plain-language re-request, not manual cleanup after the fact.
Naming what the output should NOT be was as useful a piece of the second prompt as naming what it should be.

12My honest take

Judging an AI-built result against your own low bar, effects you already owned but never used, is a more realistic test than judging against professional motion-design work.
The open question left unanswered, how much of a finished edit still needs a traditional tool like After Effects, is the honest limit of a single quick demo, not a full review.

Glossary

Terms worth knowing.

Agentic video editor: A video editor where an AI agent executes editing tasks described in plain language directly on the timeline, instead of requiring the user to manually set keyframes or layers.
Light-trail shader: A visual effect that pulls the brightest highlights in a shot into soft trailing streaks in one direction, while leaving the rest of the image unchanged.
Highlight threshold: A control that sets how bright a pixel has to be before an effect, like a light trail, gets applied to it.

Resources

Things they pointed at.

00:05toolInVideo Editor ↗

Quotables

Lines you could clip.

00:00

“Do you recognize this? The feeling that you know what you want to create for your video, but actually doing that manually...becomes really hard.”

universal creator pain point, works as a cold open→ TikTok hook↗ Tweet quote

00:35

“I'm a builder, not a motion designer. I have a folder full of effects I've saved over the years and just never used.”

relatable confession that frames the whole video's premise→ IG reel cold open↗ Tweet quote

05:35

“I made the effect I imagined and I never opened After Effects because I don't know how that actually works.”

tight payoff line that doubles as the video's own title→ newsletter pull-quote↗ Tweet quote

The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

Do you recognize this? The feeling that you know what you want to create for your video, but actually doing that manually with, for example, DaVinci or Premiere, that becomes really hard if you're a bit like me. I'm not a video editor and I have no idea how to create that.

Today, we are using agentic effects in InVideo Editor, where we can actually change a lot about how our recordings look and make it better with AI. and here is where it becomes cool the agent built the effect but it also creates the controls to actually change it so we can still tweak small stuff manually invideo actually sponsored this video so let me exactly show you how to use it i'm a builder not a motion designer i have a folder full of effects i've saved over the years and just never used i know what looks good I just don't know which layers, which settings, or which shader to actually use to fix it.

Today, I am making custom video effects with a free AI video editor. InVideo just launched InVideo Editor. It's an agentic video editor.

You just give its AI agents editing work in plain language and they will actually do it on a timeline you can still edit and you actually see them working and it all runs in your browser. So this is the video from my last video about InVideo and today we actually want some motion graphics and just some more editing because this is a very plain video.

Let me show it to you.

I dropped out of university while studying AI and within nine months. So this is just a raw video right now. We obviously want something more.

So what we can do is the following. If you don't have that yet, you will see here like create agent. You can give it a name.

You need to introduce yourself and then this agent can then do work for you. In this case, it already cut up the video and it changed the order, which is awesome. I can now paste the following.

Build a custom shader on this clip that pulls the brightest highlights into soft light trails in one direction. Don't change the colors and don't generate anything. Only my footage.

Give me controls for highlight threshold, softness, trail length, direction and mix. So this is really like how I talk about my editors telling it like I want a little bit like this. I want that.

We can now just run this. Make sure that right here in in video editor we have the mode ultra. and then just run it so it will now be thinking we just have to let this run for a second so it says building it on the opening clip the dropout line from your footage only defaults are subtle and right ward you will get all five controls to push from here so what we can now do is if we go here you will see that this lamp right here has this glow and if we go to the second clip you will see that it's gone so it can really be changing stuff inside of our footage which is really cool keep the darker areas clean only the brightest light should thrill put on all scenes we run this and it will then put it on all scenes and make everything a little bit nicer so it is done and as you see it now put that everywhere which i think it looks really solid it looks really cool it really gives more of like an effect what we can now do is the following as you see we can change stuff directly in here which is i think like super cool we can change the softness as you see we can make those changes coming from the light we have some softness that we can add or remove the trail length and this is really cool like we can now really make it in a way where we think like okay this is actually

good so i like it like this and the direction can be more like this and we can have a mix which is also really cool it really gives a cool effect so this is really like a shortcut to some effects let's say i want some motion graphics i will say the following and i use the voice right here i would like to have some text and some motion graphics on top where if i say a specific thing it just makes it a really engaging video please do my color code is cff05 perfect and we run it and then let's see what it comes up with As you see, it is now working on the actual timeline, which I think is just a super cool effect to see.

I'm really looking forward to the quality of these motion graphics as well, but we're going to see. So it has finished. As you see, it says on it, text and graphics, key to what you actually say in your CFFF05 across the whole cut.

First pass will be restrained, one graphic per point, nothing over your face. Then we tune the density. So we can now play it right here.

dropped out of university while studying ai and within nine months i hit 10 000 a month in profit how are you supposed to make money with ai when the thing as you see the graphics it's only text in return you get a lot of flexibility you have the manual editor so that is very nice like honestly i hoped a little bit more fits now all text but as you see what it says right here we can tune the density so i will now say the following So I actually want motion graphics.

So explaining what is happening in the screen, making it look nice, helping me tell the story, not only text, please fix. now that i run that it will work on that motion graphics and i will show you the actual result i dropped out of university while studying ai and within nine months i hit 10 000 a month in profit so i made the effect i imagined and i never opened after effects because i don't know how that actually works invideo editor is free to use and the agents use credits when you hand them work you just bring the idea and decide what looks right and the agent does the technical build So if I can make this in InVideo, how much of your edit actually still needs to be in Adobe, for example?

So if you want to try this on your own footage, use my InVideo link in the description. You get up to 50 % off on eligible annual plans. If you've enjoyed this video, make sure to like and subscribe, and then we'll see each other in the next video.

The Hook

The bait, then the rug-pull.

Luuk Alleman opens with the exact frustration every non-editor has felt: you know what you want your video to look like, but building it by hand in DaVinci or Premiere is out of reach. His fix this time is prompting an AI agent to build the effect for him.

Frameworks

Named ideas worth stealing.

01:45list

Effect prompt structure

Name the visual outcome
State the direction/behavior
Set an explicit constraint (what not to touch)
Request named, adjustable controls

The working prompt for the light-trail effect named the look wanted, constrained what shouldn't change, and explicitly asked for tunable parameters rather than a finished render.

Steal forany plain-language request to an AI tool where you want an editable result, not a one-shot output

CTA Breakdown