Automate your film production with AI - invideo Agent 2

Automate your film production with AI - invideo Agent 2


Can AI agents actually help manage a bigger creative project? We're testing invideo Agent Two to build a roughly 3-minute short from the ground up.

I started by putting the characters, cars, locations and visual direction into Context, then used Briefs for individual scenes. From there I built a small crew of Expert Agents: a writer developed the story, a storyboard artist broke it into shots, and a DOP worked out the cinematography. I used Playbooks to give each agent persistent rules, project Memory to keep track of decisions, and Ultra for the heavier generation work.

Then I gave Agent Two the finished video material and had it check for continuity issues across the project.

Try invideo Agent Two:
https://invideo.io/i/SebastianKamph
Closed Caption:

AI agents have gone from a cool idea to something 
people are actually using day-to-day in just the
last few months. I mean, I use them all the time. 
Coding agents can now work directly with GitHub
and issues and pull requests. And with MCP, they 
can connect into tools like Figma and actually
read or even modify real project files. It's 
pretty cool. And now that same agent idea is
starting to move into creative work. And that's 
what invideo Agent 2 is trying to do for video.
Not just generate something from a prompt, but 
actually understand a project, remember it,
and work through it with you, which sounds 
pretty cool. Now, invideo Agent 2 is four
times faster and half the price compared to the 
previous version, but that's just comparing to
their own stuff. They are sponsoring this video, 
so let's actually put it to work and see if it's
any good. Now, what I want to do today is actually 
use it on a project rather than sit and read you
a list of features because individually a lot 
of the pieces here aren't completely new. AI
that can read documents isn't new, memory isn't new, 
generating video definitely isn't new. What's more
interesting to me is how all of those things 
are being put together into something that's
supposed to behave like a team of people that you 
can work with. You know, honestly, that's the part
I'm curious about. And is it any good? Would I 
recommend it to you or would I use it myself?
That's kind of the big thing, right? So, for this 
test, I'm making a short, roughly 3 minute film.
And if you want to join me, I have a link down 
below to the platform. The idea is about a group
of misfits and their cars inside this underground 
car culture. And visually, I want the whole thing
to have this stylized 3D concept art look. So, 
rather than starting from nothing every time,
I'm going to give Agent 2 the basic world 
of the film. The title, the characters,
the locations, the general subject, and the 
visual direction. Right? And this is where
Agent 2 introduces something called context. Now 
context is basically everything that should remain
true across the whole project. Then inside that 
context, you can create individual briefs for
the specific things you're working on. So in this 
case, the short itself and this world can live in
the context, while individual scenes or sequences 
can have their own briefs. None of this is
super glamorous. It's project organization, which 
is pretty boring. But on longer AI projects,
this is normally where things start getting 
annoying. You establish a character, a location,
a visual rule, and then 20 generations 
later, you're explaining all of it again to
AI in different ways. Now, Agent 2 is designed 
to keep that information around instead. Now,
I'm going to give it the project information and 
some material to work with, but I'm deliberately
not turning everything into one giant master 
prompt first. I want to see how well it can
actually read what I give it and understand the 
project from there. Now, Agent 2 can work with,
you know, scripts, PDFs, brand books, references, 
links, and video, you know, the usual files. So,
the interesting bit isn't really that it accepts 
different file types. The interesting bit is what
it does with that information once it becomes part 
of the project and if it stays there.
So I give it something here and I just say take 
a look at this and tell me what you understand
about the project so far. What feels established 
and anything you think I should pay attention to
and go. Okay, so that's fairly quick and invideo 
tells me they have been pushing the speed of Agent
2 and you know I can see why if I had to wait two 
or three minutes every time I ask something small
I'd stop treating this like a conversation 
very quickly. Now here I can ask something
get an answer react to it and keep moving. Now 
whether the answer is good is obviously the more
important part right so let's see what it actually 
understood about the characters the world and
the visual direction the cool stuff now the part 
that I think makes Agent 2 much more interesting
is the expert agents instead of having one 
giant AI conversation trying to write the film
design the shots think about cinematography and 
keep track of everything else you can create
separate agents with specific jobs. So, I'm going to build a small crew
around this short. Sounds like a real short. 
I'll probably want someone focused on the story
and script, like a writer, the storyboard 
artist, a director of photography, DOP,
and someone keeping an eye on the characters 
and the broader continuity of the project.
When you create one, Agent 2 basically 
asks two things. Who am I? And who are you?
Which sounds very existential. Who am I even? 
But really, it just wants a job description. So,
I can tell one, you're the writer on 
this project. I'm the creative director.
Your job is to develop the story and script 
for a 3 minute short using the characters,
location and world we've already established. 
Then, the storyboard artist gets its own job.
The DP gets another one, and so on. Specialized 
agents aren't really a new concept by themselves.
What I care about is whether these actually work 
together instead of becoming four different chats
that I have to keep synchronized myself. That's I 
mean that's what's the point of that. And because
right now we don't actually have a script. 
That seems like the obvious place to start,
right? The project context already knows that 
this is a 3 minute short about misfits and their
cars inside this underground car culture. It knows 
the characters, the locations, and the stylized 3D
concept art direction. So, I'm going to go to 
the writing agent and give it a fairly normal
piece of direction. Take what we've established 
and develop a simple story for this 3 minute short.
Now, keep it focused enough that we can actually 
tell it visually in that amount of time. That is
quick. Now, this is something I actually want to 
spend all the time reading because I don't just
want it to give me a story. I just want to see 
whether it understands what we're trying to make.
And of course, I don't think this is 
the best story. Now, the big question,
best stories, are they still written by people 
with feelings or robots who beep and boop? Well,
at this stage, AI can get you kind of 
starting, but I think humans need at
least now kind of finish it. There's still that 
fine touch with stories that uh people need to
uh finalize. But for this demo, this is perfectly 
fine, but I can just give it that feedback the
same way I would with somebody I'm working with. 
Simplify this section, keep the focus more on the
characters and the relationship with the cars 
and give the ending a stronger visual payoff.
Then we iterate from there until we have something 
I actually want to make. Now once we have a story,
now we finally have something the other 
departments can work from. And this is where the
agent to agent stuff starts making much more sense. 
Now I can go to the storyboard artist and say,
"Hey, take the script we just developed 
and break the opening scene into shots.
I'm not pasting the script into this conversation. 
I'm not explaining who the characters are again.
I'm not describing the visual style again. That 
information already exists in the project. And
if I were to do any of that again, that's 
kind of missing the point. So now it's picking
up what the writing agent just created and turning 
that into something useful for its own department.
And that's the bit I want from the whole 
crew idea. The writer does their part.
Then the storyboard artist can actually build 
on it rather than becoming the messenger
carrying information between five different AI 
chats. Now before I hand this over to the DP,
that's director of photography again. I want to 
set up a playbook. Now, playbooks are
persistent rules for how one particular agent 
should work. So, you're not teaching the DP
what cinematography is. You're teaching this 
DP how you want your project handled. I might
add something like, "Hey, before developing any 
shot, always check the established visual style,
the storyboard, and the story context. Keep the 
cinematography grounded in the stylized 3D concept
artwork we established for the film. Save that. 
Now, that rule should just live with this agent. I
don't have to keep pasting it into every request. 
Your writer could have a completely different
playbook. Your storyboard artist could have 
another one. Persistent instructions by themselves
aren't revolutionary, but having different 
working rules attached to different specialists
inside the same project starts becoming much more. 
And now the DP actually has something to do. Now
we got a story. We got a storyboarded scene. So I 
can take one of those shots and say work out the
cinematography for this shot. Again, pretty normal 
direction. The DP can see the story. It can see
what the storyboard artist decided. It knows which 
character is involved, which location we're in,
and what visual style we established at the 
beginning. And again, very fast. But speed aside,
this is probably the demonstration I care about 
most. We started with characters, locations,
and an idea. The writer turned that into a story. 
The storyboard artist turned part of that story
into shots. And now the DP is working out how one 
of those shots should actually be photographed.
I didn't have to rebuild the film for every 
department. That's the crew idea here. And for me,
it makes a lot more sense when you actually watch 
the work move from one agent to another. Now,
I want to try the memory because this is one 
of those features that sounds great in product
description, but only really matters when you stop 
thinking about one prompt at a time. Now, we've
already made a bunch of decisions while developing 
this film. So, I'm going to ask about something
from earlier without giving it the answer again. 
What did we establish about the red Ford? And
there it is. Again, remembering one fact isn't 
magic. The useful part is that a project like
this slowly builds up hundreds of little facts. 
Which car belongs to which character, what a
location is supposed to feel like, what we changed 
in the story, which visual direction we rejected.
Normally after enough generations you become the 
database holding all of this together. Agent 2
is designed to keep that project memory around so 
you don't have to reconstruct it every time you
come back. And this is probably a good point to 
explain what invideo actually means by an agent.
There are obviously still AI models underneath 
all of this. The model hasn't disappeared. But the
model is only one part of this system. The agent 
is the layer around it. The memory, the project
structure, the specialists, how information moves 
between them and how it decides what matters. Now,
invideo compares this to something like Claude 
code and I think that comparison works as long as
we don't turn it into one of those um silly this 
kills that things. Claude Code is built around
software development and it's amazing. Agent 2 is 
built around creative production. I wouldn't ask
Agent 2 to code my accounting software and 
I probably wouldn't ask Claude code to plan
the cinematography for this short but maybe it can 
but probably different agents different jobs right
okay now we actually have enough to make something 
we've gone from the original idea to a story
from the story to a storyboard and from the 
storyboard to actual cinematography decisions.
So, I'm going to take one of those shots 
and have Agent 2 start developing it.
For this, I'm using ultra. Agent 2 has light, pro, 
and ultra. Light is more for drafts and tests,
planning. Pro is the general professional tier, 
and ultra is meant for heavier work where there's
more context or more complicated sequences 
involved. Now, invideo specifically recommends
Ultra for this kind of work. So, that's what I'm 
using here. And yeah, it's pretty quick.
I'm going to sound like a broken record by the 
end of this video, but it genuinely is one of the
things you notice. I don't expect every result to 
suddenly be perfect. AI video is still AI video.
The harder question is whether this still feels 
like the same film, same character, same car, same
world, same stylized 3D look. Making one cool 
AI shot isn't really a difficult part anymore.
Keeping a 3 minute short from slowly 
turning into five different films
much harder. Now, once I've got enough material 
together, there's another thing I want to test.
Now, Agent 2 can actually read video or 
look at video. So, I can give it a piece of
the work we've made and ask it to look at the film 
rather than generate something new. Something like
go through this and flag anything that feels 
inconsistent with the rest of the project or
anything you think deserves another look. And 
this is a test where I genuinely hope it catches
something I could miss. Maybe a character detail 
changes. Maybe something about a car drifts.
Maybe one shot just feels like it 
belongs to a different visual world.
Now, I don't want an AI creative director making 
every decision for me. I want something that can
watch the project with me and occasionally say, 
"Hey, Seb, have another look at this. What do you
think?" The taste kind of still has to come from 
you. Faster doesn't automatically mean better,
and smarter doesn't mean handing over the creative 
decisions. There are a couple of other things
I haven't focused on because for me actually 
making the film is more interesting. There is
multiplayer. So multiple people can work inside 
the same project and talk to the same agents with
the same context. That could be useful if you got 
an editor, a producer or another artist working on
different parts of the short. Now on the 
enterprise side, invideo says that they have
enterprise-grade security support for teams and 
external agencies working inside the same projects
and that customer data isn't used for training. 
They also run a research desk and have research
grants for ambitious research problems with 
grants up to 200k USD. And you know that's cool,
but I'm not going to pretend that's the reason 
most of you are going to try this. For me,
the interesting question is still whether it makes 
actually building the film easier. That and I bet
making AI social media slop will get even 
easier as well. So after working through this,
I don't think the story is invideo invented
AI video again because they didn't.
And trying to sell it that way would 
actually undersell the useful part.
We already have very good image and video models 
and there's another one every five minutes. What
Agent 2 is trying to solve is the mess around those 
models once you start making something bigger.
In this case, I didn't start with a finished 
script or a storyboard, which I mean you could.
I started with some characters, locations, 
a world, an idea for a three minute film.
From there, we developed the story, handed that to 
another agent for the storyboard, handed that work
to the DP, established rules for how the different 
agents should work, and then started actually
making the film. That combination is what I find 
interesting. Now, not every part of it is new.
Not every suggestion is good. Not every generation 
is going to work. And there are definitely things
I'd still like to see improve. And the speed 
matters more than I expected because the whole
thing only really works if talking to these 
agents feels like an ongoing conversation rather
than submitting another render job. So if you're 
already working on larger AI video projects and
you've reached a point where keeping track of the 
project is starting to take almost as much time as
making it, have a look at invideo Agent 2. Link 
is down below and I'll see you in the next one.

Video Length: 16:57
Uploaded By: Sebastian Kamph
Published: 9/10/2026
View Count: 5,118

Related Software Products
invideo AI
invideo AI

Published By:
Invideo Innovation Pte. Ltd.

Description:
invideo AI: an AI video editor in your browser, with agents that cut and generate for you invideo AI (now called invideo Editor with Agent Two) is a browser-based video editor for creators, marketers and small video teams: you describe an edit in plain words and its AI agents cut your footage on a multitrack timeline or generate new clips, images, voices and music. There's a free plan with a weekly limit, and paid plans start at $20 a month, or...


Related Videos
I Tested invideo Agent Two so You Don’t Have to…
I Tested invideo Agent Two so You Don’t Have to…

Video Length: 11:31
Uploaded By: Joseph Martin (8/21/2026)
View Count: 15,093

Is Invideo Worth It? Honest Review + AI Test
Is Invideo Worth It? Honest Review + AI Test

Video Length: 05:45
Uploaded By: Tooltester (8/4/2025)
View Count: 3,272

Masterclass: How to use AI Agents for Filmmaking | Penumbra -  Ep3
Masterclass: How to use AI Agents for Filmmaking | Penumbra - Ep3

Video Length: 06:24
Uploaded By: Invideo for Filmmaking (8/17/2026)
View Count: 1,266

Folders & Connect : 12 days of invideo Agent Two (Day 8)
Folders & Connect : 12 days of invideo Agent Two (Day 8)

Video Length: 03:19
Uploaded By: Invideo for Filmmaking (8/6/2026)
View Count: 371

Copyright © 2026, Ivertech. All rights reserved.