Building an Agentic Video Editor for Mass Consumer — Ekaterina Deyneka, Reelful

>> Hi everyone. I think we can start. Uh >> Hi everyone. I think we can start. Uh but before we start, I want to ask you a but before we start, I want to ask you a but before we start, I want to ask you a couple of questions. couple of questions. couple of questions. So, first of all, how many of you took a So, first of all, how many of you took a So, first of all, how many of you took a photo or video during this conference? photo or video during this conference? photo or video during this conference? Please raise your hands. Please raise your hands. Please raise your hands. Okay, and how many of you actually Okay, and how many of you actually Okay, and how many of you actually posted any video content from it online? Not that many. And um to be honest, that Not that many. And um to be honest, that was me. I I was recording a lot of was me. I I was recording a lot of was me. I I was recording a lot of content during conferences, events, content during conferences, events, content during conferences, events, trips, meetups, trips, meetups, trips, meetups, uh and I never posted them online uh and I never posted them online uh and I never posted them online because video editing is hard. because video editing is hard. because video editing is hard. Uh it sounds and it is a lot of work. Uh Uh it sounds and it is a lot of work. Uh Uh it sounds and it is a lot of work. Uh it's tedious and it's largely still it's tedious and it's largely still it's tedious and it's largely still manual. So, and and it also feels like manual. So, and and it also feels like manual. So, and and it also feels like an art and not really automated. And an art and not really automated. And an art and not really automated. And that's why we're building RealFull and that's why we're building RealFull and that's why we're building RealFull and we're trying to tackle agentic video we're trying to tackle agentic video we're trying to tackle agentic video editing problem from uh editing problem from uh editing problem from uh video editing problem from the agentic video editing problem from the agentic video editing problem from the agentic standpoint. I'm Kate. I'm founder and standpoint. I'm Kate. I'm founder and standpoint. I'm Kate. I'm founder and CEO at RealFull.

CEO at RealFull. CEO at RealFull. But let's first talk about what's But let's first talk about what's But let's first talk about what's agentic video editing is. So, as a user, agentic video editing is. So, as a user, agentic video editing is. So, as a user, you just drop in your media, photos and you just drop in your media, photos and you just drop in your media, photos and videos, and provide some context. It can videos, and provide some context. It can videos, and provide some context. It can be uh the context what happened in these be uh the context what happened in these be uh the context what happened in these media files, or it can be some media files, or it can be some media files, or it can be some directions. For example, like add directions. For example, like add directions. For example, like add captions, add music, add voiceover, and captions, add music, add voiceover, and captions, add music, add voiceover, and something like that. And then, the agent something like that. And then, the agent something like that. And then, the agent will go, understand your media, uh find will go, understand your media, uh find will go, understand your media, uh find the right moments, assemble everything the right moments, assemble everything the right moments, assemble everything together, generate captions, music, together, generate captions, music, together, generate captions, music, voiceover, b-rolls, voiceover, b-rolls, voiceover, b-rolls, uh and give you a ready-to-share clip. uh and give you a ready-to-share clip. uh and give you a ready-to-share clip. Uh and um yeah, so basically, uh that's Uh and um yeah, so basically, uh that's Uh and um yeah, so basically, uh that's uh uh uh video agentic video editing. So, agent video agentic video editing. So, agent video agentic video editing. So, agent does everything by itself. Or another does everything by itself. Or another does everything by itself. Or another example, you recorded a speak-to-camera example, you recorded a speak-to-camera example, you recorded a speak-to-camera video and you have a lot of pauses, video and you have a lot of pauses, video and you have a lot of pauses, unsuccessful shots, and you expect an unsuccessful shots, and you expect an unsuccessful shots, and you expect an agent to figure it out to remove agent to figure it out to remove agent to figure it out to remove unsuccessful shots, remove pauses, and unsuccessful shots, remove pauses, and unsuccessful shots, remove pauses, and give you a ready-to-share clip.

give you a ready-to-share clip. give you a ready-to-share clip. Um Um Um and uh the the interesting thing is that and uh the the interesting thing is that and uh the the interesting thing is that a lot of actually a lot of the things a lot of actually a lot of the things a lot of actually a lot of the things inside this pipeline can be automated. inside this pipeline can be automated. inside this pipeline can be automated. And this is exactly what we're doing at And this is exactly what we're doing at And this is exactly what we're doing at Real Fall. Real Fall. Real Fall. Oh, this is um Oh, this is um Oh, this is um the example of uh the example of uh the example of uh video edited. video edited. video edited. And um And um And um since we're at AI Engineering since we're at AI Engineering since we're at AI Engineering Conference, I wanted to talk a little Conference, I wanted to talk a little Conference, I wanted to talk a little bit about infrastructure. And from the bit about infrastructure. And from the bit about infrastructure. And from the infrastructure standpoint, agentic uh infrastructure standpoint, agentic uh infrastructure standpoint, agentic uh video editor is very similar to agentic video editor is very similar to agentic video editor is very similar to agentic app builder. Uh sorry, there is a typo app builder. Uh sorry, there is a typo app builder. Uh sorry, there is a typo on the slide. So, the uh second column on the slide. So, the uh second column on the slide. So, the uh second column is agentic video editor. So, both of is agentic video editor. So, both of is agentic video editor. So, both of them have a prompt uh a UI for prompt uh them have a prompt uh a UI for prompt uh them have a prompt uh a UI for prompt uh and in the video editor case, it's a and in the video editor case, it's a and in the video editor case, it's a media plus prompt. And usually on back media plus prompt. And usually on back media plus prompt. And usually on back end, what's happening? There is a remote end, what's happening? There is a remote end, what's happening? There is a remote machine which is called sandbox, machine which is called sandbox, machine which is called sandbox, uh uh uh which is spinning up, and inside this which is spinning up, and inside this which is spinning up, and inside this machine, there is an agent with tools machine, there is an agent with tools machine, there is an agent with tools and skills, which is working on and skills, which is working on and skills, which is working on uh what you're uh you're you're asking uh what you're uh you're you're asking uh what you're uh you're you're asking it to do. Uh in the case of the agentic it to do. Uh in the case of the agentic it to do. Uh in the case of the agentic uh app builder, it's a code base.

uh app builder, it's a code base. uh app builder, it's a code base. Uh in the case of the agentic video Uh in the case of the agentic video Uh in the case of the agentic video editor, it's a video video composition. editor, it's a video video composition. editor, it's a video video composition. And as a result, in the Argentic builder And as a result, in the Argentic builder And as a result, in the Argentic builder user get an app preview and for the user get an app preview and for the user get an app preview and for the video editor users user get rendered a video editor users user get rendered a video editor users user get rendered a rendered video. rendered video. rendered video. And but And but And but yes, the the infrastruc- from yes, the the infrastruc- from yes, the the infrastruc- from infrastructural standpoint, it's pretty infrastructural standpoint, it's pretty infrastructural standpoint, it's pretty similar, but there are a couple of similar, but there are a couple of similar, but there are a couple of differences. differences. differences. Uh and Uh and Uh and this is actually the most interesting to this is actually the most interesting to this is actually the most interesting to me, generating versus editing. At me, generating versus editing. At me, generating versus editing. At RealFull, we're focusing on editing real RealFull, we're focusing on editing real RealFull, we're focusing on editing real footage. So, we do not generate a lot of footage. So, we do not generate a lot of footage. So, we do not generate a lot of content. We are expecting you to provide content. We are expecting you to provide content. We are expecting you to provide your real life, your your real life, your your real life, your personal content, and we will edit it personal content, and we will edit it personal content, and we will edit it for you. And actually, this is for you. And actually, this is for you. And actually, this is a more complex problem because if the a more complex problem because if the a more complex problem because if the agent has a blank blank canvas, it can agent has a blank blank canvas, it can agent has a blank blank canvas, it can do whatever they can. But in the editing do whatever they can. But in the editing do whatever they can. But in the editing case, the agent has to figure out case, the agent has to figure out case, the agent has to figure out which moments are the best. Uh what to which moments are the best. Uh what to which moments are the best. Uh what to omit, what to use, how to organize omit, what to use, how to organize omit, what to use, how to organize everything together. And also, everything together. And also, everything together. And also, um sometimes footage can be um sometimes footage can be um sometimes footage can be messy or incomplete, and agent still has messy or incomplete, and agent still has messy or incomplete, and agent still has to deliver a very polished result, to deliver a very polished result, to deliver a very polished result, professionally made, so that ideally the professionally made, so that ideally the professionally made, so that ideally the viewers of this content don't get if it viewers of this content don't get if it viewers of this content don't get if it is like AI or

is like AI or is like AI or human edited. human edited. human edited. So, let's actually have a look how we do So, let's actually have a look how we do So, let's actually have a look how we do it at RealFull. So, we start, as I it at RealFull. So, we start, as I it at RealFull. So, we start, as I already mentioned, with your media plus already mentioned, with your media plus already mentioned, with your media plus a prompt, some directions like how you a prompt, some directions like how you a prompt, some directions like how you want it to be edited, and we need to get want it to be edited, and we need to get want it to be edited, and we need to get a polished clip. So, let's go through it a polished clip. So, let's go through it a polished clip. So, let's go through it step by step. So, we are doing first step by step. So, we are doing first step by step. So, we are doing first media understanding. We need to media understanding. We need to media understanding. We need to understand what's what's actually understand what's what's actually understand what's what's actually happening uh, on those clips and photos. happening uh, on those clips and photos. happening uh, on those clips and photos. And we also need to transcribe And we also need to transcribe And we also need to transcribe transcribe speech, for example, in the transcribe speech, for example, in the transcribe speech, for example, in the case if you have speak-to-camera videos. case if you have speak-to-camera videos. case if you have speak-to-camera videos. Then, we are providing a creative plan Then, we are providing a creative plan Then, we are providing a creative plan for the user so that they can approve if for the user so that they can approve if for the user so that they can approve if they like it or not, what they want to they like it or not, what they want to they like it or not, what they want to change or maybe regenerate, uh, and we change or maybe regenerate, uh, and we change or maybe regenerate, uh, and we create this plan before actually create this plan before actually create this plan before actually starting editing. Once the user approved starting editing. Once the user approved starting editing. Once the user approved this plan, this plan, this plan, uh, we spin up a sandbox, the remote uh, uh, we spin up a sandbox, the remote uh, uh, we spin up a sandbox, the remote uh, remote machine that we already remote machine that we already remote machine that we already discussed, and this is an environment discussed, and this is an environment discussed, and this is an environment for the agent to, for the agent to, for the agent to, uh, execute everything. So, the agent uh, execute everything. So, the agent uh, execute everything. So, the agent comes with the skills, and in our case, comes with the skills, and in our case, comes with the skills, and in our case, in in the case of, uh, video editing, in in the case of, uh, video editing, in in the case of, uh, video editing, our skills are, for example, cut rules, our skills are, for example, cut rules, our skills are, for example, cut rules, how, for example, how to select the best how, for example, how to select the best how, for example, how to select the best moments, moments, moments, uh, also font pairs, which fonts are, uh, also font pairs, which fonts are, uh, also font pairs, which fonts are, uh, more suitable for this use case, uh, more suitable for this use case, uh, more suitable for this use case, which are not, for example, how to which are not, for example, how to which are not, for example, how to generate B-rolls, and this is where our

generate B-rolls, and this is where our generate B-rolls, and this is where our taste and craft, uh, live, actually. taste and craft, uh, live, actually. taste and craft, uh, live, actually. Um, and then also agent, uh, can, um, Um, and then also agent, uh, can, um, Um, and then also agent, uh, can, um, can initiate some other sub-processes, can initiate some other sub-processes, can initiate some other sub-processes, for example, generating music that will for example, generating music that will for example, generating music that will fit this exact composition, generating fit this exact composition, generating fit this exact composition, generating voice-over, adding sounds, animating voice-over, adding sounds, animating voice-over, adding sounds, animating images. Yes, this is actually what we images. Yes, this is actually what we images. Yes, this is actually what we do, uh, if you provide photos, we can do, uh, if you provide photos, we can do, uh, if you provide photos, we can animate your photos to make them more, animate your photos to make them more, animate your photos to make them more, uh, dynamic and engaging. uh, dynamic and engaging. uh, dynamic and engaging. And then comes Remotion composition. So, And then comes Remotion composition. So, And then comes Remotion composition. So, here a little bit of background. What's here a little bit of background. What's here a little bit of background. What's Remotion? Remotion is a framework, Remotion? Remotion is a framework, Remotion? Remotion is a framework, open-source open-source framework, uh, open-source open-source framework, uh, open-source open-source framework, uh, to create videos as code, as React code. to create videos as code, as React code. to create videos as code, as React code. Uh, so basically, it's just like a a Uh, so basically, it's just like a a Uh, so basically, it's just like a a file with the order with all your assets file with the order with all your assets file with the order with all your assets and tracks and how they're following and tracks and how they're following and tracks and how they're following each other. And, each other. And, each other. And, why it is important? Because, uh, agents why it is important? Because, uh, agents why it is important? Because, uh, agents are really good at writing code and are really good at writing code and are really good at writing code and therefore we can use them to create therefore we can use them to create therefore we can use them to create videos with this remotion framework.

videos with this remotion framework. videos with this remotion framework. And then And then And then the last thing is the verification the last thing is the verification the last thing is the verification layer. Of course agent can make mistakes layer. Of course agent can make mistakes layer. Of course agent can make mistakes and that's why we develop this and that's why we develop this and that's why we develop this verification layer to make sure that all verification layer to make sure that all verification layer to make sure that all the the the the composition is clean, is well the composition is clean, is well the composition is clean, is well defined, everything will be rendered and defined, everything will be rendered and defined, everything will be rendered and if there are there are some problems if there are there are some problems if there are there are some problems then the agent then the agent then the agent will reiterate on the composition. And will reiterate on the composition. And will reiterate on the composition. And this is how we got to a polished clip. this is how we got to a polished clip. this is how we got to a polished clip. >> [sighs and gasps] >> [sighs and gasps] >> [sighs and gasps] >> So it's a lot, right? It's like very >> So it's a lot, right? It's like very >> So it's a lot, right? It's like very complex workflow complex workflow complex workflow and ideally we don't want our users to and ideally we don't want our users to and ideally we don't want our users to even know anything about it. And this is even know anything about it. And this is even know anything about it. And this is even maybe a bigger problem how to even maybe a bigger problem how to even maybe a bigger problem how to deliver this complex agentic workflow to deliver this complex agentic workflow to deliver this complex agentic workflow to mass consumer. mass consumer. mass consumer. And this is how we're tackling that at And this is how we're tackling that at And this is how we're tackling that at Real Flow. So we decided to go mobile Real Flow. So we decided to go mobile Real Flow. So we decided to go mobile first so that users can edit videos first so that users can edit videos first so that users can edit videos videos while driving, walking or maybe videos while driving, walking or maybe videos while driving, walking or maybe lifting weights.

lifting weights. lifting weights. Also, I know that prompting videos can Also, I know that prompting videos can Also, I know that prompting videos can sometimes be also challenging. That's sometimes be also challenging. That's sometimes be also challenging. That's why we create directional templates. For why we create directional templates. For why we create directional templates. For example, like speak to camera in videos example, like speak to camera in videos example, like speak to camera in videos or maybe you want to add B-rolls or or maybe you want to add B-rolls or or maybe you want to add B-rolls or voiceover so that users can just select voiceover so that users can just select voiceover so that users can just select these directional templates, drop their these directional templates, drop their these directional templates, drop their media and that's it. Even without any media and that's it. Even without any media and that's it. Even without any prompt it will it will work. prompt it will it will work. prompt it will it will work. And the third thing is a building And the third thing is a building And the third thing is a building editor. editor. editor. Why? Because we want to make this Why? Because we want to make this Why? Because we want to make this experience convenient and familiar for experience convenient and familiar for experience convenient and familiar for users. So a lot of people are already users. So a lot of people are already users. So a lot of people are already sort of sort of sort of using using using regular video editors and that's why we regular video editors and that's why we regular video editors and that's why we want to provide this experience as well. want to provide this experience as well. want to provide this experience as well. So, how it works? User first generates a So, how it works? User first generates a So, how it works? User first generates a video agentically, but if they want to video agentically, but if they want to video agentically, but if they want to tweak it, for example, remove a second tweak it, for example, remove a second tweak it, for example, remove a second or maybe or maybe or maybe correct some word in the captions, they correct some word in the captions, they correct some word in the captions, they can go into building editor and edit it can go into building editor and edit it can go into building editor and edit it a little bit.

a little bit. a little bit. Um Um Um Yeah, and actually I have a couple of Yeah, and actually I have a couple of Yeah, and actually I have a couple of examples here that I recently created examples here that I recently created examples here that I recently created with Real Fill. with Real Fill. with Real Fill. I will play them just maybe one of that. I will play them just maybe one of that. I will play them just maybe one of that. Oh, sorry. Oh, sorry. Oh, sorry. >> Last week I was invited >> Last week I was invited >> Last week I was invited >> Do do you hear? >> Do do you hear? >> Do do you hear? A little bit. Okay, you just can enjoy A little bit. Okay, you just can enjoy A little bit. Okay, you just can enjoy the video. the video. the video. >> because of course our creators dinner >> because of course our creators dinner >> because of course our creators dinner and honestly it was one of the best and honestly it was one of the best and honestly it was one of the best event experiences I've had. First of event experiences I've had. First of event experiences I've had. First of all, the venue was stunning. It was a all, the venue was stunning. It was a all, the venue was stunning. It was a custom event space transformed into this custom event space transformed into this custom event space transformed into this tropical sunset feast. The whole tropical sunset feast. The whole tropical sunset feast. The whole atmosphere felt so warm and cinematic. atmosphere felt so warm and cinematic. atmosphere felt so warm and cinematic. Second, the food was way beyond my Second, the food was way beyond my Second, the food was way beyond my expectations. They brought in private expectations. They brought in private expectations. They brought in private chefs from LA and we had lobster, blue chefs from LA and we had lobster, blue chefs from LA and we had lobster, blue crab, and this incredible ice cream that crab, and this incredible ice cream that crab, and this incredible ice cream that I'm still thinking about. But most I'm still thinking about. But most I'm still thinking about. But most importantly, the conversations were so importantly, the conversations were so importantly, the conversations were so much fun. It was kind of atmosphere. It much fun. It was kind of atmosphere. It much fun. It was kind of atmosphere. It felt really easy to connect with people, felt really easy to connect with people, felt really easy to connect with people, talk about what they're working on, and talk about what they're working on, and talk about what they're working on, and just enjoy the community. And lastly, we just enjoy the community. And lastly, we just enjoy the community. And lastly, we got gifts. One of the highlights got gifts. One of the highlights got gifts. One of the highlights >> So, yeah, basically all these videos >> So, yeah, basically all these videos >> So, yeah, basically all these videos they were assembled only using agent, no they were assembled only using agent, no they were assembled only using agent, no regular video editor, and I already regular video editor, and I already regular video editor, and I already posting them on social media. And yeah, posting them on social media. And yeah, posting them on social media. And yeah, it I I have a lot of fun with that.

it I I have a lot of fun with that. it I I have a lot of fun with that. And oh, sorry. And oh, sorry. And oh, sorry. And exclusively for this conference, we And exclusively for this conference, we And exclusively for this conference, we are are are giving our better, giving our better, giving our better, which is our new new second version. which is our new new second version. which is our new new second version. Please give it a try Please give it a try Please give it a try and and and let me know if you have any feedback. let me know if you have any feedback. let me know if you have any feedback. Here is my email. Please Uh free to Here is my email. Please Uh free to Here is my email. Please Uh free to reach out. Uh we're still early. We're reach out. Uh we're still early. We're reach out. Uh we're still early. We're actively working on it. actively working on it. actively working on it. Uh so we will have uh we will be happy Uh so we will have uh we will be happy Uh so we will have uh we will be happy to hear any feedback and also curious to hear any feedback and also curious to hear any feedback and also curious how you use it. how you use it. how you use it. And also um some exciting news. We And also um some exciting news. We And also um some exciting news. We recently got funded by A16Z speed run. recently got funded by A16Z speed run. recently got funded by A16Z speed run. Uh so I'm very excited to uh continue Uh so I'm very excited to uh continue Uh so I'm very excited to uh continue working. working. working. Um Um Um >> [applause] >> [applause] >> [applause] >> Yeah, that's it. Thank you so much. And >> Yeah, that's it. Thank you so much. And >> Yeah, that's it. Thank you so much. And because it's a presentation about because it's a presentation about because it's a presentation about content and how to edit videos, I have content and how to edit videos, I have content and how to edit videos, I have to uh film a video with you all.