Speaking a task to a voice-controlled coding agent, scoped to one named project, lets it split the work into several coordinated threads across desktop and phone.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You already use Codex or a similar coding agent and want ideas for multitasking by voice instead of typing and babysitting one thread.
You run a personal dashboard or 'second brain' project and want a concrete example of wiring live tools like a calendar and meeting notes into it.
You're curious what a genuinely hands-free, walk-around workflow for kicking off dev and content tasks looks like in practice.
SKIP IF…
You're looking for a setup or configuration tutorial — this is a live demo of finished workflows, not a guide to installing Astra voice mode.
You don't already have a coding agent like Codex in your stack, since the whole demo assumes that foundation is in place.
TL;DR
The full version, fast.
This video shows a creator using OpenAI Codex's Astra voice mode to run several build tasks by talking instead of typing. He delegates turning a YouTube video into a formatted X article with auto-cropped, auto-redacted screenshots, building a branded landing page for his community from a saved design skill, and adding a Fireflies-and-calendar meetings tab to his personal dashboard, all inside one named project so separate agent threads share context and can message each other when one needs the other's output. He also kicks off a thread from his phone mid-walk, proving the same delegation works away from a desk. The real lesson is the pattern: scope every task to a project, delegate by voice, then let threads run and coordinate in parallel.
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.
Cold open showing the finished X article and AIS Plus landing page before rewinding to the voice conversation that built them.
03:50 – 05:54
02 · Delegating Tasks With Your Voice
Puts on headphones and asks Astra to spin up a Codex thread for an X article and a parallel thread for its thumbnail, both scoped to his 'Herc 2' project.
05:54 – 08:59
03 · Building Websites and Dashboard Features
Delegates a branded AIS Plus curriculum landing page using his Scrollcraft design skill, then adds a Fireflies-and-calendar Meetings tab to his dashboard.
08:59 – 10:51
04 · Voice Mode on Your Phone
Starts a new voice thread from his phone mid-walk, asking for a rundown of GPT-6 Astra demos on X and a scan of YouTube trends, while the desktop keeps working.
10:51 – 12:09
05 · Reviewing the X Article
Opens the finished X article: a cropped 5x2 thumbnail matched to his YouTube upload, auto-placed screenshots, and auto-blurred sensitive details.
12:09 – 13:10
06 · Adding Meetings to My OS
Reviews the finished Meetings tab pulling in calendar events and Fireflies summaries with action items and a link back to the recording.
13:10 – 14:29
07 · Reviewing the Curriculum Website
Walks through the finished AIS Plus landing page, noting it matched his existing brand's color palette, mountain motif, and pacing.
14:29 – 14:45
08 · Final Thoughts
Sign-off pointing viewers to a follow-up video on the Scrollcraft skill used to build the landing page.
Atomic Insights
Lines worth screenshotting.
OpenAI's Codex now runs a voice mode that can delegate work to multiple coding-agent threads while a person keeps talking.
A single voice command spun up two coordinated threads, an article and its thumbnail, that messaged each other when one finished a piece the other needed.
Scoping every voice task to one named project folder is what let separate threads share the same skills, files, and account context.
The article-generation flow pulled a video transcript, screenshotted the video, cropped the frames, and placed each one next to the right paragraph without being told which shots to use.
Personal or sensitive details caught in a screenshot, like an API key or an email address, get auto-blurred before anything is published.
The agent found and reused the channel's best-performing YouTube thumbnail on its own, without being told which one to pick.
A phone can start and hold its own voice thread while a person walks, and the desktop stays in sync with whatever was kicked off remotely.
A connected dashboard pulled a Fireflies meeting summary and Google Calendar events into one new scrollable Meetings tab, built entirely by voice.
Keeping a named design skill attached to a project let a brand-new landing page automatically match an existing site's color palette and motion style.
The agent volunteered to crawl the workspace for brand context on its own, rather than needing every visual detail spelled out.
Takeaway
How one voice command turns into several coordinated Codex threads
WHAT TO LEARN
Naming a shared project, not just a task, is what lets a voice-controlled agent split work across desktop and phone threads that still coordinate with each other automatically.
01What Astra Voice Mode Can Do
A voice interface for a coding agent removes the friction of typing out multi-step build requests, so an idea can be spoken as fast as it's thought.
Showing the finished output before explaining the process sets a concrete bar for what a broad automation claim actually has to prove.
02Delegating Tasks With Your Voice
Naming the exact project, not just the tool, when delegating a task is what lets an agent inherit the right files, skills, and prior context.
Two agent threads can be told to coordinate directly, so an asset approved in one thread automatically becomes usable context in a related thread.
Reusing an existing, proven asset instead of generating something new can save an entire design step.
03Building Websites and Dashboard Features
A named design skill attached to a project functions like a style guide the agent checks against every time it builds something new.
Loose creative direction is enough when the underlying skill already encodes the brand's visual language.
Unrelated builds can run in parallel threads while a person keeps talking about something else entirely.
04Voice Mode on Your Phone
A voice-controlled agent that works the same way on mobile turns dead time, like a walk, into time spent kicking off real work.
Starting a new thread from a phone doesn't interrupt an existing desktop conversation, so a person can multitask across devices.
Asking an agent for a live trend scan of a niche is a fast way to get a directional read without doing the research manually.
05Reviewing the X Article
An agent with access to screenshots can automatically crop them to the relevant frame and place each one next to the paragraph it illustrates.
Automatic redaction of sensitive details in screenshots is a real safeguard worth checking for before trusting an agent with publishing access.
A phone-initiated research thread can independently gather and cite sources without further guidance.
06Adding Meetings to My OS
Combining two existing tools into one new dashboard view is often a matter of asking, not custom engineering.
A meeting summary that surfaces action items alongside a one-line recap makes a dashboard usable at a glance instead of requiring a click into every event.
07Reviewing the Curriculum Website
An agent building a new page can pull existing brand assets from elsewhere in the workspace without being handed them directly.
Matching an established site's visual vibe is what makes a new page feel like a continuation of a brand instead of a bolt-on.
There's still room for a human's aesthetic judgment, even after an agent-built result is otherwise satisfying.
Glossary
Terms worth knowing.
Codex
OpenAI's coding agent product, which can run autonomous work in separate threads and, as shown here, be controlled through spoken commands instead of typed prompts.
Astra voice mode
A voice interface for Codex that routes spoken instructions into Codex's underlying automation, letting someone delegate and check on tasks without typing.
AIS / AI Automation Society Plus
The creator's paid community and curriculum, referenced here as the project that gets a new branded landing page built during the demo.
Fireflies
A meeting-recording and summarization tool that transcribes calls and extracts action items, pulled into the dashboard's new Meetings tab.
Scrollcraft
The creator's own named skill for building animated, layered scroll websites, used here as the design system behind the new landing page.
Resources
Things they pointed at.
00:00toolCodex
00:00toolGPT-6 Astra voice mode
00:48productAI Automation Society Plus (AIS Plus)
06:15toolScrollcraft (creator's own website-design skill)
07:43toolFireflies
01:28toolClickUp
01:28toolSlack
Quotables
Lines you could clip.
03:08
“Cost doesn't justify price. Price justifies cost. What is the value of what you know and what you know how to do?”
sharp, standalone reframe of value pricing with no setup needed→ IG reel cold open↗ Tweet quote
08:29
“I didn't tell it to find this exact thumbnail. It looked through my YouTube probably to see which one was the live one.”
concrete, surprising example of agent initiative→ TikTok hook↗ Tweet quote
11:17
“If I have like an API key in there, or if I have like a personal email, it actually will like blur it out. So it does that automatically.”
practical safeguard detail viewers will want to verify themselves→ newsletter pull-quote↗ Tweet quote
13:51
“It feels like it just will contextualize and ask you questions and crawl through things first because it wants to make it more specific to you.”
closing thesis line on why the agent felt different→ IG reel cold open↗ 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.
17px
metaphor
Hey there, Astra. I've got a few tasks today. The first one that I want you to help me do, I want you to delegate off to a codex thread where we take a video that I made on YouTube a few days ago, or actually no, it was just yesterday.
So I want you to turn that into an X article for me and put it in my X account. Got it. Let's line that up.
So that X article is ready. Let me open this up and we'll take a look. We can see that we have...
All of this formatted. We have that 5x2 thumbnail that we wanted that matches our YouTube one. And now we can see that these screenshots are coming through.
So the prompt, it analyzed the entire video, screenshotted it, put this in here. It even cropped it, if you guys noticed. This isn't the full screen.
But it's matching these up because it understands what am I seeing in this image and where do I put it in the text based on the actual article that was written. Let's also try something else. So inside of my school community, AI Automation Society Plus, we just did a little bit of a revamp to the actual course.
So if you could sort of just like... look in there, get familiarized with that course structure and just help me build a really simple, you know, AIS branded landing page. Yep.
I'll start on that. All right. I just got word that the AIS plus curriculum page is done and it's looking pretty impressive.
Let's open it up full screen. Holy, this is actually. the courses so i just built this entire personal os with just my voice using gbd6 astra voice mode now at a glance it might not seem too impressive but it had to figure out how to connect my entire herc brain it had to go pull all the data from these sources it had to connect my real calendar and this is actually functional meaning here's my actual calendar and if i came here and i wanted to add an event right here we'll just call this test save event this is actually going to reflect on my real calendar over here Now there are still a few things that I'm looking to connect, but I can communicate with my team through Slack, ClickUp, and email right from this interface.
So I can open up this conversation and I could reply to it right here. And I can also kick off new threads via email or ClickUp. from here as well.
And I also have community polls from YouTube, from my school communities, what they're stuck on, and I also have industry polls from X, YouTube, things like that. The reason voice mode is so powerful is because it just uses Codex on the backend, which means it can look through your AI operating system and it can do everything that Codex can do, but you can control it with your voice and multitask, kick off different threads.
You can do it from your phone, so you can literally be on a walk and doing everything you need to be doing. And the browse use capabilities from GBD6 Astra are the best I've ever seen. Right here on screen, you can just see a silly example where I gave it two pictures and I had it paint me in Canva.
And this did take quite a while, but if you think about all of the little strokes and everything that it needed to do, both on the vision side and the browser use side, it's actually pretty impressive. Now on top of all of the capabilities, you also need it to have the right context and connections to actually be useful.
So when I tell you guys that I've been talking to Astra in voice mode, and it's just been feeling like it actually knows everything about me and my business, it's on another level. So we just had an event in July called AIS Live, and right here there's over 150 gigabytes of footage to look through. So I gave Codex this link, and I basically just said, hey, We need like a 60 second sizzle reel from this event, like a recap.
And in only two prompts, this is what I get back, which is really impressive. Logged off yesterday, just pausing. I had goosebumps.
I was so excited and I had so much fun.
Cost doesn't justify price. Price justifies cost.
What is the value of what you know and what you know how to do?
This culture that we have here at AIS is just really special.
If you think about the actual story that it told and how much data it looked through and what it was able to create, that was really, really impressive, like I said. So anyways, let me stop yapping to you guys and start yapping to GBD6 Astra and show you guys what it can do. So all you're going to do is down here, you can see there's a little button called Start New Voice Chat.
You're going to click on that. And now it's time to put my headphones in. Hey there, Astra.
I've got a few tasks today. The first one that I want you to help me do, I want you to delegate off to a codex thread where we take a video that I made on YouTube a few days ago, or actually no, it was just yesterday. It was called, like, Astra Made This.
It made the whole video. So I want you to turn that into an X article for me and put it in my X account. Got it.
Let's line that up. And while you're working on that, can we have a separate thread actually start making the thumbnail for that? Sure.
Adding that as well. Now, I do want to make sure that you're using all my right skills and my right context. So make sure you're working inside of my HERC 2 project for all of these little tasks that we're going to kick off today.
Got it. I'll make sure that's the context going forward. The original article task has been told to stop and hand off any verified fine -nails, and the thumbnail task has just been told the same.
Okay, awesome. Yeah, because I see that you kicked off two regular chats, and these wouldn't have had the same context, so it's important that I told you to work inside my HERC 2 project, and now you should be kicking off the right ones up there, and it looks like you are.
Yep, doing that now. And the article task now has the thumbnail task's details, so they can coordinate the source, the angle, and the finished cover. Both replacements are running inside Herc 2.
Awesome. Now, for the actual thumbnail I want for this X article, I actually already made one that I really like. The one that I put on my actual YouTube channel, it was like an image of...
It was like me with my feet up on the desk, and the... OpenAI logo was editing the video. So all I really actually need you to do there is if you could just turn that into a five by two version so it fits into the X article.
Sure, I'll update the thumbnail work with that. Awesome. So I know that probably will take a little bit of time.
So just let me know when those are done. Let's also try something else. So inside of my school community, AI Automation Society Plus, we just did a little bit of a revamp to the actual course.
So if you could sort of just like. look in there, get familiarized with that core structure. I'm talking about the AI Automation Society Plus group.
Inside of that one, if you could just analyze the structure real quick and understand sort of like the transformation from a new joiner to the end state once they've taken all the courses and just help me build a really simple, you know, AIS branded landing page that I could basically send people to if they're like, hey, you know, what is AIS Plus?
I could send them there and they could get a rundown of what that curriculum looks like. And I want you to also design that. in a way where you use my scroll craft skill to have layers and to have it be you know dynamic and visual but don't make it too overwhelming so if you could start designing that website as well based on that knowledge yep i'll start on that and i'll keep the design dynamic but not overwhelming awesome so now i see that i'm talking to you in one thread But then I can also see when I look at all the threads that you're kicking off, I can see how you're clearly multitasking.
And by the way, I see the thumbnail that you made. That looks great. That's exactly what I was looking for.
Will my other thread that is making the actual article, it knows that that's there? Oh yeah, it looks like you sent that exact message where I said that looks great. That's exactly what I was looking for.
So you are able to actually coordinate these different codex threads to talk to each other. That's right. The article task has the approved cover and your Go ad.
Awesome. Well, while I wait for... me to be able to verify that that all worked.
Could you, let's make another improvement to the UpIt OS. Let's see if we could add, I guess, let's add another section for meetings. I know we already can see all of my meetings in the actual HercBrain visual, but let's add another tab on the left that just shows the meeting.
So you pull that in from Fireflies, and it's just kind of like a nice visual of the date that the meeting was, and just like... a one -sentence summary of what was discussed, or if there's any important action items from there, just so I can visually see all the meetings that I had, and maybe if there are any important meetings coming up as well.
Okay, I'll take that on. Cool, so while you're cooking on that, I'm gonna go ahead and actually pause this voice chat. I'll pick it back up with you in a bit when you have some updates for me.
But I want to kick off some voice threads on my mobile device and see how that all works as well. So I'll be back in a bit. Okay, so anyways, just wanted to show you guys what was actually going on here.
So it made this thumbnail, which was actually based on, if I go to my thumbnails, this one. So this is the one that I wanted to use because this is the one that did best on YouTube. And I just needed it to make that a five by two.
And what you guys will notice is I didn't tell it to find this exact thumbnail. It looked through my YouTube probably to see which one was the live one. It looked through the local files to actually build that.
Same thing over here. What happened was, I don't know what it delegated around, but all I said was I need an X article for this. And so what it did is it had to pull in the actual video, it's transcribing it, and now what it's doing is it's making the X post, but it also took 11 screenshots.
And so it's gonna place those screenshots in the X article at the right spot. So we'll get to view that in a sec, but I just wanted to call out what's actually going on. on the back end there, because it's very impressive.
But now, I need you guys to look at this. So you can also do this on your phone. So imagine you're on a walk, or you're in your car driving, and you need to kick off some tasks, or delegate some work to your team, or whatever it might be.
Because it has all the connections in here, you're gonna go to remote, you're going to scroll down, and this is where you'll, oh wait, right here, this button. Right here, this is where you'll start a new voice chat. And now it's gonna be the same thing.
Hey. So I need you to help me kick off a thread inside of my HERC 2 project. What I want you to do is I just need a nice rundown of the best use cases that you've seen, the best viral demos that you've seen of Astra 6, you know, GPT -Astra 6 on X.
Sure. So the point I'm trying to make here is that I can keep scrolling on my phone even when it's doing things on the back, and as you can see, it's still keeping this conversation. Got it.
I'll keep going here. Yep, that's exactly it. I kicked off the astro research thread and we can keep talking here meanwhile.
Awesome. So while we're waiting on all this, could you just take a look at the YouTube space? Look at some of my past videos and look at what else is going on in the space and give me a quick analysis of...
maybe some trends and maybe some things to start preparing for. I'll scan the current landscape now. Big trends heading toward 2027 are more AI -assisted production and personalization, deeper community play with memberships and owned audiences, short and long form blending into one funnel, and creators rewarded for building recognizable shows and perspectives, not just one -off uploads.
So the point I was trying to make there was just that you can do this on your phone as well, and it's a super clean, crisp. syncing between your desktop and your phone. So we've got the Up It OS working on adding a Firefly's task or a Firefly's meeting section so I can see that stuff.
We've got the X article being finalized and we'll pull that up. So that X article is ready. Let me open this up and we'll take a look.
We can see that we have... All of this formatted. We have that 5x2 thumbnail that we wanted that matches our YouTube one.
We have all of this formatted in a good way. And now we can see that these screenshots are coming through. So the prompt, it analyzed the entire video, screenshotted it, put this in here.
It even cropped it, if you guys noticed. This isn't the full screen. We keep going down.
This is the full screen. This is a full screen, full screen. But it's matching these up because it understands.
What am I seeing in this image? And where do I put it in the text based on the actual article that was written? And there is nothing sensitive in this video, but what it will actually do too is if I have like an API key in there, or if I have like a personal email, it actually will like blur it out.
So it does that automatically. And now that it's just worked into the skill. So this is now an article that I would just be able to read through.
All of these screenshots are taken. They're cropped if they needed to be. They're blurred out if they needed to be.
And then I can just go ahead and publish it because it... did all of that with just my voice. We can also see that this one that I kicked off from my phone is done.
It searched through X and it found multiple posts, one from Ben Davis, one from Ethan, one from Thomas. You can see that it gives us the actual link to all of these threads. So if I want to click on this 3D graphics build, I get taken straight to that actual post.
1 .3 million views. I did see this one. This one was pretty impressive.
We can see that now we have this little rundown. And if we would have stayed on the voice chat, it would have told us about all this. It looks like the Up It OS one is also done.
Let's see what happened over here. Meetings is live. So let me open this up and we'll see.
Actually, I'm gonna open this up full screen. We now have a section called Meetings. You can see on the calendar, I've got one tomorrow, I've got one on Monday, and we can actually pull up the actual calendar details.
So if I open this one up. does this take us straight to the calendar yeah it takes us straight to the actual calendar and we see the event details there and now we can also see past meetings so this all hands we can see the team reviewed learning community growth product updates operational improvements ai tools and a shared mission centered on customer happiness we have an action highlight nate herc share bookmark links to the most used google drive folders yep and we can see other action items here and we can also open up this recording which takes us straight to fireflies so that quickly we were able to develop a new section into our actual um os here which is a combination of fireflies and google calendar and i don't even know if it uses any ai in the background because fireflies already processes these ai action items maybe it hit you know the gbt endpoint or the anthropic endpoint to actually put this stuff in here but really impressive all right i just got word that the ais plus curriculum page is done and it's looking pretty impressive let's open it up full screen build the skills shape what's next and we've got holy this is actually the courses i wonder if it
Okay, it takes you down to here. There's like a curriculum section. Now, I think this looks really good.
It pulled a picture of me. You also will realize that the background, right? The background, you can see these layers.
The mountains are in different spots. They move in different, you know, paces. But what I love about this that it did is if I actually go to our AI Automation Society website, it kept a very similar vibe, right?
Like the blue feeling, the backgrounds of the mountains and stuff, even on the certification tab, it kept the consistency. Now, honestly, I think these... mountains like a little bit cooler and there's like fog but it kept everything on brand because it was able to crawl through my workspace look up what it needed to look up to make sure that it actually understood what i was asking for and that's what i think is so cool about astra is when you give it a task it feels like it just will contextualize and ask you questions and crawl through things first because it wants to make it more specific to you and that's what is just really really cool i mean this is this is the actual curriculum if i go to ais plus i go to classroom That's exactly what happens.
You know, these are the actual courses. And then over here, wrong one. These are the actual courses that we have in there.
So it was able to look through all of that and build out the actual curriculum. I think this is really, really slick. So anyways, guys, that is going to do it for this one.
Get into Codex and start playing around with that voice mode. And if you want to learn more about how I build websites like this using Astra and using my Scrollcraft skill, then check out this video right up here. I walk through the whole thing.
I hope to see you guys over there. But thanks for watching. See you guys.
The Hook
The bait, then the rug-pull.
The video opens mid-demo, with the finished X article and landing page already built, before rewinding to show the single voice conversation that produced both.
Frameworks
Named ideas worth stealing.
04:00concept
Voice-delegate-by-project workflow
Speak a task to Astra voice mode and have it kick off a dedicated Codex thread scoped to a named project, so the thread inherits the right skills, files, and connected accounts, then keep talking to start more threads in parallel.
Steal forany coding-agent setup where multiple tasks need to run at once without losing shared context
04:40concept
Cross-thread coordination
Two separate agent threads (an article thread and a thumbnail thread) are told to talk to each other directly, so an approved asset in one becomes usable context in the other without the human relaying it.
Steal forany multi-agent build where one output (a design, a draft) feeds another
CTA Breakdown
How they asked for the click.
VERBAL ASK
14:29next-video
“if you want to learn more about how I build websites like this using Astra and using my Scrollcraft skill, then check out this video right up here”
soft sign-off pointing to a companion video rather than a hard sales pitch inside this one
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
One creator ran two frontier AI agents through the same 15 real work tasks and tracked the winner, the time, and the exact dollar cost for every single one.
A hands-on tour of a synced, phone-controllable AI agent team — agent computers, teachable skills, scheduled routines, event triggers, and where it stops making sense versus Claude Code or Codex.
A five-prompt AI agent build produced a working Calendly clone with live calendar sync and Stripe payments, then the real bill showed up: five days of agent runtime and about $15,000 in inference.
00:16
00:27
00:38
00:49
01:00
01:11
01:22
01:34
01:48
01:56
02:02
02:12
02:30
02:45
02:47
02:57
03:08
03:19
03:31
03:41
04:08
04:19
04:31
04:42
04:53
05:04
05:15
05:26
05:37
05:48
05:59
06:21
06:32
06:43
06:54
07:05
07:16
07:28
07:39
07:50
08:01
08:12
08:23
08:34
08:45
08:56
09:07
09:29
09:40
09:51
10:02
10:13
10:25
10:36
10:47
10:58
11:09
11:20
11:31
11:53
12:04
12:15
12:37
12:49
12:59
13:10
13:22
13:33
13:40
14:06
14:17
14:28
38:35
20:32
16:27
05:23
14:19
13:59