GPT-6 Astra's computer use lets Codex operate a screen directly, so anything without an API or connector can still be scripted once and reused as a repeatable workflow.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You build with Codex or Claude and keep hitting tools, apps, or sites that have no API to hook into.
You want repeatable automations for tasks like flight-price tracking, video export handoff, or settings audits.
You maintain your own app or MCP server and need a way to simulate a stranger's first-time setup experience.
SKIP IF…
You're looking for API-based integration tutorials. This is specifically about screen-level agent control, not APIs.
You don't have access to Codex or a similar computer-use-capable AI agent yet.
TL;DR
The full version, fast.
GPT-6 Astra's computer use lets Codex operate a screen directly, which matters most for tools that have no API or connector. The video walks through five workflows: turning a manual Google Flights search into a reusable command-line tool that ran 70% and 49% faster than plain browsing in two follow-up tests, having Codex open Claude Desktop to stress-test a personal MCP server, using one AI agent to audit another agent's own computer-use feature until it finds and explains a failure, automating the render-to-Descript-to-Google-Drive handoff after a video export, and configuring a new Instagram account's creator settings through Apple's iPhone Mirroring app. The throughline: point computer use at anything that lacks a backend, and a one-off manual task becomes a workflow you never have to touch by hand again.
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.
Kashef states the thesis: computer use isn't new, but GPT-6 Astra in high mode takes it far enough to be worth rebuilding workflows around. Previews the five use cases coming up.
00:46 – 03:44
02 · Turn Google Flights searches into a reusable CLI
Codex's internal browser searches Google Flights for a Montreal to Sydney trip, then builds a standalone command-line tool from that session. Kashef iterates on it to handle multi-city and open-jaw routing, not just the one route it was built on.
03:44 – 04:39
03 · CLI vs. browser: the speed tests
A fresh session compares the finished CLI against plain computer-use browsing on two new routes. Toronto to Lisbon dropped from 77.4s to 23.1s; Toronto to Seoul from 50.2s to 25.7s.
04:39 – 07:40
04 · Test MCPs and tools inside Claude
Codex opens Claude Desktop and tests Kashef's own Early AI-dopters community-brain MCP server: finding a lesson, citing its source, and running several back-and-forth exchanges to check the first-time user experience.
07:40 – 10:29
05 · Let one AI agent test another
Codex opens Grokky, Kashef's own GrokBot clone, and tries to use Grokky's built-in computer-use feature to search Google Flights. The run fails when the underlying model runs out of context window, and Codex reports back rather than papering over the failure.
10:29 – 13:25
06 · Automate your Descript editing workflow
A demo run of a render-to-Descript-delivery skill: upload a finished render, send an editing prompt, review the transcript-driven cuts, check frames for stray moments, export in 4K, then hand off via Google Drive and WhatsApp.
13:25 – 16:16
07 · Control iPhone apps from your Mac
Using Apple's iPhone Mirroring, Codex takes control of Kashef's actual phone to configure a new Instagram account's creator settings: media quality, sharing and reuse toggles, and discovery options, while leaving DMs and posts untouched.
16:16 – 16:54
08 · Get the free prompts and Google Flights CLI
Kashef closes by pointing to the free kit (field guide, prompts, and CLI source) and his paid community for anyone who wants to go deeper.
Atomic Insights
Lines worth screenshotting.
Computer use turns any app without an API or connector into something an AI agent can operate and reuse as a workflow.
A flight-search CLI built once with computer use ran a repeat search in 23 seconds versus 77 seconds for plain browsing, a 70% time cut.
The same CLI approach cut a second route's search time roughly in half, from 50 seconds down to 26 seconds.
You can build an automation with a frontier model's computer use once, then hand daily execution to a cheaper or local model.
Testing an MCP server for real means having an agent open the actual app, like Claude Desktop, and run the same first-use flow a stranger would.
Watching one AI agent audit another agent's computer-use feature surfaces failures, like a smaller model running out of context mid-task, that the builder wouldn't catch alone.
A rendering pipeline that's '80% automatable' with a tool's own CLI can be pushed to 100% by adding computer use for the steps that only exist inside a GUI.
Apple's iPhone Mirroring app lets a desktop AI agent take control of a physical iPhone screen, not just simulate one.
Auditing a new Instagram account's creator settings by hand takes personal research; delegating it to computer use with a clear guardrail took about five minutes.
Telling an agent to use its own internal browser, instead of your existing Chrome, keeps the automation from silently borrowing your logged-in sessions.
Takeaway
Point computer use at anything without an API
WHAT TO LEARN
When a tool has no connector or API, running a computer-use agent against its screen turns a manual, one-off task into something you build once and reuse indefinitely.
02Turn Google Flights searches into a reusable CLI
A repeatable command-line tool built from a single computer-use session turns a manual search into something you, or a cheaper model, can rerun on demand.
Building the CLI with a frontier model's computer use, then executing it with a lower-tier model, separates the expensive one-time engineering from the cheap recurring use.
Explicitly telling the agent to use its own internal browser rather than your existing Chrome session keeps the automation from silently piggybacking on your logged-in accounts.
03CLI vs. browser: the speed tests
In a same-route rerun, the CLI finished a flight search in 23 seconds versus 77 seconds for plain browsing, a roughly 70% time cut.
A second route showed a smaller but still real gain, about 50% faster with the CLI than with browser-only computer use.
Speed gains from an automation are only proven by testing a brand-new request in a fresh session, not by rerunning the same search you built it on.
04Test MCPs and tools inside Claude
The most realistic way to test an MCP server is to have an agent open the actual app, such as Claude Desktop, and go through the exact first-use flow a stranger would.
Asking for a few conversational back-and-forths, not just one exchange, surfaces whether a tool holds up across a real session instead of just answering a single query.
Watching the agent click into tool-call dropdowns exposes what's actually happening behind a response, including inefficient code the source pointed to.
05Let one AI agent test another
Handing one agent's computer-use feature to a second agent to audit is a way to battle-test a feature that's otherwise hard to evaluate objectively.
A failed test is useful data: it traced the failure to an older model with a smaller context window, not a flaw in the computer-use approach itself.
Instructing the auditing agent to reproduce a failure, isolate the smallest cause, and retest, rather than working around it, turns a bug report into an actual fix path.
06Automate your Descript editing workflow
A render-and-deliver pipeline that a tool's own CLI can only get 80% of the way through can be completed by adding computer use for the remaining GUI-only steps.
Automating the post-render checklist, upload, prompt, review, export, and delivery link means edits can happen and ship while you're away from the machine.
Having the agent visually check frames before finalizing an edit, for stray coughs, dead air, or off moments, is a check a CLI alone can't perform.
07Control iPhone apps from your Mac
Apple's iPhone Mirroring gives a desktop agent literal control of a phone's screen, so an app with no desktop version isn't out of reach for automation.
Giving explicit boundaries, no DMs, nothing destructive, reversible changes only, let an agent safely audit and adjust real account settings unsupervised.
A five-minute settings audit replaced manually hunting through nested menus for lesser-known creator options.
Glossary
Terms worth knowing.
Computer use
An AI agent capability that lets it see a screen and control the mouse and keyboard directly, so it can operate software that has no API.
CLI (command line interface)
A text-based tool run with a typed command instead of clicking through a graphical app, used here to make a one-off browser task repeatable.
MCP (Model Context Protocol) server
A connector that lets an AI assistant such as Claude or Codex pull in outside data or tools, like a community's saved lessons.
High mode
A setting that gives a model extra reasoning steps to work through a task, used here for the more complex computer-use jobs.
iPhone Mirroring
An Apple Mac feature that displays and lets you control a connected iPhone's screen from the desktop.
Context window
The amount of conversation and screen data a model can hold at once. Running out of it mid-task caused one of the demos to fail.
“Mastering how to use this one feature will allow you to unlock all kinds of workflows, especially ones that don't have things like connectors or APIs.”
States the whole video's thesis in one sentence.→ TikTok hook↗ Tweet quote
03:55
“We went from 77 seconds with a vanilla browser to 23 seconds with the CLI, which is almost a 70% reduction in time.”
Concrete before-and-after number that proves the technique works.→ IG reel cold open↗ Tweet quote
10:14
“My app's computer use ended up failing for two reasons. One, I'm using an older model, which doesn't have as big of a context window.”
Honest failure moment that makes the demo credible instead of a highlight reel.→ newsletter pull-quote↗ Tweet quote
12:40
“Up until now, it's been able to take me to 80%. But now with this computer use, you can take processes that have been 80% possible and bring it all the way to 100%.”
Clean framing for why computer use matters even when a tool already has its own CLI.→ TikTok hook↗ 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
One of the biggest upgrades with GPT -6's Astra is how well it can use your computer. I've been having it do everything from testing desktop applications that I've already built to working through video edits, to even controlling applications through my phone, from my computer. Mastering how to use this one feature will allow you to unlock all kinds of workflows, especially ones that don't have things like connectors or APIs.
So in this video, I'm going to walk you through the five different ways that I've been using it. So by the end, you'll be able to adapt them to your day -to -day workflows. Let's get into it.
Now computer use on its own isn't a brand new feature. It's existed for the past year and I've covered it multiple times on this channel. But GPT -6, especially if you put it on something like high mode, takes it to the next level.
Now like I said, I'm going to walk through these five different use cases and start off with a very familiar workflow. So when it comes to doing something like booking a flight, this is something that we've been able to do for more than a year using a basic version of computer use. But with the firepower of Astra, not only can we do it once, but we can build our own reusable workflow and create our own command line interface for a platform that doesn't have an API or a programmatic way to look for things like flight deals.
Now, I personally have a keen interest in this because back in high school, I had a small business where I would give access to a series of Python scripts where I would use them to find flash deals. Back in the day, this used to be rocket science, but now you can do it with just a simple prompt. So not only are we going to execute a search and look for the best deal, but we're going to make it so that we can keep doing this whenever we want and have programmatic access that you can make available to your agents.
To run this, we're going to combine computer use with Codex's internal browser and send over the following prompt. Build a reusable flight search command line interface between Montreal and Sydney for these dates, for these number of people, and this currency. I want to be able to reuse it to set up a scheduled task to look for steep price decreases on business class flights to my favorite locations.
To make sure it actually uses its internal browser, I like to explicitly call it out because otherwise once in a while it might use Codex and Chrome and actually take advantage of your existing browsers versus using its own. So if we send this over, you're going to see how quick it is, especially if you go on fast mode where this is going to go.
almost instantly compared to where we were last year, it's going to find ideally the best deal and start to reverse engineer how it got there. So we can do this more programmatically in the future. And after it executes the search and looks for the best deal, it starts looking at its own docs to see how it can build a vanilla command line interface that we can use from any agent with any model.
So one of the many advantages of doing something like this is that you can have Astra do the hard work the first time, and then you can execute this workflow with a lower level model. Now, after a few minutes, we get the first version of the CLI, but it seems to be over -indexed on this specific route. So then I ask it to do the following.
Is it optimized to work with any combination? And is it smart enough to test out things like multi -city travel? Now, if you don't know what that is, sometimes you can get a cheaper flight option on a specific route by going from one city one way to the next until you finally get to your destination.
So not only do I want it to be more resourceful out of the box, but I also want it to tap into its hidden knowledge on training data, because I'm sure it's gone through tons of blogs and snapshots on how to use points, different types of points, and go to certain types of airports to get the best bang for your buck. Now it's testing different combinations of cities to see if there's any difference whatsoever in the price.
After some more tweaks, we have a more robust version that's more flexible, can choose different depart and end dates and structure a trip in different ways. But this is not actually helpful unless this CLI is way faster than redoing this process every time using computer use. So the next step is making sure that we test a random flight request in a brand new set of sessions, one that's using the CLI and one that's just using the plain vanilla computer use.
So this ran for close to seven minutes, and these were the results. For the first test, planning Toronto to Lisbon, we went from 77 seconds with a vanilla browser to 23 seconds with the CLI, which is almost a 70 % reduction in time. With the second test, we went from Toronto to Seoul from 50 seconds down to 25 seconds, so almost exactly 50 % less time.
Now with this example, I'm just scratching the surface. There are likely many softwares and tools that you use in your day to day that might not have a backend, an API or an MCP. So doing something like this, where you use computer use to create a command line interface so that you can then use it with any agent you want, whether it's a local model or a lower tier codex model, this will create a brand new path of least resistance.
Now, the second use case is probably something that you haven't tried before. If you've ever created or worked on your own MCP, whether it's being used by only yourself, a small team, or an entire company, you know that the hardest thing to do is simulate testing. More specifically, what does it look like for someone to take your MCP server, hook it up to their cloud or codex, spin it up, and use it for the first time?
So what I'm about to show you is Codex setting up and installing an MCP server into Cloud Code and then opening Cloud Code and testing it to see how smoothly it runs, how much time it takes, and basically maps out the entire user journey. So as an example, this is one of the MCPs that I put together recently. It's basically a layer between my community and its posts and my comments that someone can tap into and use in cloud and codex seamlessly to ask questions about general knowledge related to community content or things that might have popped up in prior conversations.
So let's say you already had your own tool or MCP and it was ready to be tested. You could send over a prompt like this, where you can literally ask Codex to use computer use to open cloud desktop because it already exists on your computer. So it has access to it and then test the existing EA community brain MCP, ask it to find a classroom lesson about building or testing MCPs, then give its title source link in three useful points, show the actual tool call and check one point against the source.
Now I'm going to add one more line here. I'm going to say, Have a few back and forths so we can make sure that the user journey in using this tool is as smooth as possible.
And once we send it over, I added one detail, which is to use the Cloud Code tab. And this should be enough for it to open the app, double check it's on the right tab, then check it has the MCP server, then initiate the conversation. So you can see right here, it's double checking that it's not on the cloud code tab.
We'll just click on always allow here. Now it is. So it should be able to go and click and double check that the connector is indeed connected and send over this request.
So the best part of this is not only is it monitoring the conversation, it's also clicking down on the dropdowns to see exactly what's happening behind the scenes. So you can see all the lessons that are being pulled, the exact sources and everything in between. It then reads the response and sends a follow -up.
And the coolest thing is you can apply this to all kinds of scenarios, whether it's cloud code or if there's no specific plugin for Gemini for whatever reason, you can open up the Gemini desktop app and have Codex use it and in a way have a back and forth between them without ever using an API or any form of plugin. And 20 minutes later, it comes back after a thorough back and forth to not only give me feedback about the MCP, but also if I kept scrolling, it has source code that it monitored that said, basically the way you structured this function and this function is not very efficient and causes delays and latency.
And again, this process is not limited to MCPs. If you built a series of skills and you want to make sure that your skill that works in Codex works just as well in Claude, this would be another way you could do that. All right, so use case three is my favorite, and it's likely to be the one that's the most applicable to your day -to -day workflows.
Whether it's a desktop app or a mobile app that you're using something like TestFlight on your computer to go through and test the user journey, you can ask computer use to take over the app, battle test it in the exact same way you saw me do it in Cloud. So let's say you're testing a desktop app or a mobile app on your computer.
As long as you give it the guidance, not only can you test it, but once it finds bugs, assuming that it has access to that code, it can keep improving the app, testing it until the goal is reached. So let's take this app that I put together, which is my recreation of Grokbot, where I've connected it to a series of agents and has access to things like my codex subscription, open router, et cetera.
And I've even added the ability to easily add multiple agents and have them work together and give them their own computer. But of every feature that I've built so far, the computer use is the weakest because it's the hardest to teach a completely vanilla agent. So what if we did computer use section where we use Codex's computer use to audit this app's computer use and keep improving it until it's perfect.
So let's say we send this prompt. Open Grokki, my Grokbot clone, and test its computer use feature through the app. Watch Grocky browse, check one requirement against the page, and reopen the conversation to verify it persists.
Send a request around Google Flights, like we did earlier, that will explicitly ask it to use its computer abilities. And then, just to avoid you and I having to wait hours, we just want it to send a message, monitor it, and come back. In actuality, I would want this to run for hours, using maybe something like a slash goal, and wake up to a series of bugs that were identified and fixed.
So when we send the request, it spins up the app and right now it should enter the prompt. There it is. It says, use your computer use abilities.
It should automatically allow this. And then it should monitor what's happening with the computer use. And it's smart enough to realize that there's a component in the app where you can spy on what's happening.
And there you go. There is my vanilla agent trying to use Google Flights. And we are watching computer use, watching computer use to see how well it does.
Now because I have all of the actions in the tool calls very transparent, it can start to really understand what is taking too long, what am I over -engineering or under -engineering to make this as smooth as possible. So my app's computer use ended up failing for two reasons. One, I'm using an older model, which doesn't have as big of a context window.
And I haven't built a feature that helps compact the conversation. So Codex was able to test it out and see very quickly that it failed the test. And theoretically, if you told it that its goal slash goal was to make this computer use as amazing as possible, it would see that failure, adjust the code, then redeploy, then re -spin up the app, and go through that loop until it was better.
Use case number four is automating your editing workflow. And whether or not you're a content creator, you should be able to at least learn a few tricks with this workflow that you can apply to something else. Now in my case, after I finished recording these videos, I rendered them in 4K.
And depending on the length and whatever else is running on my computer, that can take anywhere between 40 minutes to four hours. Now let's say I'm up late recording a video like I am this one and I don't want to wait until 3, 4 a .m. for it to render to then make some slight edits before I ship it off to my editing team.
So with the help of computer use, I was able to build a workflow where all I have to do is click render and export the video and then Codex can keep pulling and double checking every 30 minutes how far the video is and how close it is to finally rendering. Once it's done, it can open up Descript, then take the video, upload said video to Descript, wait until it's ready, then send a prompt into the actual chat where you can't actually do this programmatically, at least not that easily.
Then wait for the response, click through all the different frames to make sure there's no random scene where I'm coughing or just dying, which happens more than you think. And then it can export it, double check the export, send it to a Google Drive folder, and then take that link and share it with my team. Now these tools like Descript have a command line interface of their own.
And up until now, it's been able to take me to 80%. But now with this computer use, you can take processes that have been 80 % possible and bring it all the way to 100 % with the few parts that need a human in the loop. Now, naturally, I can't render a video while I record a video.
So I'm going to send a simulated request to take an existing video and just show you what the process would look like for Descript. So I would say use the render to Descript delivery skill in demo mode. Go to my videos folder and I have a video related to the current state of the AI market.
I want you to take said video and execute this process as is. So when I send this over, this should open the Descript app. then upload said video.
Then once it's done, start going through the editing process. Once it's done uploading the video, it sends this mega prompt on my behalf. waits for the response, sees all the tweaks that happened to the transcript on the left -hand side, then it physically clicks through the video frame by frame to see if I'm looking a little bit too shady like this, and sees if there are areas for us to cut out based on, let's say, silences where there's a lack of audio in one section.
And I do this to make it as easy as possible for my editing team to take the raw video and add some polish. And once it audits the transcript and makes sure that all of my infinite stutters have been removed, it clicks on export in 4K, waits for it to export. Then once it physically sees it on screen completed, then it will go and create a Google Drive link using the Google Drive connector and take the process from there all the way to opening up my WhatsApp on my computer and sending a message with the link.
Then the last case isn't something that you would typically use computer use for, but it's unbelievably effective. So I just finished setting up my brand new Instagram account where I'll be making all kinds of new AI content. And by the way, if you want to follow me, follow the handle that you see on screen right now, I'll start being active very soon.
But anyway, as an Instagram new, there are a series of settings that I'm supposed to toggle on and toggle off to increase the likelihood that I do well on the platform. Instead of me having to go through it myself and spend time on my phone, I would rather Codex use computer use to do the same thing. So we could send a prompt like this that says, use the iPhone mirroring app I opened to configure Instagram on my actual phone.
And let's add some detail. I just set up a brand new account and I want to make sure that anytime I upload a new video, that we have all the settings optimized for a new creator to make sure that my videos do as well as possible. I'm aware from some Instagram videos I've seen in the past that there are some hidden features or settings that I should toggle on or off.
I want you to take control of my Instagram, not send any form of DMS. Don't do anything destructive, but go and optimize all of the easy settings that you can. So if we send this over, this should be able to open up the iPhone mirroring app on my Mac, take control of it, take control of the phone, which I found to be a huge surprise, and click through that specific app.
Now that I've sent this over, it should open the iPhone mirroring app, go and search for the Instagram app, go through, double check it's on the right account, then go through the settings. So it's connecting to my phone. It should go and click on the search bar right now and enter the Instagram app.
There we go. It's clicking through. It's spotted it without even searching for it.
It's already in settings and activities. So it's double checking that it's on the brand new right account. Then it's going to go back, click through, and do what it needs to do to make sure that everything is optimized as possible.
So it goes to the media quality tab where it toggled on the highest quality. And it's just going through what seems to be any core things in its training data that tells it these are the core things to focus on. And as this continues to go through my settings, you can imagine that any one of your apps that doesn't have a desktop equivalent, you can go through, navigate, clean it up, check features, check user journeys, et cetera.
So you could theoretically spin up a series of sub -agents to go do some deep research for how to optimize your Facebook profile or your X profile or whatever, and then have it go through and implement all the changes that it found in its research. And just like that, five minutes later, it goes through and gives me a full checklist on what it did, what it toggled on and off, and then we're ready to go.
And that's pretty much it. So hopefully this gives you a full breakdown as to how powerful Asterisk computer use can be and how you can apply it to 10x your existing workflows. If you want access to any of the prompts that I showed you, including the Google Flight CLI that you can use for finding flight deals or automating your next trip, I'll make all of them available completely for free down in the second link.
And for those of you that want to go deeper and master things like Astra and get more exclusive content, I've already released a separate video for my community on exactly how I'm prompting and using Astra for a variety of use cases. If you want to master Cloud, Codex, and everything in between and find a way to monetize your skills, check out the first thing down below and maybe I'll see you inside.
For the rest of you, if you found this video helpful and you found something that might help you today, I'd super appreciate a like on the video and a comment if you so choose. I'll see you in the next one.
The Hook
The bait, then the rug-pull.
Mark Kashef opens by naming the upgrade that changed his own workflow the most: not a smarter chatbot, but an agent that can actually drive a screen. He spends the next sixteen minutes proving it across five different jobs, from flight research to phone settings nobody wants to touch by hand.
Frameworks
Named ideas worth stealing.
00:00list
Five computer-use workflows
Turn a manual browser search into a reusable CLI
Test your own MCP server inside another AI app
Have one AI agent audit another agent's computer-use feature
Automate a render-to-editing-to-delivery handoff
Configure phone app settings through screen mirroring
The five recurring jobs Kashef hands to computer use, each one picked because the target tool has no API or programmatic path in.
Steal forAny workflow where the blocker is a GUI-only tool rather than a missing model capability.
CTA Breakdown
How they asked for the click.
VERBAL ASK
16:54product
“If you want access to any of the prompts that I showed you, including the Google Flight CLI that you can use for finding flight deals or automating your next trip, I'll make all of them available completely for free down in the second link. And for those of you that want to go deeper and master things like Astra and get more exclusive content, I've already released a separate video for my community.”
Two-tier pitch: a free downloadable kit (field guide, prompts, and the CLI source) as the low-friction offer, with the paid community link presented as the deeper option. Both delivered in the same calm, non-hypey tone as the rest of the video.
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.
A creator walks through the local tool he built that routes to 37 image and video models, then reverse-engineers exactly what a subscription platform like Higgsfield is doing so you can rebuild it yourself.
The same update that let Claude Code and Codex turn a screen recording into a skill quietly taught both of them to watch raw video, no plugin required.
A 36-minute blueprint for moving a personal AI agent stack into a locked-down, compliance-ready AWS environment — built over a month and nearly 10 million tokens.
Grok Bot, Hermes Agent, Claude Cowork, ChatGPT Work, and OpenClaw are all built from the same six parts. The video ranks them twice, then argues the strongest long-term move is skipping all five.
A Claude Code creator mines his own chat history into a personal test pack, then builds a slash-command benchmark that tells him in one run whether a new model release is actually worth switching to.
00:14
00:29
00:44
01:09
01:22
01:34
01:47
02:00
02:25
02:38
02:51
03:03
03:16
03:29
03:57
04:07
04:19
04:32
04:57
05:16
05:23
05:35
05:48
06:01
06:13
06:26
06:39
07:04
07:17
07:29
07:55
08:07
08:15
08:33
08:46
08:58
09:11
09:23
09:36
09:49
10:02
10:40
10:52
11:05
11:18
11:30
11:43
12:01
12:08
12:21
12:36
12:46
13:12
13:37
13:50
13:56
14:15
14:28
14:40
14:53
15:06
15:18
15:44
15:56
16:04
16:37
16:41
Video of the Day13:01
13:12
36:27
18:18
Video of the Day08:38
08:16