Loading video...

Video Failed to Load

Go Home

Perplexity Computer in 60 seconds: 1. It's a cloud-based AI employee that runs tasks in the background. 2. 19 models working together. Claude for reasoning, GPT-5.2 for research, Grok for speed tasks. You don't pick. It routes automatically. 3. 400+ connectors. Gmail, Slack, Notion, Salesforce, HubSpot. One click to...

coreyganim's profile picture

Corey Ganim

45,329 subscribers

106,105 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs
0:18

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Daniel San

91,123 views • 4 months ago

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.
0:18

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.

Workshop AI

883,582 views • 2 months ago

Claude builds Google/Meta ads dashboards in 30 seconds Looker and every marketing SaaS is obsolete connect Claude to your ad accounts in 1 click via Ryze AI and it will: → pull any data you ask for → make changes in your account → schedule recurring tasks → generate ad creatives (not perfect yet, actively improving) still early but it works
0:11

Claude builds Google/Meta ads dashboards in 30 seconds Looker and every marketing SaaS is obsolete connect Claude to your ad accounts in 1 click via Ryze AI and it will: → pull any data you ask for → make changes in your account → schedule recurring tasks → generate ad creatives (not perfect yet, actively improving) still early but it works

Ira Bodnar

519,385 views • 2 months ago

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!
0:10

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!

Lydia Hallie ✨

32,459 views • 4 months ago

Stop endless app switching. You can now ask Gemini to complete complex tasks for you across two apps - with one prompt. Look up a location on Maps AND text it to a friend. Ask a question about a video AND save it to notes. What two-in-one tasks will you be asking Gemini?
0:15

Stop endless app switching. You can now ask Gemini to complete complex tasks for you across two apps - with one prompt. Look up a location on Maps AND text it to a friend. Ask a question about a video AND save it to notes. What two-in-one tasks will you be asking Gemini?

Android

183,847 views • 1 year ago

most people open Claude every morning and re-explain their entire life. every. single. time. then I built 7 layers that remember everything: Layer 1: tell Claude who I am, once Layer 2: build separate brains for separate work Layer 3: turn on memory so it learns me Layer 4: upload 5 writing samples so it sounds like me Layer 5: dump my world into project files Layer 6: connect Gmail, Calendar, Drive, Slack Layer 7: schedule tasks that run while I sleep 60 minutes to set up. spread across one week. now Claude finishes my sentences. knows which client I mean from one word. catches mistakes I'd miss. it's not a chatbot anymore. it's a personal AI that knows me better than most coworkers do. your AI doesn't know you yet. this article fixes that.
0:11

most people open Claude every morning and re-explain their entire life. every. single. time. then I built 7 layers that remember everything: Layer 1: tell Claude who I am, once Layer 2: build separate brains for separate work Layer 3: turn on memory so it learns me Layer 4: upload 5 writing samples so it sounds like me Layer 5: dump my world into project files Layer 6: connect Gmail, Calendar, Drive, Slack Layer 7: schedule tasks that run while I sleep 60 minutes to set up. spread across one week. now Claude finishes my sentences. knows which client I mean from one word. catches mistakes I'd miss. it's not a chatbot anymore. it's a personal AI that knows me better than most coworkers do. your AI doesn't know you yet. this article fixes that.

Nav Toor

62,350 views • 1 month ago

Introducing Novo Launching today a new project I coded for myself in 1 weekend in May and decided to finish this week. Novo is a dead simple to-do app that lets you "Speech-To-Tasks", or paste a huge text and organize for you. You can customize the AI and make it organize in any criteria: - Auto-tag by category - Schedule some types of tasks to certain days - Prioritize based on your own rules Try it:
0:13

Introducing Novo Launching today a new project I coded for myself in 1 weekend in May and decided to finish this week. Novo is a dead simple to-do app that lets you "Speech-To-Tasks", or paste a huge text and organize for you. You can customize the AI and make it organize in any criteria: - Auto-tag by category - Schedule some types of tasks to certain days - Prioritize based on your own rules Try it:

Pedro

76,232 views • 11 months ago

💥EARN #UBX TODAY! EVERY DAY!💥 ⭐️1) Register on the platform: ⭐️2) Apply on the task called ""CF Telegram Bounty"" and complete the tasks in it. 🤑 Don't forget to add your Telegram username in the task comments. 😉🤑 Developed by UBIX.Network
0:15

💥EARN #UBX TODAY! EVERY DAY!💥 ⭐️1) Register on the platform: ⭐️2) Apply on the task called ""CF Telegram Bounty"" and complete the tasks in it. 🤑 Don't forget to add your Telegram username in the task comments. 😉🤑 Developed by UBIX.Network

Airdrop Presents 🗽

12,663 views • 3 years ago

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.
0:15

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

Peter Gostev (SF: 22-26 June)

105,619 views • 2 months ago

Bubble Pilot is the first AI that helps users use AI. You don’t wait for AI to finish thinking. You just keep talking. Drop a task. Pilot dispatches it to the right SOP in seconds. Add another. Change your mind. Ask something else. Tasks run in the background. The conversation never stalls. Learning AI is a depreciating asset. Letting AI learn AI is an appreciating one.
0:17

Bubble Pilot is the first AI that helps users use AI. You don’t wait for AI to finish thinking. You just keep talking. Drop a task. Pilot dispatches it to the right SOP in seconds. Add another. Change your mind. Ask something else. Tasks run in the background. The conversation never stalls. Learning AI is a depreciating asset. Letting AI learn AI is an appreciating one.

DAPPOS

21,985 views • 1 month ago

You want to undress for free🔥 Don't have time to use a promo code? There's a “Tasks” section on for that. Complete simple tasks and get credits🤍🧡 #undressgirl #ainsfw #undressbot
0:16

Sensitive content

You want to undress for free🔥 Don't have time to use a promo code? There's a “Tasks” section on for that. Complete simple tasks and get credits🤍🧡 #undressgirl #ainsfw #undressbot

Undress App

36,661 views • 1 year ago

Introducing Mission Task: The easiest way to earn 1Launch Point! Mission Task is coming soon to 1Launch, and it's about to become your secret weapon for stacking those precious points! What is Mission Task? It's your one-stop shop for earning 1Launch Points through simple social media tasks. Say goodbye to complex hoops and hello to effortless point accumulation! Coming very soon, Mission Tasks will be your one-stop shop for skyrocketing your 1Launch Point balance through engaging social media tasks. In the meantime, drop a comment below! What social media tasks would you love to see in Mission Task? #1Launch #earnings #Airdrop #ComingSoon
0:14

Introducing Mission Task: The easiest way to earn 1Launch Point! Mission Task is coming soon to 1Launch, and it's about to become your secret weapon for stacking those precious points! What is Mission Task? It's your one-stop shop for earning 1Launch Points through simple social media tasks. Say goodbye to complex hoops and hello to effortless point accumulation! Coming very soon, Mission Tasks will be your one-stop shop for skyrocketing your 1Launch Point balance through engaging social media tasks. In the meantime, drop a comment below! What social media tasks would you love to see in Mission Task? #1Launch #earnings #Airdrop #ComingSoon

0xTotally

15,719 views • 2 years ago

Big news, friends! I hereby introduce It's a multi-agent chat app with special features for collaborative ranking and estimation tasks, to help you quickly fact-check AI responses against each other. It has GPT-5, Claude Opus 4.1, Gemini 2.5 Pro, and Grok 4, and built-in systems for comparing and aggregating their responses. If you try it, post feature requests for me and the team theMultiplicity.ai!
0:13

Big news, friends! I hereby introduce It's a multi-agent chat app with special features for collaborative ranking and estimation tasks, to help you quickly fact-check AI responses against each other. It has GPT-5, Claude Opus 4.1, Gemini 2.5 Pro, and Grok 4, and built-in systems for comparing and aggregating their responses. If you try it, post feature requests for me and the team theMultiplicity.ai!

Andrew Critch (🤖🩺🚀)

20,112 views • 8 months ago

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.
0:15

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

54,017 views • 10 months ago

Turns out the "IDE but for notes and tasks" is also becoming my... IDE! More and more I just make notes and boards with specs of what needs to be built, connect a bunch of code agents to thymer all working in parallel, have them pick up open tasks, build it and update progress back in the notes.
0:10

Turns out the "IDE but for notes and tasks" is also becoming my... IDE! More and more I just make notes and boards with specs of what needs to be built, connect a bunch of code agents to thymer all working in parallel, have them pick up open tasks, build it and update progress back in the notes.

Wim Cools

28,299 views • 4 months ago

The biggest lie in agentic development: "Run 4 agents on 4 projects at once." I built this animation to show why that fails. Focus on 1 project → 4/4 tasks done Context switch between 4 → 0/4 tasks done Same time. Different results.
0:16

The biggest lie in agentic development: "Run 4 agents on 4 projects at once." I built this animation to show why that fails. Focus on 1 project → 4/4 tasks done Context switch between 4 → 0/4 tasks done Same time. Different results.

Antoine v.d. SwiftLee 

159,797 views • 3 months ago

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.
0:12

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

531,610 views • 4 months ago

Product update: You can now select which agent to run your scheduled tasks for better credit management! Settings > scheduled tasks > advanced settings Try it now!
0:12

Product update: You can now select which agent to run your scheduled tasks for better credit management! Settings > scheduled tasks > advanced settings Try it now!

Manus

60,902 views • 5 months ago

Manage multiple agents at once in the Agent Dashboard. See what each is doing, reply to the ones that need you, and dispatch new tasks. Try /dashboard in Grok Build.
0:14

Manage multiple agents at once in the Agent Dashboard. See what each is doing, reply to the ones that need you, and dispatch new tasks. Try /dashboard in Grok Build.

Grok

648,577 views • 20 days ago

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money
0:11

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

Kirill

392,673 views • 4 days ago