Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

after using replit's coding agent i think...its over for a lot of traditional saas wanted slack notifications when customers subscribed/cancelled Zapier was 30/mo JUST to add a price filter instead replit's agent built & deployed one in < 5 mins, with tests. 1/10 of the cost

Sully

58,019 subscribers

364,667 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

The Canaanite2 years ago

Kinda wild huh, most people have no idea about the tsunami of change that's forming on the horizon lol

Sully2 years ago

fr lol

Millin Gabani2 years ago

Yep, software or SaaS is race to the bottom. There is going to lots of new software that will be built. I doubt we will ever get to 8B people building their own software, but in a decade 20-30M people will be building it. Relevant comment from another discussion.

Sully2 years ago

similiar to youtube probably

Ken Greeff2 years ago

I think you forget that most businesses don’t want to go and build their own things. They just want to grab something off the shelf and move on with their core product

Sully2 years ago

what if he thing costs you 1k/mo? b2b saas is insanely expensive

Max the VC 👨‍🚀2 years ago

Ironically, had this exact thought last week ahaha

Sully2 years ago

gg saas lol

Al Cattell2 years ago

It’s over for no code

Sully2 years ago

actually yeah lmfao goodnight nocode lol

Related Videos

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

rvivek

11,870 views • 3 months ago

I used Factory CLI to build a tiny TUI tool that: - monitors web page changes - sends Telegram notifications - runs privately on a $5/mo VPS - uses Droid headless agent to summarise content All in <2hrs. Watch this 11m demo of the app and how I deployed it to my server ↓

I used Factory CLI to build a tiny TUI tool that: - monitors web page changes - sends Telegram notifications - runs privately on a $5/mo VPS - uses Droid headless agent to summarise content All in <2hrs. Watch this 11m demo of the app and how I deployed it to my server ↓

Ian Nuttall

32,008 views • 11 months ago

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 views • 1 year ago

Over the last month, I burned over $200k in tokens with gpt-5.6-sol. I built a lot. Instead of just reacting to the benchmarks, news, tweets, etc, I went a different route. This video is an overview of all the cool shit I built using the new model. Proper review coming soon™

Over the last month, I burned over $200k in tokens with gpt-5.6-sol. I built a lot. Instead of just reacting to the benchmarks, news, tweets, etc, I went a different route. This video is an overview of all the cool shit I built using the new model. Proper review coming soon™

Theo - t3.gg

253,267 views • 2 months ago

I asked Fable to create a Mars city in Three.js, after 6hrs and dozens of subagents in one shot, this is the result (100% procedural), using my Three.js Awesome Graphics Agent Skills Still a lot of details i need to polish but this was beyond my expectation🤯

I asked Fable to create a Mars city in Three.js, after 6hrs and dozens of subagents in one shot, this is the result (100% procedural), using my Three.js Awesome Graphics Agent Skills Still a lot of details i need to polish but this was beyond my expectation🤯

Scott

43,241 views • 1 month ago

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Harjot Gill

4,777,289 views • 4 months ago

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,973 views • 1 year ago

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Anthropic Managed Agents team: "Fable 5 is our best model for running self-improving agent systems. Add /loops, dynamic workflows, dreaming and you are unstoppable" in this video he breaks down exactly how most people are using Claude: - the 34% you lose to CLAUDE.md before typing a word - one agent researching. one building. one reviewing. one orchestrating - the architecture that separates hobbyists from real builders - the 3 properties every agent team needs to actually survive if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady

21,533 views • 3 months ago

I shot this video last week to onboard a new set of alpha customers to Notion Custom Agents. Figured I should just put it out here so you can follow along the latest and greatest. It's so cool to see all the things people are building with it. You can see some of my own use cases here: (0:00) Intro to custom agents Starting with personal use cases (1:00) Building a mail triage agent (5:00) Creating a prep doc for all my daily meetings (6:45) Generating a daily report that helps me catch up with multiple slack channels Switching to company use cases (8:30) Agent that automatically answers questions in a slack channel and files tasks when necessary (10:30) Agent that auto-routes product feedback to the right team channel and task db. And it does this with routing rules, that it wrote itself. (12:40) Build your own agent. Let your imaginations run wild! Send us feedback! The product is rolling out quickly, and everyone should have access in the next couple weeks.

I shot this video last week to onboard a new set of alpha customers to Notion Custom Agents. Figured I should just put it out here so you can follow along the latest and greatest. It's so cool to see all the things people are building with it. You can see some of my own use cases here: (0:00) Intro to custom agents Starting with personal use cases (1:00) Building a mail triage agent (5:00) Creating a prep doc for all my daily meetings (6:45) Generating a daily report that helps me catch up with multiple slack channels Switching to company use cases (8:30) Agent that automatically answers questions in a slack channel and files tasks when necessary (10:30) Agent that auto-routes product feedback to the right team channel and task db. And it does this with routing rules, that it wrote itself. (12:40) Build your own agent. Let your imaginations run wild! Send us feedback! The product is rolling out quickly, and everyone should have access in the next couple weeks.

Akshay Kothari

74,831 views • 7 months ago

JUST IN: Iran has published footage showing the destruction of a US MQ-1 Predator drone over southern Iran yesterday, using one of its modern air defense systems. MQ-1 is estimated to cost between $4 million and $5 million per unit.

JUST IN: Iran has published footage showing the destruction of a US MQ-1 Predator drone over southern Iran yesterday, using one of its modern air defense systems. MQ-1 is estimated to cost between $4 million and $5 million per unit.

Current Report

15,489 views • 3 months ago

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

29,013 views • 2 years ago

Most scripts never get made. And it's rarely about the writing. It's about risk. About economics. About no one in the room willing to take the bet. One of our directors stopped waiting. He built a 10-min episode of his in a week using InVideo Agent One. We're taking it to full production. The line just moved. The stories that didn't make it through the room now have a way through. Just spend 10 mins watching it. An Invideo original - Penumbra - EP - 1

Most scripts never get made. And it's rarely about the writing. It's about risk. About economics. About no one in the room willing to take the bet. One of our directors stopped waiting. He built a 10-min episode of his in a week using InVideo Agent One. We're taking it to full production. The line just moved. The stories that didn't make it through the room now have a way through. Just spend 10 mins watching it. An Invideo original - Penumbra - EP - 1

Invideo

15,030 views • 3 months ago

SpaceXAI engineer, Lauren Tan: "99% of people using GrokBot just for 1% of its real power. They run 1 agent without "loop" & "graph" I'm running a team of 20+ GrokBot agents, fully autonomous. I have a Chief of Staff agent, a PM agent and 20+ workers - that's the new stack of engineer" In a 1-hour session, a SpaceXAI engineer showed how to build a team of effective AI agents from scratch this is worth more than a $500 agentic engineering course watch this workshop today, then read how to build a fleet of GrokBot agents in the article below

SpaceXAI engineer, Lauren Tan: "99% of people using GrokBot just for 1% of its real power. They run 1 agent without "loop" & "graph" I'm running a team of 20+ GrokBot agents, fully autonomous. I have a Chief of Staff agent, a PM agent and 20+ workers - that's the new stack of engineer" In a 1-hour session, a SpaceXAI engineer showed how to build a team of effective AI agents from scratch this is worth more than a $500 agentic engineering course watch this workshop today, then read how to build a fleet of GrokBot agents in the article below

0xRafy

47,726 views • 13 days ago

After testing Kimi.ai K2 for a few hours, My overall take: - Performance between Claude 3.5 & Claude 4 (Just my vibe eval!) - The UI generation seems great - But the cost is only 20% of Claude 3.5 - So good enough for most coding agent with a lot more manageable cost Easiest way to use Kimi K2 in Claude Code: - export ANTHROPIC_AUTH_TOKEN=YOUR_MOONSHOT_API - export ANTHROPIC_BASE_URL= - claude ------ Here are my tests & how to integrate to Claude Code: 1. Whole UI component library 2. Make online IDE UI 3. Build Functional mario game ...

After testing Kimi.ai K2 for a few hours, My overall take: - Performance between Claude 3.5 & Claude 4 (Just my vibe eval!) - The UI generation seems great - But the cost is only 20% of Claude 3.5 - So good enough for most coding agent with a lot more manageable cost Easiest way to use Kimi K2 in Claude Code: - export ANTHROPIC_AUTH_TOKEN=YOUR_MOONSHOT_API - export ANTHROPIC_BASE_URL= - claude ------ Here are my tests & how to integrate to Claude Code: 1. Whole UI component library 2. Make online IDE UI 3. Build Functional mario game ...

Jason Zhou

80,871 views • 1 year ago

SpaceXAI engineer, Lauren Tan: "99% of people using GrokBot just for 1% of its real power. They run 1 agent without "loop" & "graph" I'm running a team of 20+ GrokBot agents, fully autonomous. I have a Chief of Staff agent, a PM agent and 20+ workers - that's the new stack of engineer" In a 1-hour session, a SpaceXAI engineer showed how to build a team of effective AI agents from scratch this is worth more than a $500 agentic engineering course watch this workshop today, then read how to build a fleet of GrokBot agents in the article below

SpaceXAI engineer, Lauren Tan: "99% of people using GrokBot just for 1% of its real power. They run 1 agent without "loop" & "graph" I'm running a team of 20+ GrokBot agents, fully autonomous. I have a Chief of Staff agent, a PM agent and 20+ workers - that's the new stack of engineer" In a 1-hour session, a SpaceXAI engineer showed how to build a team of effective AI agents from scratch this is worth more than a $500 agentic engineering course watch this workshop today, then read how to build a fleet of GrokBot agents in the article below

Codez

624,869 views • 15 days ago

This was a top 3 moment in my life. After losing Ben, I’ve wanted to continue to honor him in my music & at my shows. I put together a couple of moments at the end of the set with a lot of feeling & this was one of the highlights. LLBB

This was a top 3 moment in my life. After losing Ben, I’ve wanted to continue to honor him in my music & at my shows. I put together a couple of moments at the end of the set with a lot of feeling & this was one of the highlights. LLBB

Robert Oliver

17,134 views • 10 months ago

What happens when you give a frontier agent access to a full company's history of docs, messages, tasks and more? As I'm onboarding to ClickUp, this feels like an absolute cheat code. "Cursor for your entire job." Full history of the company's thinking, decision making and operations are natively accessible w/ first-party tools and data access. No exaggeration this has reduced the amount of overhead to get ramped up (# of messages sent) by >60%. At Codegen we built an agent that straddles multiple applications - Slack, Linear, Notion, etc. - with many obvious limitations. Agents cannot search Slack historical conversations, for example, nor can you index Slack data. Any question concerning a historical decision is just out of reach. There are clear constraints of fragmentation preventing otherwise extremely capable models from performing productive tasks. Seems the biggest bottleneck to agent productivity in early 2026 is not capabilities or knowledge, it's the politics and incentives around SAAS fragmentation. Very bullish for all-in-one horizontal SAAS and what that unlocks

What happens when you give a frontier agent access to a full company's history of docs, messages, tasks and more? As I'm onboarding to ClickUp, this feels like an absolute cheat code. "Cursor for your entire job." Full history of the company's thinking, decision making and operations are natively accessible w/ first-party tools and data access. No exaggeration this has reduced the amount of overhead to get ramped up (# of messages sent) by >60%. At Codegen we built an agent that straddles multiple applications - Slack, Linear, Notion, etc. - with many obvious limitations. Agents cannot search Slack historical conversations, for example, nor can you index Slack data. Any question concerning a historical decision is just out of reach. There are clear constraints of fragmentation preventing otherwise extremely capable models from performing productive tasks. Seems the biggest bottleneck to agent productivity in early 2026 is not capabilities or knowledge, it's the politics and incentives around SAAS fragmentation. Very bullish for all-in-one horizontal SAAS and what that unlocks

Jay Hack

17,226 views • 7 months ago

I just created a 30-second Louis Vuitton fashion campaign by sharing just one thought with my Pika Agent ✨ Told my Pika agent: "using me as the character, create a 30s video in Louis Vuitton, fashion campaign vibe, absolutely cinematic and cool, ends with a black screen. have some pixelated elements, keep the facial identity of the character throughout the video" That's it. One message and my Pika Agent handled the rest- casting, directing, editing, sound! This is what it means when I say creation just got insane. Pika Agent is the most personal creative tool I've ever used.

I just created a 30-second Louis Vuitton fashion campaign by sharing just one thought with my Pika Agent ✨ Told my Pika agent: "using me as the character, create a 30s video in Louis Vuitton, fashion campaign vibe, absolutely cinematic and cool, ends with a black screen. have some pixelated elements, keep the facial identity of the character throughout the video" That's it. One message and my Pika Agent handled the rest- casting, directing, editing, sound! This is what it means when I say creation just got insane. Pika Agent is the most personal creative tool I've ever used.

Oluwatimileyin✨🦋

431,001 views • 4 months ago