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.

Excited to share - purpose driven, context- specific, high precision agents on top of your codebase that can perform engineering tasks like onboarding, debugging, testing, system design and a lot more. 🥧

Aditi Kothari

3,554 subscribers

10,498 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

akshay1 year ago

this is amazing and what a cool video aditi!

Aditi Kothari1 year ago

Thanks Akshay 🙏🏻

Aravind Putrevu1 year ago

Congratulations, Aditi and Dhiren!

Aditi Kothari1 year ago

Thanks Aravind! You’ve been super supportive throughout 🙏🏻

Vikrant Bhat ⚛️ 🚀1 year ago

Congratulations Aditi! 🚀

Aditi Kothari1 year ago

Thanks Vikrant ✨🙏🏻

Yash Kewalramani1 year ago

Congrats @aditikothari_ 🚀🚀

Aditi Kothari1 year ago

Thank you Yash!!

Manan Agarwal1 year ago

Godspeed!

Aditi Kothari1 year ago

Thanks Manan 🙏🏻✨

Related Videos

Windsurf CEO Varun Mohan says code generation is just the appetizer. Real engineering is debugging, testing, system design. As AI agents tap logs, databases, and browser context, “every aspect is going to be 10× more effective.” The real disruption is in engineering cognition.

Windsurf CEO Varun Mohan says code generation is just the appetizer. Real engineering is debugging, testing, system design. As AI agents tap logs, databases, and browser context, “every aspect is going to be 10× more effective.” The real disruption is in engineering cognition.

vitrupo

170,606 views • 1 year ago

Most people are underusing AI agents Right now,they’re mostly stuck on basic tasks, but I’ve started to feel like they can do a lot more than that. Projects like Agent Hansa kind of changed my perspective it’s interesting seeing agents act more like workers, actually handling 👇

Most people are underusing AI agents Right now,they’re mostly stuck on basic tasks, but I’ve started to feel like they can do a lot more than that. Projects like Agent Hansa kind of changed my perspective it’s interesting seeing agents act more like workers, actually handling 👇

Aina Ai | Tools & Updates

15,150 views • 3 months ago

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Resolve AI

313,748 views • 1 month ago

I'm *very* excited to share something we’ve been working on for a while now... It's a set of AI agents tailor-made for founders and built around each founder's specific workflows. Here’s an early look at some of the things the agents can do:

I'm very excited to share something we’ve been working on for a while now... It's a set of AI agents tailor-made for founders and built around each founder's specific workflows. Here’s an early look at some of the things the agents can do:

Ran Aroussi

30,170 views • 1 year ago

Introducing Kombai 2.0 - the first AI design engineer. We keep hearing that AGI is almost here. Still, we’re stuck with coding agents that don’t have taste and design tools that don’t understand our codebase. Both are artifacts of a world where design and engineering were two different jobs, with a handoff in between. That world is changing fast. Today, designers ship code, engineers want to escape handoffs, and everyone wants to build tasteful UX. Kombai is built for this new world. Design and engineering, finally on the same side.

Introducing Kombai 2.0 - the first AI design engineer. We keep hearing that AGI is almost here. Still, we’re stuck with coding agents that don’t have taste and design tools that don’t understand our codebase. Both are artifacts of a world where design and engineering were two different jobs, with a handoff in between. That world is changing fast. Today, designers ship code, engineers want to escape handoffs, and everyone wants to build tasteful UX. Kombai is built for this new world. Design and engineering, finally on the same side.

Dipanjan Dey

438,711 views • 1 month ago

We are excited to share new experiments with AgiBot @AgiBot_zhiyuan on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.

We are excited to share new experiments with AgiBot @AgiBot_zhiyuan on multi-task, multi-embodiment VLAs! With one model that can perform many tasks with both two-finger grippers and multi-fingered hands, we take another step toward one model for all robots and tasks.

Physical Intelligence

75,796 views • 1 year ago

Tools like Windsurf could change education forever Agents like Cascade can be instructed to perform a variety of predetermined tasks, including being your personal computer science tutor The potential use cases are truly mind boggling

Tools like Windsurf could change education forever Agents like Cascade can be instructed to perform a variety of predetermined tasks, including being your personal computer science tutor The potential use cases are truly mind boggling

Windsurf

53,251 views • 1 year ago

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Databricks

47,044 views • 1 year ago

I'm super excited to share that you can now speak to TOSHI and get your work done. Toshi can read your emails, do your work and automate your workflows. Pretty soon, Toshi can do a whole lot more and we expect many more features coming in including a fully live subconscious.

I'm super excited to share that you can now speak to TOSHI and get your work done. Toshi can read your emails, do your work and automate your workflows. Pretty soon, Toshi can do a whole lot more and we expect many more features coming in including a fully live subconscious.

Steven Enamakel

26,478 views • 17 days ago

🚨 UNCANNY VALLEY: AI’S NEXT WAVE WILL BE WRAPPED, PERSONALIZED, AND EVERYWHERE Swupnil Sahai 🎾🧠: “What we’ll start to see is a lot more products that are being built on top of these foundation models. If you have companies that are kind of putting a nice wrapper onto it, putting a nice interface, making it really easy and like super specialized for you, your use case. Then I think that’s where we’ll start to see like a lot of innovation happening and then it just becomes like more accessible and then also more specific to like your specific use case that you’re trying to get out.”

🚨 UNCANNY VALLEY: AI’S NEXT WAVE WILL BE WRAPPED, PERSONALIZED, AND EVERYWHERE Swupnil Sahai 🎾🧠: “What we’ll start to see is a lot more products that are being built on top of these foundation models. If you have companies that are kind of putting a nice wrapper onto it, putting a nice interface, making it really easy and like super specialized for you, your use case. Then I think that’s where we’ll start to see like a lot of innovation happening and then it just becomes like more accessible and then also more specific to like your specific use case that you’re trying to get out.”

Mario Nawfal

91,621 views • 1 year ago

I made an AI data science team with Python. I'm excited to share my new project, the AI Data Science Team, a Python package for creating AI co-pilots and agents to assist in common data science tasks. I walk you through the GitHub page, showcasing the progress and potential of this project. I'll explain how these agents can streamline tasks like code generation and modeling pipeline creation, making data science projects more efficient. Introduction to AI Data Science Team Project Integrating Human-in-the-Loop Example: Accessing Agents for Feature Engineering Setting up Feature Engineering Agent Code On GitHub: Python AI-Tips Newsletter (stay updated as I build this project in the open):

I made an AI data science team with Python. I'm excited to share my new project, the AI Data Science Team, a Python package for creating AI co-pilots and agents to assist in common data science tasks. I walk you through the GitHub page, showcasing the progress and potential of this project. I'll explain how these agents can streamline tasks like code generation and modeling pipeline creation, making data science projects more efficient. Introduction to AI Data Science Team Project Integrating Human-in-the-Loop Example: Accessing Agents for Feature Engineering Setting up Feature Engineering Agent Code On GitHub: Python AI-Tips Newsletter (stay updated as I build this project in the open):

Matt Dancho (Business Science)

11,799 views • 1 year ago

Your agents can now browse and take actions on the web, just like you can. This lets agents work with sites that don’t have APIs and still complete tasks end to end. Plus, each interaction is streamed live to Studio.

Your agents can now browse and take actions on the web, just like you can. This lets agents work with sites that don’t have APIs and still complete tasks end to end. Plus, each interaction is streamed live to Studio.

Mastra

16,848 views • 2 months ago

Elon Musk says Tesla is building an “Optimus Academy” so the robots can perform different tasks in the real world. “We’re going to need to build a lot of robots, and put them into a Optimus Academy, so they can do self-play in reality. We’re actually building that out, we’re going to have at least 10-30K Optimus robots that are testing different tasks.”

Elon Musk says Tesla is building an “Optimus Academy” so the robots can perform different tasks in the real world. “We’re going to need to build a lot of robots, and put them into a Optimus Academy, so they can do self-play in reality. We’re actually building that out, we’re going to have at least 10-30K Optimus robots that are testing different tasks.”

Nic Cruz Patane

20,052 views • 5 months ago

Inviting early beta testers for our upcoming SWE agent, Asteria. We're solving AI code comprehension, where the context window and the size of your codebase are no longer limitations, and reinventing the UX of how coding agents are currently implemented. We initially built this to address false positives and enhance accuracy for our SAST agent, which autonomously identifies security vulnerabilities, traces how a payload would flow through code, and ultimately demonstrates an actual exploit. The performance improved so significantly that we decided to test it on realistic engineering tasks on large codebases and witnessed SOTA results. Reply "access" if you'd like to be an early beta tester, a lot of quirks to fix.

Inviting early beta testers for our upcoming SWE agent, Asteria. We're solving AI code comprehension, where the context window and the size of your codebase are no longer limitations, and reinventing the UX of how coding agents are currently implemented. We initially built this to address false positives and enhance accuracy for our SAST agent, which autonomously identifies security vulnerabilities, traces how a payload would flow through code, and ultimately demonstrates an actual exploit. The performance improved so significantly that we decided to test it on realistic engineering tasks on large codebases and witnessed SOTA results. Reply "access" if you'd like to be an early beta tester, a lot of quirks to fix.

mufeed vh

12,408 views • 1 year ago

Tabracadabra 🎉 is a system that brings tab-to-autocomplete literally *anywhere* there’s a textbox. Instead of relying on a single codebase for context, Tabracadabra uses a General User Model to autocomplete with everything you see or do on your computer.

Tabracadabra 🎉 is a system that brings tab-to-autocomplete literally anywhere there’s a textbox. Instead of relying on a single codebase for context, Tabracadabra uses a General User Model to autocomplete with everything you see or do on your computer.

Omar Shaikh

87,437 views • 10 months ago

This is Repo Prompt 2.0 A fully integrated agent, that makes it seamless to use RP's powerful MCP tools, with a built-in oracle and context builder. A first class experience showcasing how much better and efficient your agents can be with good context engineering tools.

This is Repo Prompt 2.0 A fully integrated agent, that makes it seamless to use RP's powerful MCP tools, with a built-in oracle and context builder. A first class experience showcasing how much better and efficient your agents can be with good context engineering tools.

eric provencher

38,921 views • 4 months ago

📁 Emad Mostaque, founder of Stability AI, says we’re entering “AI Atlantis,” a world where anyone can access trillions of AI agents that perform complex tasks for almost nothing, even creating other agents. In this future, it won’t matter how many people are on your team, but how many agents you can orchestrate.

📁 Emad Mostaque, founder of Stability AI, says we’re entering “AI Atlantis,” a world where anyone can access trillions of AI agents that perform complex tasks for almost nothing, even creating other agents. In this future, it won’t matter how many people are on your team, but how many agents you can orchestrate.

Jon Hernandez

29,575 views • 11 months ago

I’m super excited to share our work on AdA: An Adaptive Agent capable of hypothesis-driven exploration which solves challenging unseen tasks with just a handful of experience, at a similar timescale to humans. See the thread for more details 👇 [1/N]

I’m super excited to share our work on AdA: An Adaptive Agent capable of hypothesis-driven exploration which solves challenging unseen tasks with just a handful of experience, at a similar timescale to humans. See the thread for more details 👇 [1/N]

Feryal

418,273 views • 3 years ago

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

Swami Sivasubramanian

26,035 views • 7 months ago

Julianna Peña says UFC's current drug testing program is "not that great" and thinks Kayla Harrison can cheat for #UFC316. "I don't like the way that the testing system is now. I think that it is a lot more lax than ever before." (via Mike Bohn)

Julianna Peña says UFC's current drug testing program is "not that great" and thinks Kayla Harrison can cheat for #UFC316. "I don't like the way that the testing system is now. I think that it is a lot more lax than ever before." (via Mike Bohn)

MMA Junkie

69,855 views • 1 year ago