Загрузка видео...

Не удалось загрузить видео

На главную

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. 🥧

aditikothari_'s profile picture

Aditi Kothari

3,554 subscribers

10,498 просмотров • 2 лет назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля akshay
akshay2 лет назад

this is amazing and what a cool video aditi!

Фото профиля Aditi Kothari
Aditi Kothari2 лет назад

Thanks Akshay 🙏🏻

Фото профиля Aravind Putrevu
Aravind Putrevu2 лет назад

Congratulations, Aditi and Dhiren!

Фото профиля Aditi Kothari
Aditi Kothari2 лет назад

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

Фото профиля Vikrant Bhat ⚛️ 🚀
Vikrant Bhat ⚛️ 🚀2 лет назад

Congratulations Aditi! 🚀

Фото профиля Aditi Kothari
Aditi Kothari2 лет назад

Thanks Vikrant ✨🙏🏻

Фото профиля Yash Kewalramani
Yash Kewalramani2 лет назад

Congrats @aditikothari_ 🚀🚀

Фото профиля Aditi Kothari
Aditi Kothari2 лет назад

Thank you Yash!!

Фото профиля Manan Agarwal
Manan Agarwal2 лет назад

Godspeed!

Фото профиля Aditi Kothari
Aditi Kothari2 лет назад

Thanks Manan 🙏🏻✨

Похожие видео

Introducing Design System Agents. Turn your repos, npm packages and docs into an agent that builds prototypes engineering can actually ship. The Prototype is t̶h̶r̶o̶w̶n̶ ̶a̶w̶a̶y̶ the Product.
0:54

Introducing Design System Agents. Turn your repos, npm packages and docs into an agent that builds prototypes engineering can actually ship. The Prototype is t̶h̶r̶o̶w̶n̶ ̶a̶w̶a̶y̶ the Product.

bolt.new

118,963 просмотров • 7 месяцев назад

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 👇
0:59

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

15,331 просмотров • 6 месяцев назад

And don’t forget about Notion workers! They’re like serverless functions you deploy to notion. Instead of only pushing info to notion from your agents, run notion workers on a schedule to fetch/organize info that your agents can use. Much more efficient for many tasks:
2:41

And don’t forget about Notion workers! They’re like serverless functions you deploy to notion. Instead of only pushing info to notion from your agents, run notion workers on a schedule to fetch/organize info that your agents can use. Much more efficient for many tasks:

Vinny

13,041 просмотров • 2 месяцев назад

I use subagents for ~80% of my Codex tasks these days. If you're new to subagents, here's a quick primer: - Subagents = separate agents that work on a specific piece of work in a fresh isolated context window. - Your main thread can create subagents and delegate work to them. - Subagents report back when tasks are complete. - Codex subagents are especially useful for read-heavy tasks (e.g research, investigation, and review). - Also useful for testing and building parts of a project in parallel. Subagents are great for working on focused parts of a big task, like planning, implementation, testing, or review. My biggest pro tip for using subagents in Codex: You don’t have to design the entire delegation plan yourself. Just ask Codex to “Use subagents as needed,” and then Codex can then decide where subagents would help it in the task. Here's a demo of using subagents in Codex:
0:42

I use subagents for ~80% of my Codex tasks these days. If you're new to subagents, here's a quick primer: - Subagents = separate agents that work on a specific piece of work in a fresh isolated context window. - Your main thread can create subagents and delegate work to them. - Subagents report back when tasks are complete. - Codex subagents are especially useful for read-heavy tasks (e.g research, investigation, and review). - Also useful for testing and building parts of a project in parallel. Subagents are great for working on focused parts of a big task, like planning, implementation, testing, or review. My biggest pro tip for using subagents in Codex: You don’t have to design the entire delegation plan yourself. Just ask Codex to “Use subagents as needed,” and then Codex can then decide where subagents would help it in the task. Here's a demo of using subagents in Codex:

Avthar

18,444 просмотров • 2 месяцев назад

This is how a Head of Design uses Figma to do design onboarding for new product managers, engineers Design onboarding is a brilliant process to coach product, engineering on how to work best with designers and reduce friction Adam Storr shows he uses Figma to do design onboarding for new PMs, engineers at Hex
3:30

This is how a Head of Design uses Figma to do design onboarding for new product managers, engineers Design onboarding is a brilliant process to coach product, engineering on how to work best with designers and reduce friction Adam Storr shows he uses Figma to do design onboarding for new PMs, engineers at Hex

Jayneil Dalal

32,664 просмотров • 1 год назад

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.
56:30

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.

Movez

14,923 просмотров • 3 месяцев назад

Vibe-coded prototypes get thrown away because they don’t use your design system code. Bolt’s Design System Agents fix this: - Upload your npm package, Storybook, repo, etc - Bolt builds using your design system - Engineering wires up the backend and ships
3:10

Vibe-coded prototypes get thrown away because they don’t use your design system code. Bolt’s Design System Agents fix this: - Upload your npm package, Storybook, repo, etc - Bolt builds using your design system - Engineering wires up the backend and ships

bolt.new

14,390 просмотров • 7 месяцев назад

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:
2:52

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 просмотров • 1 год назад

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.
1:11

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

313,949 просмотров • 5 месяцев назад

AI agents are starting to feel less like tools you open and more like a team you actually manage. Skydive turns that idea into a whole 3D world where you can move into your office, see your AI coworkers, check what they’re working on, and put them on real tasks. this is a much more interesting way to imagine what working with a team of agents could look like.
0:24

AI agents are starting to feel less like tools you open and more like a team you actually manage. Skydive turns that idea into a whole 3D world where you can move into your office, see your AI coworkers, check what they’re working on, and put them on real tasks. this is a much more interesting way to imagine what working with a team of agents could look like.

Dhaval Makwana

30,281 просмотров • 5 дней назад

94% OF ENGINEERING ORGS USE AI. ONLY 6% SCALE IT The missing link is context and governance. That’s exactly what Atlassian is going after with its new agentic engineering stack: Code Context + governed agent loops in Atlassian Jira + DX measurement. The idea is simple: make agents a native part of your engineering system instead of a side quest in a terminal. > Code Context grounds them in your architecture > Governed loops take work from backlog to pull request > DX measures the impact And the data backs up the context thesis: DX found context-rich AI teams shipped ~64% more per developer 👊 A pretty strong signal that context is becoming one of the biggest leverage points in agentic engineering.
1:00

94% OF ENGINEERING ORGS USE AI. ONLY 6% SCALE IT The missing link is context and governance. That’s exactly what Atlassian is going after with its new agentic engineering stack: Code Context + governed agent loops in Atlassian Jira + DX measurement. The idea is simple: make agents a native part of your engineering system instead of a side quest in a terminal. > Code Context grounds them in your architecture > Governed loops take work from backlog to pull request > DX measures the impact And the data backs up the context thesis: DX found context-rich AI teams shipped ~64% more per developer 👊 A pretty strong signal that context is becoming one of the biggest leverage points in agentic engineering.

Charly Wargnier ♨️

29,622 просмотров • 1 месяц назад

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.
1:24

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

443,277 просмотров • 5 месяцев назад

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.
3:15

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

77,160 просмотров • 1 год назад

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.
2:02

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 🐥

28,836 просмотров • 4 месяцев назад

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
4:21

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 просмотров • 1 год назад

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.
0:24

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 просмотров • 1 год назад

🚨 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.”
0:44

🚨 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

91,654 просмотров • 1 год назад