Loading video...

Video Failed to Load

Go Home

AI coding agents have access to your API keys, your codebase, your production environment. One prompt injection and they work for someone else. Gate AI sits inline on every request and stops it. Launching June 2026.

Conste11ation's profile picture

Constellation²

86,638 subscribers

12,136,428 views • 1 month ago •via X (Twitter)

News & PoliticsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Nexus The easiest way to payment gate any existing API Enable AI agents to use your service without needing accounts or API keys. Register your API for free and get paid for every request. No code change required. Powered by x402 and thirdweb infra
2:59

Introducing Nexus The easiest way to payment gate any existing API Enable AI agents to use your service without needing accounts or API keys. Register your API for free and get paid for every request. No code change required. Powered by x402 and thirdweb infra

Joaquim

16,816 views • 9 months ago

Holy shit... someone just solved the biggest problem in AI coding. Every time you start a new session, your AI forgets everything. XHawk captures every coding session, commit, and decision into a living knowledge base your agents actually remember. No more re-explaining your codebase. Ever. Here's how it works:
0:26

Holy shit... someone just solved the biggest problem in AI coding. Every time you start a new session, your AI forgets everything. XHawk captures every coding session, commit, and decision into a living knowledge base your agents actually remember. No more re-explaining your codebase. Ever. Here's how it works:

Nav Toor

24,406 views • 3 months ago

Agents on OpenClaw🦞 can run commands and act autonomously, one bad prompt and they could leak your production API keys. That’s why we built the control layer: introducing - the Endpoint Detection & Response platform built specifically for AI Agent Security. <20 seconds setup. Logs every action. Enforces policy before execution. Installation instructions below.
0:35

Agents on OpenClaw🦞 can run commands and act autonomously, one bad prompt and they could leak your production API keys. That’s why we built the control layer: introducing - the Endpoint Detection & Response platform built specifically for AI Agent Security. <20 seconds setup. Logs every action. Enforces policy before execution. Installation instructions below.

Cantina 🪐

13,378 views • 4 months ago

Inspector (@tryinspector) is an AI IDE for front-end that connects browser and codebase. It lets you select elements visually and prompt changes, giving coding agents access to the same runtime context developers have: visuals, elements, and logs.
0:58

Inspector (@tryinspector) is an AI IDE for front-end that connects browser and codebase. It lets you select elements visually and prompt changes, giving coding agents access to the same runtime context developers have: visuals, elements, and logs.

Y Combinator

115,675 views • 8 months ago

APIs weren’t built for AI agents. Orthogonal (YC W26) fixes that. Agents and developers get instant access to any API on our marketplace via a single MCP or SDK. Orthogonal handles your API keys and payments, so your agent doesn’t have to. Pay as you go. Congrats on the launch Christian Pickett, Bera Sogut
1:11

APIs weren’t built for AI agents. Orthogonal (YC W26) fixes that. Agents and developers get instant access to any API on our marketplace via a single MCP or SDK. Orthogonal handles your API keys and payments, so your agent doesn’t have to. Pay as you go. Congrats on the launch Christian Pickett, Bera Sogut

Y Combinator

38,047 views • 5 months ago

Figment is getting better every day Let your own AI trade for you now Access limitless AI signals and knowledge Battle your agents Win.
0:44

Figment is getting better every day Let your own AI trade for you now Access limitless AI signals and knowledge Battle your agents Win.

Figment.Trade

21,866 views • 7 months ago

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:
4:01

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

DeepLearning.AI

23,255 views • 1 year ago

Introducing Hacktron Review: an AI security reviewer for your pull requests. It understands your whole codebase, builds a threat model, takes your feedback, and catches exploitable vulnerabilities before they reach production. Try for free:
3:34

Introducing Hacktron Review: an AI security reviewer for your pull requests. It understands your whole codebase, builds a threat model, takes your feedback, and catches exploitable vulnerabilities before they reach production. Try for free:

Hacktron AI

47,995 views • 2 months ago

World's first tool that gives AI coding agents full production context. Until now, AI could write your code, but it had no idea what was actually happening in production. We built Comie to change that. Connect your production stack once, and now Claude Code, Cursor, Codex, or any AI coding agent can: - inspect logs - analyze production databases - debug backend issues - trace production errors - understand real production behavior All directly inside your existing workflow. It takes 60 seconds to setup. We're giving first 50 requests free for every user:
1:07

World's first tool that gives AI coding agents full production context. Until now, AI could write your code, but it had no idea what was actually happening in production. We built Comie to change that. Connect your production stack once, and now Claude Code, Cursor, Codex, or any AI coding agent can: - inspect logs - analyze production databases - debug backend issues - trace production errors - understand real production behavior All directly inside your existing workflow. It takes 60 seconds to setup. We're giving first 50 requests free for every user:

yutish

17,133 views • 2 months ago

It will soon be time to initiate your Wayfinder shell. Fund your wallet for your AI agents. What is your PROMPT?
1:00

It will soon be time to initiate your Wayfinder shell. Fund your wallet for your AI agents. What is your PROMPT?

Wayfinder Foundation 🧭

36,182 views • 1 year ago

AgentMail () is building an API to give your agents their own email inboxes. It’s not AI for your email, it’s email for your AI. Congrats on the launch, , Michael Kim, and Haakam Aujla!
1:05

AgentMail () is building an API to give your agents their own email inboxes. It’s not AI for your email, it’s email for your AI. Congrats on the launch, , Michael Kim, and Haakam Aujla!

Y Combinator

45,352 views • 11 months ago

Introducing an idea-to-GenAI app platform, where AI agents do the hard work Draw your ideas, connect to AI agents and ship to production on day 1 Powered by tldraw, @YouSearchEngine API, Mistral AI 🧵1/10 Today is day 1, let's ship some apps together
0:55

Introducing an idea-to-GenAI app platform, where AI agents do the hard work Draw your ideas, connect to AI agents and ship to production on day 1 Powered by tldraw, @YouSearchEngine API, Mistral AI 🧵1/10 Today is day 1, let's ship some apps together

Shaun.AGI

104,010 views • 2 years ago

Train Once, Earn Limitless. Introducing Moonbase Your All-in-one AI Model Marketplace, only on FLock. Train AI models, create AI agents with standard API, and earn when AI agents use your models. Coming soon. Join the waitlist:
0:42

Train Once, Earn Limitless. Introducing Moonbase Your All-in-one AI Model Marketplace, only on FLock. Train AI models, create AI agents with standard API, and earn when AI agents use your models. Coming soon. Join the waitlist:

FLock.io

277,143 views • 1 year ago

AI coding without systems thinking is just tech debt on speedrun. Delty (@delty_ai) is an AI Staff Engineer for your team. With deep expertise, it designs software systems, evaluates tradeoffs and makes AI coding agents smarter with your engineering context. Congrats on the launch, Lalit Kundu and Catherine!
1:09

AI coding without systems thinking is just tech debt on speedrun. Delty (@delty_ai) is an AI Staff Engineer for your team. With deep expertise, it designs software systems, evaluates tradeoffs and makes AI coding agents smarter with your engineering context. Congrats on the launch, Lalit Kundu and Catherine!

Y Combinator

73,297 views • 1 year ago

"#1 advice for sales and marketing leaders: deploy an AI agent yourself. Don't hire an agency. Don't tell someone on your team to do it. Deploy an AI agent into production, for real, yourself." with Lenny Rachitsky "For junior sales & GTM folks? Embrace it. Be the one that embraces every bit of output from AI Agents."
2:42

"#1 advice for sales and marketing leaders: deploy an AI agent yourself. Don't hire an agency. Don't tell someone on your team to do it. Deploy an AI agent into production, for real, yourself." with Lenny Rachitsky "For junior sales & GTM folks? Embrace it. Be the one that embraces every bit of output from AI Agents."

Jason ✨👾SaaStr.Ai✨ Lemkin

24,997 views • 6 months ago

AI agents can now see your UI like you do. Select any element in your live app, leave a comment, and your AI agent fixes it in your local codebase automatically. This is wild for React devs. 100% Opensource and Local.
0:33

AI agents can now see your UI like you do. Select any element in your live app, leave a comment, and your AI agent fixes it in your local codebase automatically. This is wild for React devs. 100% Opensource and Local.

Unwind AI

12,591 views • 11 months ago

If your contracts don’t fit in a prompt window, your AI has to work at document scale. See how Google’s Gemini 3 Pro + Box AI API extract contract metadata and run multi-file risk analysis with the Box AI Ask API using your own governance docs.
8:40

If your contracts don’t fit in a prompt window, your AI has to work at document scale. See how Google’s Gemini 3 Pro + Box AI API extract contract metadata and run multi-file risk analysis with the Box AI Ask API using your own governance docs.

Box

30,545 views • 8 months ago

Jensen Huang says AI agents can't do 100% of any job, but they will do 50% of the work for 100% of people, and AI won't take your job; AI used by somebody else will take your job
0:47

Jensen Huang says AI agents can't do 100% of any job, but they will do 50% of the work for 100% of people, and AI won't take your job; AI used by somebody else will take your job

Tsarathustra

232,844 views • 1 year ago