Blink is the first vibe coding platform that builds AI agents. Describe what you want — Blink creates an agent that thinks, uses tools, and completes tasks end-to-end. Built-in web search, code execution, vector database, sandbox, and 180+ AI models. We used it to recreate Cursor, Perplexity, and Shortcut in minutes. Now it's your turn.
When we launched Blink, something interesting happened. People weren't just building landing pages and dashboards — they kept trying to build AI agents. Research assistants. Coding copilots. Support bots that actually do things.
But building agents meant stitching together APIs, managing context windows, handling tool calls, deploying infrastructure. Real engineering work.
So we asked ourselves: what if you could just describe an agent and have it work?
That's what we're launching today.
Blink Agent Builder lets you create agentic AI apps from a prompt. We tested it by rebuilding Cursor, Perplexity, and Shortcut — fully working, no code.
Everything's included: web search, code execution, vector database, sandbox, image and video generation, 180+ models, webhook tools for any API. Plus human-in-the-loop, multi-agent, and context engineering so your agent stays sharp.
Would love to hear what you think — and what agents you'd want to build. I'll be here all day.
This is honestly one of the coolest launches I’ve seen here in a while. The idea of just describing an agent and having it work is wild.
@kf_builds Hi Kai, we spoke on LinkedIn about this. Where do you access the discount?
This feels like an actual agent app builder, not just a UI generator — bundling web search + code execution + vector DB + sandbox in one place makes it much easier to go from “cool demo” to something you can run as a real workflow.
It sounds so cool that it’s hard to believe 🙂
Can your project create an AI for shopping? Does it need to visit store pages, analyze product information, compare them, and then train its own database?
Great experience overall—fast build times, solid integrations, and a surprisingly smooth path to deployment. I’d love more templates and deeper customization options, but even as-is it’s one of the best “idea to app” workflows I’ve used.
Is this tool dedicated to agent building or whole apps with infrastructure?
It has taken care of all the troublesome things like certification, database, and deployment. I only need to focus on the creativity itself, which is really impressive. I hope the connection and settings between various functional modules can be made smoother to reduce the time I spend on finding configurations.@Kai (Jiabo) Feng
It has taken care of all the troublesome things like certification, database, and deployment. I only need to focus on the creativity itself, which is really impressive. I hope the connection and settings between various functional modules can be made smoother to reduce the time I spend on finding configurations.
Congratulates team！Compared with other tools, the code and apps generated by Blink are significantly more stable and have fewer errors, which gives me great confidence. If it could explain in plain language what has been changed when modifying the code, I would feel even more at ease.@
I’m having trouble seeing the practical differences between Blink, Replit, and Lovable.
could you briefly explain what sets Blink apart?
This looks seriously impressive. The self-correcting + full-stack setup (auth, DB, AI, hosting) in one flow is exactly what builders need right now. Curious to see how it handles real-world edge cases 👀
Hopefully that is affordable, vibe coding different agents is more controllable for me comparing using general-purpose agents. Good work team
Upvoted! Love it that you can just scan the QR code to test it out on phone, its usually a bit of pain in the ass for iPhone user. Looking forward to vibe coding more things with it!
I’ve played with a lot of AI coding tools, and most of them still feel like fancy chatbots.
This one is different. You’re not writing code or prompts — you’re explaining intent. The agent system does the rest. I rebuilt a Cursor-level app surprisingly fast.
What stood out to me about Blink.new is how much it seems to value speed of intent rather than speed of execution.
A lot of tools optimize for doing things faster once you’re already set up. Blink.new feels more focused on reducing the moment of hesitation at the start — getting from “I have an idea” to “I’m doing something” with as little friction as possible. From a UX perspective, that’s a subtle but important distinction.
As a first impression, the product feels lightweight and decisive without being gimmicky, which makes it easy to imagine using it repeatedly rather than just trying it once.
The claim about recreating Cursor and Perplexity in minutes is bold. Does it actually generate production ready code, or does it need significant cleanup and debugging afterward?
Congrats on the launch!
Congrats on the launch, Kai 🚀 The shift from stitching together infra to describing an agent and having it actually work is compelling—especially with built-in context handling and tool orchestration.
From your testing, which part turned out to be the hardest to generalize across different agent types: long-running context, tool reliability, or multi-agent coordination?
Hey everyone! 👋
Kai here, founder of Blink.
When we launched Blink, something interesting happened. People weren't just building landing pages and dashboards — they kept trying to build AI agents. Research assistants. Coding copilots. Support bots that actually do things.
But building agents meant stitching together APIs, managing context windows, handling tool calls, deploying infrastructure. Real engineering work.
So we asked ourselves: what if you could just describe an agent and have it work?
That's what we're launching today.
Blink Agent Builder lets you create agentic AI apps from a prompt. We tested it by rebuilding Cursor, Perplexity, and Shortcut — fully working, no code.
Everything's included: web search, code execution, vector database, sandbox, image and video generation, 180+ models, webhook tools for any API. Plus human-in-the-loop, multi-agent, and context engineering so your agent stays sharp.
Would love to hear what you think — and what agents you'd want to build. I'll be here all day.
—Kai
PS Grab our PH launch discount 🎁