Parikshit Deshmukh

"A star goes supernova. Scatter wireframe debris outward." English → interactive 3D. Streamed. Generative UI isn't just forms and charts OpenUI + @threejs

What if your agent could generate a beautifully designed personalized email for every user OpenUI + react-email by @resend

Streaming-first language for model-generated UI github.com/thesysdev/open…

Had fun adding @hero_ui v3 support in OpenUI - built a Generative UI version of Google Forms over the weekend (since HeroUI works across React and React Native this should just work as easily on mobile too)

I am very bullish on OpenUI (openui.com) .. it comes with great components out of the box, streaming protocol is super efficient and has a super small footprint! Also .. very easy to put together with @LangChain_JS 🚀

@rabi_guha and @ParikshitGD told me about their vision for generative UI back in early 2024 when the category barely existed... LLMs responding with live, interactive charts and components instead of just text. They were years ahead on this. Cool to see the whole market validating it now. If you want this in your own app/agent, check out @thesysdev (C1 API) and OpenUI.com (open source). The infrastructure is already there.

We deleted entire Rust codebase and replaced it with TypeScript and it got 3x faster. Rust is fast != Rust in browser is fast Here's what we found 🧵

watch openai acquire them in like 6mo

We just published our benchmarks and source code: github.com/thesysdev/open… Check it out and let us know what you think!

We built a better alternative to json-render & A2UI Up to 3x faster rendering & 67% fewer tokens. Far fewer broken outputs. We've been shipping Generative UI interfaces to 10,000+ developers for the past year. We know where JSON-based rendering breaks in production. So we built a new format - one that works with how models actually generate, not against it. And today we're open sourcing it: openui [dot] com

@rabi_guha @thesysdev Lessgo 🙌

Today we take one more step towards making Generative UI accessible to everyone beyond just developers With Agent Builder by @thesysdev, building engaging agents is as simple as dropping your Excel files and asking away. The LLM plans, reasons, and adapts while you scan, compare, and act through a living interface. Generative UI shouldn't be gated by who can write code. Today we're opening that gate a bit wider

🚀 Agent Builder by Thesys just dropped! You can now build agents like Claude Cowork, Perplexity, Julius, Gamma — but customized for your own use case. What makes it different: - No rigid workflows or coding required - Responds with interactive UI (charts, tables, reports, slides) - Production-ready (embed or ship as apps) No code needed. Just connect data, define behavior with prompts, customize and publish. Build analytics agents, sales co-pilots, finance tools, internal dashboards, whatever you need. Watch it work👇 and then build one yourself! $10 free credits to get started (link below) #GenerativeUI #genUI

Any good implementations of /compact in the wild? Didn't realise this fundamental block of conversational apps is such an overlooked problem

AI assistants like Claude still reply with walls of text. Slow. Passive. Meh. What if they could show instead of tell? With C1 MCP by @thesysdev, Claude can respond with Interactive UI like 📊 Charts 📦 Cards 📝 Forms 📄 Slides If you use Claude, you’ll want this. Takes 2 minutes to setup. 👉 thesys.dev #Claude #AI #GenerativeUI

@neural_avb @rabi_guha @thesysdev @claudeai Absolutely. Which one do you think we should do next ?

@rabi_guha @thesysdev @claudeai CFBR... Man this looks really cool! Does this only work on Claude, or are you planning to extend this to other chat services?

MCP Apps feels like a new primitive for agents. We built @thesysdev MCP so Generative UI becomes a first-class citizen in agent workflows, not an afterthought. When your thinking happens inside @claudeai, it shouldn’t stay trapped in text. Humans reason spatially, visually, iteratively - agents should meet us there, generating charts, cards, slides, and reports as part of the thought process itself. Built on MCP Apps. Brought to life inside @AnthropicAI’s ecosystem. This is how agents become interfaces.

A big thank you to everyone who joined us for the “AI for Engineering Leaders Dinner” last Saturday in Bengaluru! One of the highlights of the evening was seeing Ask Ellie in action. It also turned into a great space for hearing different perspectives on how AI fits into engineering workflows and how teams are thinking about using AI day to day. Shoutout to @EntelligenceAI and @composio for making this happen. Cheers!

Work is changing. It’s no longer tickets, dashboards, and slide decks stitched across disconnected tools. MCP redefined the data layer. With MCP Apps, @claudeai and @anthropic are redefining the application layer. Integrating @thesysdev was the next obvious step. This is the Generative UI layer for a modern Work OS.

Today, we’re launching C1 Artifacts API on @ProductHunt! Build AI apps that can generate stunning slides & reports in real time ✨ Last month, we launched C1 Generative UI API and the response genuinely blew us away. Thousands of developers signed up, started building, and pushed C1 into production way faster than we expected. Now we’re shipping the next step in that vision. Today, your users are stuck app-hopping👇🏻 They pull metrics from your product → switch to ChatGPT to summarize → then move everything into Slides/PowerPoint and spend hours beautifying to share with their team. It’s slow, tedious, and breaks the workflow. C1 Artifacts API solves this. Your users can now create beautiful & interactive Artifacts right inside your app: ➡️ Slides with layouts, visuals, and sectioning ➡️ Reports with charts, summaries & highlights And edit easily with follow-up prompts. Fully on-brand. Instantly shareable. Integrate with your app in just 3 easy steps or try as MCP in your favourite AI apps (ChatGPT, Claude, Cursor, etc.). Whether you’re building an AI copilot, assistant, analytics tool or an AI-first B2B product, C1 Artifacts API lets your AI app get work done faster and smoother.