Thesys

C1 API changed how AI apps respond turning plain text into live, interactive interfaces. But one thing remained the same: pulling data from the product, summarizing in ChatGPT, then adding it to slides to share. To solve for this we built C1 Artifacts API! 🚀 It lets your AI apps create stunning artifacts right inside the chat: ☝️Slides with layouts, visuals, and sectioning ✌️Reports with charts, summaries & highlights Fully on brand, easily editable with follow up prompts and easily shareable. Integrate with your stack in just 3 easy steps or plug the C1 MCP into your favorite AI app to give it a spin! You can also test it out below! #GenerativeUI #genUI #newlaunch

Try Agent Builder here - console.thesys.dev/onboarding

Your agent, your models! Agent Builder now lets you connect custom models through OpenRouter. You now have access to a growing roster of models from labs around the world. Plug them in, test them out, and find what works best for your use case. And keep building without constraints! Try Agent Builder. Link below.

Day 1 of LIFT Labs’ Spring Accelerator ✅ 6 companies joined us at Comcast HQ in Philly for roundtables + 1:1s with teams across the business, focused on real use cases. Closed with a 7–0 Phillies win! @thesysdev @NEXTGRES @memories_ai @aaruHQ @appliedcompute 1mind

🚀 We're thrilled to share that Thesys is a part of the Comcast NBCUniversal LIFT Labs Spring 2026 Cohort. A huge milestone for our team! Pumped to work alongside an incredible group of builders and to bring Generative UI into real workflows. Let's get to work!

Six companies shaping what’s next in #AI. Not more tools, but systems that learn, adapt, and drive real outcomes. Meet the Spring 2026 cohort of @LIFT_Labs. @thesysdev, @memories_ai, @aaruhq, @appliedcompute, @Nextgres, and 1mind #Startups #IWorkForComcast

🙌🚀

Introducing OpenUI v0.5 v0.1 helped you build chat with UI v0.5 lets LLMs build full apps State, data, actions. All handled seamlessly without the security risks of generating raw code

Try Thesys Agent Builder here -console.thesys.dev/onboarding

Your AI agent doesn't have to look like it was built in a weekend. We added new presets to Thesys Agent Builder! Now build agents that look like ChatGPT, Claude, Perplexity, or fully custom. Skip the frontend. Pick a preset. Ship your agent. 🚀 Try Agent Builder, link below.

The next frontier for AI is generative UI: interfaces that dynamically capture user attention. Claude is leading the way with its latest updates. But before this @thesysdev came up with the framework now they have built this openui which can help achieve that.

Love what Claude shipped with Cowork Artifacts but generating code for Generative UI is the wrong architecture Wasteful: A single dashboard costs 2k boilterplate React/HTML tokens before any meaningful pixel is streamed Inconsistent: Two dashboards generated 5 mins apart don't feel like the same product. No design system. No shared components. Every output is a one off Security Liability: Today its a single-user sandboxed demo. But real software has shared dashboards, team views, embedded reports - LLM generated code for one user running in another user's session. Sandboxed or not, that's OWASP LLM05 territory. Multi-surface: A dashboard generated for desktop never works reliably on mobile. Want to render it on an iPhone? Your only option is an iframe. Yuck. Unstreamable: Partial code is extremely hard to stream meaningfully. What you get is hundreds of chunks of broken renders that flash and flicker. That's not progressive UI - that's broken UX. Code generation is a great starting point. It's not a production architecture. Generative UI in production needs an abstraction layer. The model describes intent. The renderer owns the pixels. Everything else is a liability.

Since a lot of people sent me this, I'll just write about it here Anthropic just shipped what I called Stage 3 in my SaaS 2.0 article - persistent surfaces that refresh with live data, not just reply in text. 2026 is the year of Generative UI. We'll finally go beyond chatting and into the realm of actually delightful AI software

👀 thesys.dev/blogs/agentic-…

Traditional UIs wait for you to decide the next step. Agentic UI acts with you. We break down the full stack, from GenUI protocols to proactive design principles to real use cases like smart dashboards, adaptive onboarding, and automated QA. 🔗 Read the full guide, link below.

> In the agentic enterprise, the conversation is the interface It's not just homepages anymore. Salesforce just bet that the entire app doesn't need to exist. > Why should you ever log into Salesforce again? - cofounder @parkerharris But here's the part most people missed. They didn't stop at headless. They're betting just as big on Slack being the experience layer for the entire platform. > Some work needs more than text. A card to approve, a workflow to complete, a decision to make. This is the beginning of SaaS 2.0 SaaS became chat. Chat will become Generative UI - where the agent doesn't just reply in text, it composes the interface itself.

Check it out here - openui.com

OpenUI is out in the wild and y'all showed up 🫶 We've been reading every tweet, every dm, every late-night build post. Watching what you're making with it is genuinely the best part of shipping. Keep cooking. We're watching 👀

A lot of people asked: what about voice? Voice is the perfect companion to Generative UI. It’s the most versatile input modality, but not always the best output. But paired with Generative UI, something shifts. We don’t navigate software anymore - we express intent, and the interface assembles itself around us.

Agent builder now supports @Snowflake, @supabase, @MongoDB, @databricks, and more. Skip the manual exports. Skip the middleware. Just connect your database right inside Agent Builder. Describe what your agent does, hook up your data source, and deploy it. Then simply ask questions and get back insights as interactive UI, generated in real-time. Try out Agent Builder, link below.