Very excited to launch @WorkshopAI.
The idea is to make it much easier to build useful things with AI. Connectors to your data, built-in AI without API headaches, and one-click publishing, including private apps.
You can do that in the cloud or on your desktop, with local models that are free, private, and offline — and we even help you pick the right one for your hardware.
Try it out today and let me know what you think!
Introducing Workshop: cloud + on-device agentic AI.
And to celebrate, we're giving away $250k in @GeminiApp AI credits. (details below).
The future of AI work is neither cloud-based nor local.
It's both.
In Workshop Cloud, you can use agents powered by frontier models like @claudeai and/or open source models like @Zai_org's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads.
In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations.
Our favorite part?
You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline.
2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer.
Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally.
Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either.
The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity.
- Native support for skills
- Autocompaction for seamless context management
- Built-in AI for your apps
- Dozens of connectors, like Google Drive, Big Query, and Supabase
- dbt integration to ground your dashboards in your semantic layer
- Native Github integration
- Private app deployment
- ... and more
(+ we're shipping super fast)
To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem.
- First 100 to RT + comment get $500 in credits.
- Everyone else gets up to $250
And thanks to our partners @modal, @GeminiApp, and @Zai_org!
https://t.co/KGBIflxxjK
Gemini is free on Workshop for Max subscribers from May 12–20!
Use Gemini for apps, workflows, internal tools, dashboards, agents, image tools, and more.
Available for both existing and new Max subs.
Want to win an election? Change your name.
Live data from London's #electiontresult2026 shows candidates higher in the ballot get more votes than their party colleagues in the same ward 72% of the time.
17 candidates so far that missed out on a seat:
https://t.co/UpgUuSqdmf
Prompt-to-app is table stakes.
The hard part is what comes next: backend, data, APIs, auth, services, jobs, infrastructure.
Workshop is for building real software.
Want to build with AI for free?
With local models in Workshop, you can build websites, dashboards, internal tools, workflows, prototypes, and more.
That means:
- Zero API costs
- Offline access
- Full privacy
Try local models today in Workshop Desktop.
You don’t have to use one model (or one provider!) for everything.
With Workshop, you can combine frontier and local models in the same workflow.
For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents.
Better quality where it matters. Better privacy, speed, and cost where it counts.
One workflow, best model for each task.
NJ will probably be like:
"Speaking of what "other events" don't do. No other event:
- Leases out operations of the stadiums.
- Changes parking requirements (in cases getting rid of 10K+, in some cases free, parking spots for their hospitality).
- Require extra levels of security"
The USA was always going to be a weird cultural / systemic fit for the world cup (just like Qatar was!), and comparing the experiences vs European hosts would always make it look bad. What a shame.
Hate to be the cliche of "that guy", but you should give @WorkshopAI a try, especially the Desktop version.
Can use a lot of models (including in the same convo via subagents), even local ones.
Potential con is we don't have plans where we loose a ton of money on inference per user though, but models like GLM 5.1 go a long way for way cheaper!
Not every AI model is best at everything.
Some are better at code, others at reasoning, design, or review.
Some are fast. Some are cheap.
Each one a fit for a different task.
So why limit yourself to just one? Or even one family of models?
Workshop's new multi-provider subagents let you delegate different parts of a task to different models.
A sub-task requires deep reasoning? Use a frontier model.
A sub-task is simple? Use a fast, cheap model
A sub-task needs access to sensitive or private data? Delegate to a local model.
Try them out today in both Workshop Cloud and Workshop Desktop.
@googlegemma It's been fun to play around with it!
@chilang loves tennis so he had to test it with it.
Running in @WorkshopAI with MLX on Apple HW is *chef's kiss*
https://t.co/epf5fw3YNf