Workshop your ideas into reality with cloud and on-device AI. Chat with AI to build websites, AI apps, dashboards, native tools and more. Cloud + Desktop
Pisces–Cetus Supercluster Comp
Joined June 2024
- Tweets368
- Following33
- Followers2.3K
- Likes233
Workshop AI retweeted
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.
Workshop AI retweeted
🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power!
Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇
What's new:
🧠 Outstanding agentic coding — surpasses Qwen3.5-397B-A17B across all major coding benchmarks
💡 Strong reasoning across text & multimodal tasks
🔄 Supports thinking & non-thinking modes
✅ Apache 2.0 — fully open, fully yours
Smaller model. Bigger results. Community's favorite. ❤️
We can't wait to see what you build with Qwen3.6-27B! 👀
🔗👇
Blog: qwen.ai/blog?id=qwen3.6-27b
Qwen Studio: chat.qwen.ai/?models=qwen3.6…
Github: github.com/QwenLM/Qwen3.6
Hugging Face:
huggingface.co/Qwen/Qwen3.6-…
huggingface.co/Qwen/Qwen3.6-…
ModelScope:
modelscope.cn/models/Qwen/Qw…
modelscope.cn/models/Qwen/Qw…
Workshop AI retweeted
"Delegate good times, come on!"
That's the song, right?
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.
Workshop AI retweeted
Cool idea @MaziyarPanahi @googlegemma
Here is a demo you can play with
Gemma 4 + Sam 3.1 running all on a Mac via MLX
Build with @WorkshopAI
Repo 👇
Workshop AI retweeted
A lot of our product thinking has gone into this idea:
AI workflows get much more useful when you can mix frontier + local models, across providers and environments, in one easy to use system.
Excited to see that taking shape in Workshop.
Workshop AI retweeted
Most on-device AI isn't useful for running agents beyond a demo.
But the models are no longer the bottleneck. Most people just aren't using them the right way.
We've found that a simple paradigm change takes on-device models from demo to actually useful:
Oversee on-device models with a more powerful AI model.
It's an overlooked approach, because all of the major agent harnesses are optimized to keep you spending money with their cloud inference.
With yet another update to our agent harness this week, @WorkshopAI lets you use frontier and "open frontier" models for the main agent, which can itself delegate tasks to smaller, on-device models.
It eliminates >90% of the failure modes of using on-device models for agentic tasks, and it turns on-device AI usage from a demo to a legitimate tool for daily use.
Workshop AI retweeted
Wow works with GLM 5 and Qwen 3.5 (offline)
Build websites in your desktop
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!
workshop.ai
Workshop AI retweeted
It's Opening Day! The best day of the year. ⚾
Baseball has always been THE sport of numbers. But wOBA? FIP? WRC+? For years I'd nod along and quietly Google later.
So I built StatDNA. An interactive encyclopedia of baseball analytics. Explore metrics with easy to understand explanations and examples, compare park factors across all 30 stadiums, and ask an AI to break down any stat line you paste in.
Started as something I wanted for myself, but hopefully it’s helpful for anyone looking to understand these stats a bit better too (because honestly, they make the game even more fun).
Dropping the link below.
Workshop AI retweeted
To celebrate Workshop's launch, we just open sourced dbt-skillz.
Your @getdbt project already contains the knowledge of your data stack. dbt-skillz compiles that context into a skill your agent can use.
Built for Workshop, @claude_code, Codex, @cursor_ai, et al.
Repo 🔗 below
Workshop AI retweeted
👀
@claudeai Opus 4.6 is now powering Memex Web's Genius mode, just in time for your weekend building.
Happy trails!
Workshop AI retweeted
I can’t count how many times I’ve started with “this should be easy” … and ended up fighting joins, permissions, and environments.
Memex Web makes that whole loop effortless.
Workshop AI retweeted
Memex Web in mobile is here!
For those times where you can't wait to get to your desktop to get to building or getting an answer from your data.
Workshop AI retweeted
Idea to app is very quick now
Legal doc reviewer using AI
Took 10 minutes to build with @workshopai
Workshop AI retweeted
Congrats to the @workshopai team on the launch of their AI builder for data apps, powered by Modal Sandboxes.
Learn more → modal.com/products/sandboxes
Big thank you to our partner @modal for the best-in-class serverless infrastructure that makes this happen!
We evaluated all the main players in this space, and Modal was head-and-shoulders above the rest.
Workshop AI retweeted
🍌 Built a tiny thing: Bananarama.
A super simple tool (made with @workshopai) to try Google’s new image models, Nano Banana Flash and Pro, and even feed in context images.
Password-protected in case it goes viral 😂
Want access? DM me. I’ll cover generation costs.
Workshop AI retweeted
Couldn't find a good World Cup 2026 schedule so I built one with @workshopai 🏆
✅ 104 matches with smart filters
✅ Interactive knockout bracket with transition logic
✅ 16 venues + directions
✅ Favorite and share features
Hope its helpful for others!
Link in 🧵
Workshop AI retweeted
Here's how I one-shotted the OCR python app using @workshopai
My prompt:
make a python app to implement uploading of image and call the ocr using this sample code. use streamlit for the user interface
(then paste the sample api call to lmstudio)
Model used: qwen3-vl-30b
Full process shown in this demo👇
(link to try in comments)
Workshop AI retweeted
omg one-shotted this OCR app in windows using Memex
@Alibaba_Qwen Qwen3 VL 30B (model)
@lmstudio serving the API
@streamlit for the UI
check this out
