2026 is the year agents move to the cloud, and top startups like ramp already live in this future.
unfortunately many companies are unprepared. to help, we @mainframe wrote down all we know about making codebases cloud agents ready.
hope it's useful! https://t.co/ZJNQvIzUiq
We’ve been in private beta with a human + AI workspace similar to Buzz, with a few really important differences:
(We previously built a company backed by Slack that sold to Atlassian, so we've been thinking about this problem for a while)
- Agents reply by default unless you specifically flip to “team chat.” This feels 10x better than having to @ mention the agent every time.
- It’s all in the cloud, with shared compute spread across a set of VMs. Way smoother onboarding, and yes, you can still connect your claude/codex subscriptions
- You don’t create an army of agents. Number of agents is a vanity metric. Instead, you create shared computers, each one is a “space” where you define shared memory, connectors, skills, automations, etc. The Type agent pulls the appropriate context from the space where you have the conversation.
- You can connect it to Slack to make it easy for your team to adopt and slowly move over rather than having to rip out Slack day 1.
We’re working with a couple dozen forward thinking companies, who have told us “the whole team loves type”, “it’s the most used app on my computer”, and “type gives you superpowers”
Here's a demo of how it works. Reply if you want to test it out!
software factories are failing because models aren't trained to optimise code quality - begs the question what exactly is code quality then
lovely read and waiting for part 2!
We shipped a brand-new Effect website.
Take it for a spin, click everything, and let us know what you think.
Bugs, feedback, confusing bits, we want all of it ↓
https://t.co/zNbx1ef9ZD
the thing that killed my editor for me was fast local voice models more than OpenCode
from the beginning i was looking for faster ways to interface with the computer. for a while that meant becoming very good with the editor
but ultimately voice beats that
A running thread of Effect community videos 🧵
Talks, tutorials, demos, podcasts, workshops - in no particular order - we’ll collect useful videos from people across the community building with, teaching, and talking about Effect.
I stole this idea and now use it with every single employee.
It’s the best illustration I’ve seen of teaching someone to be high agency.
It says there are 5 levels of work:
Level 1: “There is a problem.”
Level 2: “There is a problem, and I’ve found some causes.”
Level 3: “Here’s the problem, here are some possible causes, and here are some possible solutions.”
Level 4: “Here’s the problem, here’s what I think caused it, here are some possible solutions, and here’s the one I think we should pick.”
Level 5: “I identified a problem, figured out what caused it, researched how to fix it, and I fixed it. Just wanted to keep you in the loop.”
Using this framework, here’s what I say to every new employee…
You will live at Level 4 from Day 1 and as we build trust you will rise to Level 5.
Being high agency doesn’t just mean tackling problems in this way. It means your entire way of working should be oriented to being a Level 4+ employee.
Plz feel free to steal it as well.
And ty @stephsmithio for the framework!
i've never hyped a model release, we're generally conservative with how we use these things
but gpt-5.6 has had a massive impact on our team, we're using 5x the tokens as we used to
it's not even smarter than fable or anything, but it's just so reliable and fun to use
TypeScript can be surprisingly robust with @EffectTS_.
The latest Code and Stuff video walks through some of the parts I like: retries, structured concurrency, error handling, and dependency injection.
All with great type safety!
https://t.co/BndtjkKGz7
"How do the top products handle this?" Every builder has asked this, and it usually means a week of screenshots and a shared doc.
Give @ManusAI access to @Mobbin and it does the research for you, and more.
Go from:
— KYC onboarding across 10 fintech apps → stakeholder deck
— Camera app research → working retro digicam prototype
— Pricing page audit → annotated recommendations on your design
— 10 language learning apps → competitive pattern atlas
Save this thread.