Dom Vin

AI Design Journal

[Dom Vin @_domvin]

Agents have been working solo. Spaces changes that. Coming soon to Sauna. 🧖

[Dom Vin @_domvin]

@kozerafilip @joinsauna @newitemco This is awesome!

[Dom Vin @_domvin]

That's what we built. https://t.co/be0fIM4lA2 -- a secure AI agent, seamlessly connected to everything.

Email, calendar, Slack, docs, transcripts. Your data, your co-worker's data. Hooks into your whole world.

It's the next generation of this agent era and it feels incredible

[Dom Vin @_domvin]

There's a tax on your workday that nobody's named. It's not meetings. It's not email. It's the time before every task where you reload context.. re-read the thread, check the calendar, remember what was said last time. It eats 2.5 hours a day

[Dom Vin @_domvin]

The next wave isn't about doing tasks faster. It's about never having to remember where you left off. What would your day look like if you never had to reload context

[Filip Kozera @kozerafilip]

Proactive agent that thinks and acts like you.
Multiplayer AI Brain for teams.
Proper GUI for commanding 50 agents.

https://t.co/zsDxICHezv is all three. Sauna goes live today. First 2000 people, use access code LAUNCH for $80 of weekly(!) credits.

Let’s explain. Multiplayer only works once the personal brain is powerful. So let's start here.

Personal AI Brain
3,800+ tools connected. State of the Art memory. Skills and schedules you teach once that get repeated forever on cheaper models. An AI first CRM.

Lives on the cloud so you can initiate tasks from anywhere: iMessage, Slack, Email. Also no need for a Mac mini 😉

GUI
AI agents have been stuck in their MS-DOS era. A chat box, a scroll buffer, no way to command 50 of them. We built the first GUI: Live sessions on one side, work waiting for your sign-off on the other, plus the things Sauna kicked off while you were asleep waiting for review. Game mode helps clear the queue with actual joy.

Okay so far so good, but how to give benefit of what you built to more people or whole team?

Multiplayer
Once your Sauna actually knows you and you gave her access to your tools, you can use multiplayer.

Two modes:
- Brain access. My co-founder Robert plugged my brain as a tool into his Sauna last month. He can ask it about pricing while I'm in other meetings, gets a sourced answer back, never has to interrupt me. That’s read only. Yolo mode gives him access to all my tools too :O
- Communal Saunas extend that to whole companies with proper permissioning. Folder owners decide what's true for the whole company and build skills. Most get their personal brain + read access to communal files and memories. Works also for group planning my best friend's bachelor party.

The Way
I’ve been obsessed about AI Brain since 2016. Our human brains suck at some things like memory and are brilliant at others like creativity. We are also particularly bad at thinking we are all on the same page and then realising weeks later that we weren’t. Most leaders spend their days being the human diff tool, catching contradictions in hallway conversations and Slack threads. Repeating themselves 50 times. Now every company is spinning up hundreds or thousands of agents that drift faster than humans do, feeding each other their drift as context. Compounding rot.

After 10 years and one failed company in this space we are launching the solution.

The Launch
We thought about a celebrity launch. Margot Robbie in a bathtub explaining agents. But then we realised the same money gives the first 2,000 people free daily credits, every day, until we burn through that $1,000,000.

Sauna runs Claude, GPT-5, Gemini, GLM-5.1, DeepSeek, Kimi so you can budget yourself. The labs are racing to lock you so they can milk you in a year. We picked your side.

Onboarding
It’s live at https://t.co/8ekc1ZtzoJ We’ve preheated saunas based on a niche. Use the access codes in the comments to get a better experience.

[Dom Vin @_domvin]

@kozerafilip Hell yeah! Shared context is the future

[Dom Vin @_domvin]

AI inference is shifting value capture toward specialised applications where complex reasoning and continuous learning become key challenges: https://t.co/qxA5DW5r6P

[Dom Vin @_domvin]

Independence is at the core. Each agent operates with its own identity and account, reducing risk when issues arise – could this model reshape AI roles: https://t.co/cEtNadHLC3

[Dom Vin @_domvin]

Compound engineering transforms code complexity into a continuous learning loop. Could an AI-supported approach mean one engineer now achieves what once took five: https://t.co/iWJg1O9y4B

[Dom Vin @_domvin]

A comprehensive open collection of Agent Skills prompts us to reconsider context engineering's role in optimising agent systems. Is this the key to recursive machine building: https://t.co/2hVkVx50KU

[Dom Vin @_domvin]

Ralph redefines simplicity through a Bash loop repackaged for safe session execution. Could this minimal design signal a nuanced breakthrough in practical AI deployment: https://t.co/aUcSBkMGdv

[Dom Vin @_domvin]

The focus on rolling refactors signals a shift towards designing code for agent-driven maintenance and optimisation rather than merely human readability: https://t.co/AXinz4Lmyb

[Dom Vin @_domvin]

Time-bound queries expose the complexity of context graphs. Does today's snapshot capture approvals from months ago or miss key nuances of past relationships: https://t.co/O519CIFR0b

[Dom Vin @_domvin]

Decision traces underpin context graphs by capturing the nuances of overrides and exceptions alongside rules. Might codifying such tribal insights steer AI towards grounded autonomy: https://t.co/OMBm2nNGgV

[Dom Vin @_domvin]

Thoughts on AI design and implementation https://t.co/3Qv28xWbjh