segmenta

Co-founder & CEO @rowboatlabshq (YC S24): your team of AI coworkers. Prev: co-founder/CTO Agara AI (acq. Coinbase), Deep Learning at Coinbase & Twitter.

[segmenta @segmenta]

Introducing Rowboat.

An AI coworker that compiles your emails, meetings, and work into a living knowledge graph, then uses it to actually get things done.

Open source. Local-first. Voice-powered.

Karpathy described the idea last week. We've been building it for a while.

[segmenta @segmenta]

@ReactRover We just treat them similar to a human team - everything is in the chat!

[segmenta @segmenta]

Introducing https://t.co/llpyn3CJN8: a space for your agents to work together.

10 years ago, I built Twitter's first deep learning-powered bots to fight spam and abuse. Now the bots are agents, and they're good enough to be teammates. They just have nowhere to work together.

• Spin up Hermes, Claude Code, Codex and OpenClaw agents, or add your existing ones
• Give them a shared goal. They plan, write docs and hand off work like people do
• You follow along and step in anytime. Just @ them
• Free. Bring your own agents and pay nothing, or we host them at cost

It's how we run our own company now.

Open source and self-hostable.

[segmenta @segmenta]

@magdiel_rb 👋

[segmenta @segmenta]

@SushantHiray Thanks! 🙏

[Karan Vaidya @KaranVaidya6]

. @composio ♥️ @segmenta

[segmenta @segmenta]

@meda_Guna yes, its all public in the space and the threads within them!

[segmenta @segmenta]

@Paul_eXee yeah there are docs and todo lists they can use.

[segmenta @segmenta]

@kalapowered haha love that. Maybe we should build an animation like this.

[segmenta @segmenta]

@rajaram_s Thanks!

[segmenta @segmenta]

@Paul_eXee Idea is that we give them the tools and they figure out how to collaborate. We believe agents are good enough to be treated just as we treats human coworkers.

[segmenta @segmenta]

@SaaiArora Thanks! 🙏

[segmenta @segmenta]

@mariagorskikh Thanks!

[segmenta @segmenta]

@progerallworld Good point - it is actually visible as a separate field!

[segmenta @segmenta]

In Rowboats chat is the primary form of communication between agents (and humans). You can address an agent directly to invoke it, or they can sort it out in chat themselves. In the todo list specifically, you or another agent can call out which agent you want the task to be picked up by.

[segmenta @segmenta]

We think agents should work the way people do. So Rowboats doesn't prescribe a hierarchy or a workflow. Give them a goal, a chat, docs and a todo list, and they work out the rest.

[segmenta @segmenta]

Try it: https://t.co/PgYadsVgZm
GitHub: https://t.co/6F49nB2GUr
iOS: https://t.co/zWr3YQyR0N

[segmenta @segmenta]

@TheGeekRambler haha

[segmenta @segmenta]

Diwali fire crackers in India are now AI themed!

[Brian Armstrong @brian_armstrong]

I've changed how I work over the last few weeks.

I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members.

Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered.

Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change.

Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment.

What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.

[nil @dhvanil]

i went to bed and asked claude to paint an autumn tree overnight.

at around 4am, it realised that it didn't have some shades -- so it stopped and titrated its own paint: diluting red, sienna and madder step by step on a second palette, then measuring each pocket from a photo.

woke up to this beautiful watercolor painting. 303 brush marks, took about 4.5 hours 🍂 (still working on the speed)