People and AI agents work from one shared context.
1. Create custom agents in plain language
2. Agents build on each other's work
3. Turn chat into research and webpages
Teamily AI lets teams collaborate in one group chat.
Personal bots will give way to team agents in every workspace.
1. Chat panel updates daily metrics in real time
2. Embedded widget tracks live stats
3. Teamily AI turns chat into finished work
This UI from @Teamily_AI gets it right.
team agents turn chat into research and docs in one shared workspace.
1. Agents build on context
2. People review in real time
Teamily AI sign-ups grew 32x this quarter.
"Nothing, not even mountains and seas, can separate people with common goals and vision."
@ChinaAMC_HQ CEO Yimei Li and @FranklnTempletn Co-President and Chief Commercial Officer Daniel Gamba trade perspectives on innovation — and discover why local insights and global expertise are stronger together 🌎
#ChinaAMC #FranklinTempleton #innovation #globalinvesting #leadership
Investment involves risk, including possible loss of principal. Any forecasts, projections, or opinions contained herein are for reference only and are not guaranteed to occur. The information in this material reflects prevailing market conditions and our judgment as of the release date, which are subject to change without further notice.
The interface matters. Give your agent a computer. It stops block me when doing compute use 😂
Connected Codex to Simular’s Sai MCP, sent a plain-English task, and watched Sai operate Windows Calculator on a hosted desktop. It entered the calculations through the app and left both results visible in History.
For developers, having the computer and desktop control available behind MCP is pretty useful. I can hand my agent a desktop task without building and maintaining the VM, screenshot pipeline, and action loop myself.
Simular’s Agent S4 research also caught my attention: keep the model and agent harness fixed, then improve the interfaces the agent works through. Alongside clicks and typing, better tools can turn repetitive actions into a single operation. I think that direction has a lot of potential for vertical agents too.
This video is a small, real Sai product demo; it doesn’t reproduce the S4 experiments. Waiting was cut from the recording.
Separately, Simular reports the highest partial score on OSWorld 2.1—79.38%—for Sai with Claude Opus 5, at $14.34 per benchmark task. Those are vendor benchmark figures, separate from this demo.
Agentic trading is multiplayer.
We’re building a way for you to create your own trading desk, with specialized agents working together, powered by @SuiNetwork’s parallel execution and agent memory on Walrus.
Join the Agentic Economy: https://t.co/IUR4sZSPm2