Nate retweeted
There’s an incredible amount of technical depth behind building AI agents that can actually work for executives.
We’re building an AI agent that needs to be reliable, accurate, smart, and fast, while also adapting extremely quickly to the individual working style of each executive.
@Dorbernsohn and the team are doing brilliant work on this!
Read more here:
engineering.catchagent.ai/ow…
You may know subagents as a way to maintain an efficient, modular context, fan out concurrent work, etc. But they could also be a powerful tool in keeping minimal trust boundaries when building agents that communicate externally.
engineering.catchagent.ai/su…
מה אם יכולת להוסיף רק 3 דקות להליכה שלך כדי שהיא תהיה כמעט כולה בצל במקום להיות רובה בשמש הקופחת של סוף אוגוסט?
darksides.app






