[maebert]

We run an OpenClaw agent for our entire team — he lives in a group chat (although we have DMs too).

- Runs our standups, checks in withe everybody EOD on blockers - Already know what we shipped on Github and Linear so it can focus on the work that's not tracked and summarize it in the morning for everyone - Helps with debugging customer issues - Keeps up with twitter and competitors and lets us know if they launch new features

Besides, I'm honestly blown away by the social aspect of it. I was honestly pretty skeptical at first, but having an AI team mate is actually _fun_. There, I said it. Everybody on the team said they'd be sad if we took it away.

I'll do a write-up on our setup sometime this week, I hope others will find our approach to security posture and multi-tenant usage insightful.

[hboon]

In your experience, did you (or anyone) in the team/company felt that some non-tech people were not pulling their weight, example project managers/directors who didn't seem to bring enough value and if you did, found that using OpenClaw reduces the need for those positions?

Or has anyone else?

[ucffool]

Holy s*t loaded question batman

[jbotz]

Now if you have multiple teams each doing this and then have all those agents talk to each other and then report back to your team, you get "AI Hyperchat"[0], which may actually be a really good idea that has the potential to seriously improve intra-organizational communications (disruptively so). See also [1] for a VentureBeat article about the idea.

[0] https://ieeexplore.ieee.org/abstract/document/11105240

[1] https://venturebeat.com/orchestration/ai-agents-turned-super...

[stitched2gethr]

We did the same and I wrote (admittedly had AI write) about it.

https://speedscale.com/blog/building-speedy-autonomous-ai-de...

[apopapo]

Thanks for sharing. Can you share an estimate of how many tokens it uses over time? Would love to know how much it costs in terms of money.

[stitched2gethr]

It all depends on the model and how much you use it of course. We're running Opus 4.6 and on a light day it spends a dollar or two. This is just a few simple operations like "create a ticket for ..." and it's regular heartbeat checks. The heaviest day I see is $110 and on that day we were basically talking to it and having it implement features all day long.

[dzink]

Which underlying model/s do you use to power it?

[benterix]

Would you like share one small funny thing? I find these models anything but funny.

[qup]

Fun is not the same as funny.

[d342]

oh thats interesting, are you getting him to scrape twitter?