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.
We did the same and I wrote (admittedly had AI write) about it.
https://speedscale.com/blog/building-speedy-autonomous-ai-de...
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.
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?
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...
oh thats interesting, are you getting him to scrape twitter?
Which underlying model/s do you use to power it?
Would you like share one small funny thing? I find these models anything but funny.
Fun is not the same as funny.
[flagged]
Out of curiousity, is it nonsense because you're a scrum master feeling threatened, or nonsense because automating rituals like those seen in SCRUM makes them less about communication and more about just doing the ritual itself?
It is nonsense because it's just nonsense finding a bot "funny" and the team requesting it otherwise they'd be sad. It's totally nonsense if not just marketing
You comment is against hn guidelines: https://news.ycombinator.com/newsguidelines.html
In particular: "Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith."
I assume good faith and still finding it nonsense