Super clean concept. Most AI agent tools make you use their platform or rebuild your agent from scratch. Switch just lets you bring whatever agent you already have and plug it into Slack. The agent shows up as an actual channel member, not some clunky bot integration. It follows threads, responds to mentions, and keeps the conversation context. Open source too so you can self host if that matters to you.
Can an agent carry context from slack into teams and vice versa? I see that as being the most useful element, where context from a slack channel with engineers can answer questions on a teams channel with execs.
@safi_amin congrats on the launch, looking forward to testing this out.
@safi_amin @umier Hey ! Yep that is possible, the session of an agent that is connected to let's say a slack channel can jump to another channel in another connected messaging like teams, back and forth, and therefore carry the require context!
@umier Thank you Umier! That's one of the most exciting use cases we're seeing. Engineering works in Slack, leadership is in Teams, and the agent carries the context between both without anyone having to copy-paste or re-explain. Let us know how it goes when you try it out!
@safi_amin @umier You can bridge between rooms if needed (even on different messaging apps), or you can get agents from each room to write to a common resource outside of it (eg confluence, a word doc, a wiki) to ensure context is carried.
What happens when two agents in the same channel disagree or give conflicting answers?
@artstavenka1 This actually happens! And I think it's one of the key benefits of having agents in a shared room... when two agents give different answers, the team can see both in real time and make a call. It's the same thing that happens when two teammates disagree in a thread. The difference with isolated agents is that you wouldn't even know they disagreed because nobody sees both answers side by side.
@artstavenka1 It's actually a really good thing! They will be able to see what the other has said and can even have a transparent discussion about the disagreement. The channel gives the agents a way to communicate with each other as well as with humans. I think it's common practice these days to have agents review each others' work, and this just takes it to a new level.
louis says each agent has one human owner and only they can change it. does that hold in telegram too or is it slack and teams first?
@niveditha_patluri1 Applies to every supported messaging app :)
@niveditha_patluri1 Worth adding that this is handled by Switch itself, not by the individual chat apps. So your permissions don't break if you add a new connector or chat app later.
Context switching is the worst so staying natively in Teams is a big plus. really interesting nice work @Switch team👏
@priya_kushwaha1 Thanks Priya, appreciate the support. If the team already lives in Teams, they shouldn't have to go somewhere else to work with their agents!
@safi_amin exactly, keeping the workflow uninterrupted is so valuable. i hope it will be the product of the day🙌
@priya_kushwaha1 Thank you Priya, fingers crossed!
That looks pretty cool. Congrats to the build and launch :) Will give it a try. Isnt it quite token intensive if your agents are always following the conversation?
I noticed we sometimes have discussion which then get compressed into a short clear working document for the agents to run it. Lots of answeres already cleared beforehand. I do have the feeling though the vision of switch is bigger and i will need to grow my horizonts :)
Having one environment that keeps the organizational context and workflows consistent while allowing for the other tools (Claude, Slack, etc) is a big unlock for making human x agentic collab work durably. Will be testing this out soon
@luca_ferrara2 Yep 100% That's the vision -> provide the underlying infrastructure and framework that allows for true human x agentic collaboration.
@luca_ferrara2 Would love to hear how it goes!
If I built my own harness, how would I bridge it to Teams with Switch? (I did build one ;))