Humalike - Give your AI agents the social intelligence they're missing
by•
Today's models are capable enough. Smart enough. Fast enough. But we still feel they don’t fit in the room. Humalike is building the behavioral infrastructure for humanlike AI agents. The social skills & proactiveness your agents have been missing. APIs, models, benchmarks.
Replies
One quick question: i feel that knowing when not to speak is what always gives bots away in group chats rather than the opposite. Does it work out of the box, or do you have to tune it per community?
jared.so
@david_vilalta Spot on, and that's exactly one of our biggest advantages: you don't have to tune it. It works out of the box, no per-community setup.
Thank you for the comment! :))
Humalike
@david_vilalta So far, solutions were either bad or didn't work at all. This is our first solution to this problem, give it a try! We'll keep making it better :))
Congrats on the launch, this is such a sharp problem to tackle!! The Social Signals piece hit home for me, on the recruiting side we run into the exact same thing: a candidate going quiet after a great call, or an interviewer's one line notes not saying what they actually mean. The signal is almost always there, it's just messy, not absent. Curious how much of Turn Taking transfers from group chats to something like a one on one interview flow?
Humalike
@ceciliatran Thank you!!
1:1 interviews are more structured than group chats, so the “right behavior” is easier to define: ask, listen, follow up, give space, move forward.
But social awareness still matters a lot. The candidate needs to feel heard, not rushed or interrogated. That’s where Turn-Taking transfers well: knowing when to pause, when to follow up, and when to move on.
@ceciliatran Thanks for support and in-depth question cecilia!
Humalike
@ceciliatran tysm for the supp Cecilia!!
Really interesting direction. I am curious that for AI chat products, do you think agents will make users feel being manipulated when they can read emotional signals or adapt their tone in real time?
@xinrui1 I think the opposite, users will feel more understood and less annoyed. But manipulation is real risk we have to look out for.
Humalike
@xinrui1 That's a sketchy topic, I think that we as humans use / act with diff behaviors consistently, one of them being manipulation. Humalike pushes in the direction of agents feeling human, with good intention.
Congrats on the launch! 🎉 How does Turn-Taking decide when an agent should jump into a group conversation vs. hold back?
@rimar_boter Thanks! It's several aspects working together:
1. We use other Humalike components to make context and judgement as good as possible - Theory of Mind, Social Memory, Norms, Social Signals
2. We tuned turn-taking based on our experience building several AI products across different niches (neonagent.ai - community manager on Discord, jared.so - AI coworker for slack...)
3. We handle tricky edge-cases e.g. someone cutting agent off when it was typing, or if the chat is chaotic with rapid messages on different topics
There's a lot of judgment need AND handling of complexity/edge cases. We handle all of this:))
Humalike
@rimar_boter tysm for the supp Rimar!!
The strongest version of this is not making agents feel more human; it is helping them know when not to act. Turn-taking, memory, and observability are exactly the boring layers that make an agent usable in a real group instead of just impressive in a demo.
Humalike
@krekeltronics Exactly!
@krekeltronics It's good point and I like your wording of it!
Congrats on the launch! How does this play with the one-shot integrations? I'm thinking about testing with WhatsApp groups where context switches constantly, does the agent keep social memory across platform boundaries if the same group moves between channels?
@inescastillo Agents for whatsapp is exactly the usecase we played with during development and testing. I recommend using our docs docs.humalike.com (just give this link to your coding agent) and it can often one-shot it (if you struggle we are happy to help!)
About social memory context: it can remember people across channels on a single platform. Recognizing people across platforms is on our roadmap!
Humalike
@inescastillo Looking forward to you trying it!
Congrats on the launch! This hits close to home. The gap is never how smart the model is, it's exactly what you're describing: agents that don't read the room. Turn-Taking and Persona look genuinely useful for our customer-facing agents. Grabbing the free tokens now, how hard is it to wire the WhatsApp integration into an already-built agent stack?
@pedrolivares Great to hear your interest! We made it super easy to connect existing 1:1 agents to our stack and make them humanlike both on 1:1 and in groups. In terms of whatsapp integration this is something you have to do on your end, but we are happy to help you, we have experience with it.
If you have any issues or new questions please hit me up on linkedin (sent an invite :))
Humalike
@pedrolivares 100%. Tysm for the support!
Framing AI social skills as infrastructure rather than a feature is the real unlock here, most teams bolt on personality as an afterthought but treating turn-taking and social memory as primitives changes how you architect agents from day one.
@ilko_kacharov We got used to AI being capable and useful. Interaction quality will be the next differentiator
Humalike
@ilko_kacharov 100%! tysm for the supp Ilko!
I'm soo interested in this! I find myself using "please" and "thank you" with agents all the time; however, when I'm hit with a 50-page response, I quickly realize my courtesy means nothing haha. Maybe this will ease my pain!
Humalike
@cairacshields 100%!! We as humans are used to dealing with other humans, and that simple human interaction feels "normal" which translates to = correct. With AI, now we are "getting used" to a new way of interaction that we really can't get used to / don't enjoy at all. Humalike aims to solve the experience problem, which will solve your issue!
jared.so
@cairacshields Thanks for the support! I would love to chat about it in the future
The social memory piece is what stands out to me - most agent frameworks treat every conversation as stateless, so an agent forgets it already annoyed someone yesterday. Curious how you handle memory decay though, do old signals about a person just fade over time or does everything stay weighted the same forever? Congrats on the launch.
jared.so
@galdayan You absolutely nailed it Gal and that's one of the reasons why we came up with that idea.
Regarding the handle memory decay - we don't actually handle it right now, but weighting the memories based on their age is a good idea and we will probably implement it in some way int he future!
Happy to chat more about it :))
Humalike
@galdayan Good insight Gal, thanks! tysm for the supp