Launched this week
Humalike
Give your AI agents the social intelligence they're missing
725 followers
Give your AI agents the social intelligence they're missing
725 followers
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.
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!!
@lakshminath_dondeti Components that change behavior of agent (Theory of Mind, Turn-taking) take personality into account. It's not about changing personality of the agent, it's making his judgement and context more humanlike while still being aligned with his personality.
Humalike
@lakshminath_dondeti tysm for supp! I'm curious, what made you think about this question? Are you working on something similar or?
This is an awesome idea.
Do you have some benchmarks comparing Humalike behaviors with the baseline model?
@rezgar Sadly there are no pre-existing benchmarks for this problem, we had to define the problems and evals ourselves. We open-sourced one of our benchmarks for inferring local social norms in group conversations.
Paper link: https://arxiv.org/abs/2606.14600
We don't brag about it too much because being the best on your own benchmark has "trust me bro" energy haha
jared.so
@rezgar Thanks for the comment!
Humalike
@rezgar tysm Rezgar :))
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 turn-taking and social observability APIs make sense to me, but persona/norms feel like they could go wrong in a way that's hard to detect. if the agent reads the room and picks a side or a tone to fit in, how do you catch it drifting into something the team didn't actually want, before a customer sees it
Humalike
@omri_ben_shoham1 Great question - this is exactly the failure mode we think about a lot.
We don’t want persona/norms to mean “the agent blindly adapts to the room.” The agent should understand the local context, but still stay inside the team’s intended personality, brand rules, safety boundaries, and escalation policy.
So persona is an anchor, not a free variable. Norms are interpreted, not blindly copied. And social observability is what helps catch drift in tone, intervention rate, conflict level, or user reactions before it becomes a customer-facing issue.
@omri_ben_shoham1 I will also add that social observability is meant to help you monitor the drift of how users percept your agent. The components complement each other
that makes sense as a monitoring layer, my worry was more about the response lag though. if drift only shows up after enough interactions to trend, is there a way to catch it on a single bad interaction before it ships, or is this mostly a "watch the pattern over time" tool
@omri_ben_shoham1 Oh I see. You can put hard rules on what agent should never do, if you use turn-taking just include it in the turn-taking system prompt. It will watch the generated message and if it breaks a hard rule, it will catch it.
There are also other things you could do to avoid drift but our goal is to make it so you don't have to worry about it. Solving this problem is on us, so you don't have to think about 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!