Launched this week
Jared is an AI employee that lives in Slack, connects to 10,000+ tools, and gets work done without being asked. Unlike every other AI tool, it reads the room, follows conversations, knows your team and speaks up when it matters. Your social AI employee.
Starnus
Hey team! Great work, curious to learn what are the exact use cases Jared can perform? Is it mainly coding? or generic tool execution? or something else?
@khashayar_mansourizadeh1 He's great at making reports and coding obviously. But he's exceptional at longer ongoing tasks that require coordinating stakeholders. For example you can ask him to "make sure we have all marketing materials ready for PH before friday" and he learns what is needed for PH, makes a list, ask questions to clarify. Then he checks on it during the week, pings people responsible to ask how is the progress going and makes sure everything is ready by friday:)
He has his own email, browser, computer and 10k+ tools available so he can be helpful in hundred different ways:))
Starnus
@mateusz_jacniacki Nice, curious, how it has 10K+ tools? I assume you haven't done 10K+ complete integrations, it would be even hard to say it has access to 10K+ API docs, and then how it would handle Auth, Keys, etc. So very curious to know how it would work :)
Visdiff
Looks awesome! I like the idea of the bot being able to collect all the information it needs from the existing conversations, but can we also point it at external sources to use as reference when doing its work?
@abdelh2o Yeah! Exactly. It comes with 10,000+ tools to connect to your sources like Linear, Figma, Github, and many many more. It also has browser and email, so you can just send him a link of the resource, send it on slack, or do a CC for a mail.
Do you have any specific source you'd like to use? I will let you know how good Jared is with it:))
Visdiff
@mateusz_jacniacki I had notion in mind, since a lot of knowledge gets stored there that is usually useful when getting things done (at least for me)
@abdelh2o Yes! Notion is well supported and test. It should work fine
What happens when it jumps into a public channel and gets something wrong? That feels like the moment that can either build or break trust with the team. Is there a way for people to correct it so that feedback actually shapes how it behaves next time?
jared.so
@jared_salois Yes! He has an amazing memory, that shapes the social behavior of the agent in real time. He might not be perfect the first day, and we are far from being perfect. But we will get better over time!
which llm models are being used under the hood and are they configurable?
jared.so
@pedro_pizarro2 Not configurable rn. Routed to best model to balance speed and accuracy. For hard problems we route to top models :))
Proactive monitoring is the hard part. We built something similar for our AI audit pipeline, the system needs to know WHEN to act, not just HOW. Curious how jared handles false positives, does it learn from dismissals or is there a confidence threshold you can tune? In our experience, the "when to trigger" logic took 3x longer to get right than the actual AI response.
Can I assign job titles to your AI? Or does it automatically detect the job title in Slack and then adapt to the person and their specific work? It also has memory, right?
Hi everyone! I'm Mateusz and I'm leading Jared on the tech side. 💻
We built Jared to do any task, be social, form his own opinions, understand people and be proactive.
It's not a tool. It's a partner that takes responsibility for his job, gathers input from people in your org if needed, delivers the job and maintains it - all without extra setup. He's built that way.
I will be active on PH today to answer any questions you may have :))