Launched this week
Hyper: Self-driving Company Brain
Turn your AI agents from interns to veterans
110 followers
Turn your AI agents from interns to veterans
110 followers
Hyper is the company brain that learns everything about your company (Docs, Slack, Email, Calendar, etc) then plugs into your AI skills & agents & automations so they go from forgetful interns into seasoned veterans that accomplish tasks. It helps them drafts emails in your voice, reads your contracts, triages your tickets, and preps you for every meeting, because it knows everything everyone at your company knows. Give it a spin from our website!
Hyper
Hey PH 👋,
Hyper cofounder here. My cofounder Kanyes and I have been (best friends and) building together for last decade. We’ve been power users of nearly all the second brain / tool-for-thought tools as students back in 2017, then later tried fine-tuning GPT-2 in Kanyes’s garage back in 2020 to build an AI that knew everything about us — our taste, how we work, what we believe in, etc. and have that AI automate work that we found tedious (like doing problem sets, yuck). We were obviously 5 years too early.
After college, we joined Matic to build robots, and we again felt this pain but in a real company that needed to ship real products. We saw information constantly fall through the cracks and tribal knowledge lost when key people left the company. We watched people trying their best to prevent this by being disciplined with writing docs or posting slack threads, and eventually we became those people. Then in 2023 when the world shifted to AI agents, we realized that even thought we’ve hacked “good enough” solutions together for human workers, our AI workers still remain dumb!
They’re as powerful as executives but have the context of a day-one intern.
So we both quit our jobs and decided to go solve this properly. Today, I’m excited to share that you can download and start using Hyper directly from our website! We're deeply grateful to be able to deliver world class software to the dreamers and pirates like us. Hyper has already sped up our AI automations significantly (drafting emails that has all our company knowledge and writes like me!) and we're relentless about fighting hard for the world-bending teams that want to move extraordinarily fast.
@_shalinshah_ The company brain positioning is strong. alot of Ai agents fail because they don’t know the company context.
Does Hyper work better as a shared company knowledge layer? or as a personal assistant for each team member?
Hyper
@dmitrii_volosatov Thanks for the note, and yes right now we support both onboarding as an entire team as well as onboarding as an individual in a team. Both use cases are well supported. We don't currently work for a purely personal use case that's purely outside of work however. Out of curiosity, which one would you like to use it as?
The support ticket triage use case is probably the most immediately valuable. That's a task with clear ground truth (was the triage correct?) and high volume, which means you can measure improvement fast. The harder version of that problem is when the institutional knowledge needed for correct triage lives in a decision someone made 18 months ago in a Slack thread that no one bookmarked. Curious whether Hyper indexes Slack history retroactively on setup, or whether it only captures context going forward from the point of connection. that distinction would significantly change the time-to-value for new customers.
Hyper
@binu_george That's great feedback, but yes Hyper goes back and indexes Slack history (and as a matter of fact all connectors like Gmail, Drive, Notion, etc) retroactively to collect the entire history of what has happened in the company. Once connected though, it's "live" in the sense that on every new message Hyper's agents read and understand how that fits into the graph of all previous knowledge. And then on the point about support ticket triaging, we definitely agree that it's a high utility use case and one that we're actively working to go tackle!
The company-brain framing is strong because it names the real bottleneck with agents: they can act, but they usually do not know what the company has already learned.
One thing I’d want to see very clearly in a product like this is how Hyper separates shared company truth from personal working style. “We always position the product this way” and “Shalin tends to write emails this way” are both useful, but they should probably age, conflict, and get overridden differently.
If the system can show source trails and confidence for those two layers separately, it would make the voice/email use cases much more trustworthy.
Hyper
@jim_jeffers Great insight here. Hyper's architecture lets us extract all of thse angles, and trace its conclusions for each question back to its source. It's a core part of the real workflows people expect a brain to be able to solve, and we're trying to build a great experience around that.
Hyper
@rafael_romano Not yet but definitely in the works!
Wudpecker
This is super cool. Congrats on the launch guys!!
Hyper
@hai_ta1 thanks Hai!
Superset
Congrats on the launch!🚀
Hyper
@avi_peltz thanks Avi!