Hey everyone! This is Paulina & Matthew from Agentic Fabriq.
TL;DR: Agentic Fabriq is Okta for agents. Fabriq ensures that employees can’t access data or do actions with agents that they themselves would not have permissions to do.
Our launch video: https://youtu.be/V4dTw58ZeTQ?si=ykoz3x06_fTgEXeK
The field of agentic AI is brand new, and everyone is rushing to build and ship their own agents. But there’s a critical gap appearing: how do you guarantee an agent can’t do more than the employee using it?
THE PROBLEM
AI is rewriting how work gets done, but most companies still can’t let every employee harness it with their own, permissioned data. The market is full of tools and agents, but the core organizational layer is missing. There’s no unified place to enforce per-user + least-privilege access, separate tenants, or audit what an agent did, with which user, and why, across all of your internal agents and tools.
Today, there’s only scattered solutions to this with identity and permission systems that were built for humans, not for agents acting as humans. Agentic Fabriq solves this issue for the first time by giving IT and admins a way to ensure their agents are always constrained to the exact permissions of the employee asking - no more, no less.
OUR SOLUTION
Agentic Fabriq is the secure fabric that simplifies data permissioning for all your agents, tools, and employees. We handle the auth & integration so IT & admin can manage employee permissions, agent permissions per employee, and tool connections. We’ve solved the security and identity hurdles so you can connect to a tool in minutes and personalize what your agents can do and access per user.
On Fabriq,
register a tool connection,
register your own AI/agents,
and manage your entire organization
we made it as simple as that.
Agentic Fabriq provides users with:
- per-user connections: connect your own account to approved tools - no shared creds
- org-wide controls: define what internal agents/apps can access & which employees can use them
- least-privilege by default: access is scoped & revocable, with centralized policy
- full visibility: every action is logged for audit & compliance
- prebuilt connectors: add tools fast without rebuilding auth & permissions each time
This allows teams to make the most use of AI with exactly the data they’re allowed to use - safely, auditable & at scale.
OUR ASK
If you or anyone you know would like to be early adopters of Fabriq, book a call with us or send us an email!
CONTACT
- email us: founders@agenticfabriq.com
- book a meeting: https://calendly.com/paulinaxu/agentic-fabriq-meeting
- website: https://www.agenticfabriq.com
TEAM
Paulina and Matthew met @ MIT admit weekend and have been friends since. They dropped out before their second year to work on Agentic Fabriq
Paulina was studying AI + Physics and doing CS/ML research at MIT Kavli Institute, MIT Haystack Observatory, and INAF Padua.
Matthew was studying AI + Math and doing CS/Econ research at MIT Futuretech Lab and Computational Biology research at MIT CSAIL.