Illia Polosukhin

Yeah, so Ironclaw is built on this idea of defense in depth.

And so, yes, on credential side, so all credentials are fully encrypted and they're attached to a specific policy.

So let's say you give it your Google account credentials.

it will not let anything else in the system to send its credentials to another domain that's not Google, googleapi.com, google.com.

It's locked in a vault and vault checks, yeah, vault checks how you use it before letting it out.

Okay.

So same for, for example, for cryptographic keys, you can actually attach a policy saying, hey, you can only, you know, use Aave and, you know, Morpho.

You can only, you know, whatever, spend $100 a day on unknown addresses, et cetera, et cetera.

So, and we're, you know, kind of designing how to, how to like write this.

We also, for any action that you do, we're working on kind of system where you can effectively describe kind of what effects in the world, right?

Like LLM can effectively analyze like, hey, you're planning to send a bunch of emails to people and tell them they're, you know, whatever, idiots.

Like you can design effectively a natural language policy as well that checks like, hey, is this actions independently of the context of how agent arrives to section is compliant with our organizational policy or your personal policy, right?

So like almost like values and like HR handbook type validation, right?

So you can have like different levels of validation.

The other side is everything is isolated into tools and tools are effectively, you can think of them as smart contracts, right?

They are running inside a VM.

We're using our WebAssembly VM that we use for near smart contracts, which we spent seven years effectively battle testing with, you know, billions of dollars.

And so we use that to isolate all of the tools, including the tools it builds itself.

So that tool itself cannot go in like rack your machine

or your system doing it.