three.ws / IBM / Identity Firewall
Live demo · Granite embeddings + Guardian
IBM watsonx · real inference, no mock path

The Identity Firewall
for AI agents.

Every three.ws agent holds a wallet and earns on-chain reputation — so impersonating a trusted one is a real attack. Before an identity is born, IBM Granite embeddings cosine-compare it against every public agent to catch look-alikes a name match would miss, and IBM Granite Guardian screens the name, bio and persona for harmful content. Try to clone an agent below.

Propose an identity

A name and a description are embedded and screened in real time.
0 / 500

Granite verdict

Embedding distance + Guardian content screen.
Enter a name and description, then run the check.
·
Identity uniqueness

    How the firewall works

    01

    Embed with Granite

    The candidate's name + bio are embedded on watsonx.ai with granite-embedding-278m — the same vectors that power the Agent Galaxy.

    02

    Compare semantically

    Cosine similarity against every public agent surfaces look-alikes a plain name match misses. Above ~93% to another owner's agent reads as impersonation.

    03

    Screen with Guardian

    Granite Guardian classifies the identity for harm, social bias and sexual content before it can ever represent the platform.

    This is the exact gate that runs on every POST /api/agents — a blocked identity is refused at creation. Explore the rest of three.ws on IBM watsonx.

    This is an independent demo three.ws built for developers to explore IBM Granite on watsonx.ai and build their own tools — not an official IBM partnership deliverable, not an IBM product, and not endorsed by IBM. IBM, watsonx, watsonx.ai, and Granite are trademarks of IBM.