KRContact

Control and prove every enterprise AI action

Patty connects models, GPU infrastructure, and agents through one governance layer.

Contact usExplore technology
PattyExecution receipt
Evidence sealed
Execution ID
EX-02481
Executed at
2026-08-26 · 09:42:18 KST
Approved scope
production / configuration.write

Before AI can act inside an enterprise

Example action

Change a production environment configuration

  1. AI proposes

    The AI first states the change and its expected impact.

  2. People approve

    An authorized owner reviews the scope and risk.

  3. Systems execute

    Only the approved change runs in an isolated environment.

  4. Evidence remains

    Who did what, why, and with which result stays verifiable.

Verification statusEvidence sealed

The approval scope, execution result, and provenance remain in one verifiable record.

Cryptographic sealDARI · COSE-SIGN1

What AI is authorized to do matters more than what it can do

Patty separates proposal, approval, execution, and recordkeeping. A conversation is not authority, and a log is not verifiable evidence.

Propose

AI proposes the next action within the work context and policy boundary.

intent captured

Approve

An authorized person reviews the scope and impact before granting authority.

authority verified

Execute

The control kernel runs only approved work through isolated tools and infrastructure.

policy enforced

Record

Action, rationale, result, and provenance remain as a verifiable receipt.

evidence sealed

One control layer, five execution surfaces

Each product handles different work while managing identity, approval, execution, and evidence through the same operating model.

Featured product
01Propose02Approve03Execute04Record
Patty Code

A controllable coding agent that converses in your terminal, runs tools, and stays with the task until it’s done.

Control planePCCP

Making every AI action visible, governed, and provable

Work executionErgazo

The AI-native work execution platform

Collaboration surfaceCrew

The workspace where humans and AI agents work side by side

Organization operationsPilot

The control plane for operating an AI-agent organization

Technical depth organized as verification paths

Inspect the mechanisms we build across model training, distributed inference, and agent execution.

Models & training

6 capabilities

Evaluation & benchmarks

2 capabilities

Inference & infrastructure

6 capabilities

Applied AI

7 capabilities
All capabilities · 21 capabilities

We publish only verifiable claims

Measurements include conditions. Protocol claims link to specifications and conformance evidence. Unverified customers, certifications, and awards are excluded.

Agent browser finished-path measurementDebug build · semantic snapshot and governed cycle~14–16 / <25 msDARI protocolOpen specification with conformance testingApache-2.0 / v1.0Deployment profiles including sovereign and closed-networkPCCP deployment architecture3 profiles

Security and governance are operating architecture

Policy cannot remain in documents. Identity, data boundaries, approval, execution, and audit must work together at runtime.

Enterprise review questionWhat evidence and provenance remain after execution?Control outcomeAudit & Provenance

DARI receipts, line-level human/AI provenance linked to Git, encrypted trace vaults.

Enterprise review questionWhere is policy enforced before infrastructure is contacted?Control outcomeLLM Gateway & Policy Engine

Server-side model authority; per-request policy decisions before infra contact.

Enterprise review questionWhere do data and models execute?Control outcomeData Residency & Sovereignty

Korean data residency; closed-network profiles; residency-honoring region failover.

Enterprise review questionWho can authorize an AI action, and within what scope?Control outcomeIdentity & Access

Human/AI dual identity model; COSE-signed credentials; scoped agent privileges.

Complete control coverage

We build systems, not model wrappers

From Korean modeling and GPU serving to agent runtimes and organizational control, Patty builds the full enterprise AI system.

About Patty

Start an enterprise evaluation

Review product adoption, technical validation, security requirements, and sovereign deployment with our team.

Contact us