Sumsub launched an AI agent integration that allows systems such as ChatGPT and Claude to configure compliance and identity verification environments directly from anti-money laundering policies. The company said the integration eliminates much of the manual work traditionally required to build onboarding and risk management workflows. Sumsub described the release as the first verification platform to provide AI agents with access not only to operational tasks but also to the configuration layer of a compliance system, based on its implementation of Model Context Protocol and a collection of AI agent skills that translate regulatory requirements into live platform settings.
Sumsub Enables Policy-to-Configuration Automation
Compliance teams can upload anti-money laundering policies, regulatory requirements, or internal governance documents and ask an AI agent to build the corresponding configuration within the platform. The system interprets country-specific risk classifications, scoring models, onboarding requirements, verification levels, questionnaires, and conditional workflows before applying those settings to a live environment. Sumsub said this process, which historically required compliance specialists, implementation teams, consultants, or solution architects to manually interpret policy documents and translate them into technical configurations, can now be completed in minutes rather than days or weeks.
Andrew Novoselsky, Chief Product Officer at Sumsub, said: "Setting up a compliance workflow has always required significant manual effort, and updating it when regulations change requires even more. Our Agentic experience changes that by connecting an AI agent directly to the configuration layer of the platform — a team can take their AML policy, hand it to an AI agent, and have their full environment built automatically. That is a fundamentally different category of capability from what has been available in this space."
AI Agents Handle Technical Deployment and Ongoing Operations
Sumsub outlined three primary use cases for the functionality. The first is policy-to-configuration automation, where teams upload compliance documents and allow AI agents to determine what verification requirements, risk assessments, onboarding controls, and monitoring processes should be implemented. The second involves technical deployment, with AI agents handling portions of the technical integration process by generating code and embedding verification requirements directly into onboarding journeys. The third area focuses on ongoing compliance operations, where organizations use AI agents to review applicants, generate analytics, create verification links, and adapt workflows in response to regulatory changes.
Model-Agnostic Architecture Supports Multiple AI Providers
Sumsub said the integration is model-agnostic and designed to work with multiple AI providers rather than being tied to a single large language model. The company published its AI agent skills through an open-source repository, allowing organizations to deploy them within existing environments. The platform supports ChatGPT, Claude, and other systems, positioning itself as infrastructure that can operate across a variety of AI ecosystems.
Governance Controls Manage AI Agent Permissions
Access to the Model Context Protocol integration is managed through separate permissions, allowing organizations to control what actions AI agents can perform. Sensitive operations are executed within isolated sandbox environments, and configuration changes remain subject to human review and approval. Sumsub emphasized that governance and access controls are built into the system to maintain accountability and auditability in regulated industries.
FAQ
What did Sumsub launch for compliance automation?
Sumsub launched an AI agent integration that allows systems such as ChatGPT and Claude to configure compliance and identity verification environments directly from anti-money laundering policies, eliminating manual workflow building.
How does Sumsub's AI agent integration handle compliance policies?
Compliance teams can upload AML policies or regulatory documents, and the AI agent interprets country-specific risk classifications, scoring models, onboarding requirements, and conditional workflows before applying those settings to a live environment.
What governance controls does Sumsub include in the AI integration?
Access to the integration is managed through separate permissions, sensitive operations run in isolated sandbox environments, and configuration changes remain subject to human review and approval.
