TLDR: Performativ has launched Custom AI Agents and an AgentKit Builder, enabling financial institutions to design, govern, and deploy AI solutions securely and compliantly within their existing operations. This initiative aims to integrate intelligent automation into banking, capital markets, and asset management while ensuring regulatory oversight and auditability.
COPENHAGEN, Denmark – November 5, 2025 – Performativ, a leading provider of operating backbones for modern wealth enterprises, today announced the unveiling of its Custom AI Agents and AgentKit Builder. These new capabilities are specifically designed to empower financial institutions – including banks, capital markets firms, and asset managers – to integrate artificial intelligence into their core operations with an unprecedented focus on safety, compliance, and control.
The AgentKit Builder allows financial entities to create and deploy bespoke AI agents tailored to their specific needs. These custom agents are built upon the OpenAI AgentKit foundation and leverage Performativ’s proprietary Model Context Protocol (MCP) architecture. This robust framework ensures that AI deployments maintain full regulatory oversight, auditability, and control within the institutions’ existing workflows and enterprise infrastructure.
Albert Geisler Fox, CEO of Performativ, emphasized the critical importance of governance in AI adoption within the financial sector. “AI must operate under the same governance frameworks as the rest of the enterprise,” stated Fox. “With Custom Agents, institutions can now deploy intelligent automation that is both production-ready and compliant by design. Every action is permissioned, explainable, and accountable.”
Performativ’s Custom Agents introduce a sophisticated, structured framework for enterprise AI governance. Each agent operates through an MCP user, adhering to least-privilege and role-based access controls. This ensures that all data access, processing, and actions remain strictly within approved boundaries. Furthermore, all agent operations – including inputs, tool calls, parameters, and outputs – are meticulously logged and versioned, creating a comprehensive chain of evidence suitable for rigorous regulatory review. Administrators are also able to define and enforce policy guardrails, dictating when an agent can run, what data it can read or write, and under which approvals. Structured output schemas further guarantee predictability and traceability, facilitating the deployment of AI-driven workflows that meet stringent internal model governance requirements.
Illustrative applications of these new tools include the development of virtual analysts capable of classifying liquidity needs, checking policy guardrails, and generating compliant investment proposals, all within a governed and auditable framework.
Also Read:
- Zenity Unveils Real-Time Security for OpenAI AgentKit-Powered AI Agents
- GenerativeX Unveils ExelenceAI: An AI Agent Revolutionizing Financial Modeling in Excel
Custom Agents and the AgentKit Builder are currently available in a controlled preview for interested financial institutions. Performativ plans to release additional documentation and and support in the coming weeks. The company, known for unifying custody, trading, and client relationship data, also powers analytics and compliance, enabling controlled AI deployment under enterprise governance to modernize technology stacks and improve advisor productivity and client outcomes.
