Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values

TL;DR

This paper presents a personalized oversight mechanism for agentic AI, called the 'superego', which dynamically aligns AI behavior with diverse human values and safety standards, significantly reducing harmful outputs.

Contribution

Introduces a novel 'superego' system that personalizes AI alignment through user-defined 'Creed Constitutions' and real-time compliance enforcement, enhancing safety and value alignment.

Findings

Achieves up to 98.3% harm score reduction in benchmarks.

Attains 100% refusal rate for harmful outputs with tested models.

Effectively integrates with third-party models via Model Context Protocol.

Abstract

Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values, complex safety requirements, and specific compliance needs. Existing alignment methodologies often falter when faced with the complex task of providing personalized context without inducing confabulation or operational inefficiencies. This paper introduces a novel solution: a 'superego' agent, designed as a personalized oversight mechanism for agentic AI. This system dynamically steers AI planning by referencing user-selected 'Creed Constitutions' encapsulating diverse rule sets -- with adjustable adherence levels to fit non-negotiable values. A real-time compliance enforcer validates plans against these constitutions and a universal ethical floor before execution. We present a functional system, including a demonstration interface with a prototypical constitution-sharing portal, and successful integration with third-party models via the Model Context Protocol (MCP). Comprehensive benchmark evaluations (HarmBench, AgentHarm) demonstrate that our Superego agent dramatically reduces harmful outputs -- achieving up to a 98.3% harm score reduction and near-perfect refusal rates (e.g., 100% with Claude Sonnet 4 on AgentHarm's harmful set) for leading LLMs like Gemini 2.5 Flash and GPT-4o. This approach substantially simplifies personalized AI alignment, rendering agentic systems more reliably attuned to individual and cultural contexts, while also enabling substantial safety improvements. An overview on this research with examples is available at https://superego.creed.space.