Next Article in Journal
Diagnosing Bias and Instability in LLM Evaluation: A Scalable Pairwise Meta-Evaluator
Previous Article in Journal
Electronic Voting Worldwide: The State of the Art
Previous Article in Special Issue
Business Logic Vulnerabilities in the Digital Era: A Detection Framework Using Artificial Intelligence
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

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

1
School of Computing and Engineering, University of Gloucestershire, The Park, Cheltenham GL50 2RH, UK
2
Independent Researcher, Hills Rd, Cambridge CB2 8PH, UK
3
Independent Researcher, 47645 College Dr, St Mary’s City, MD 20686, USA
4
Independent Researcher, 4616 Henry St, Pittsburgh, PA 15213, USA
*
Author to whom correspondence should be addressed.
Information 2025, 16(8), 651; https://doi.org/10.3390/info16080651
Submission received: 31 May 2025 / Revised: 18 July 2025 / Accepted: 29 July 2025 / Published: 30 July 2025
(This article belongs to the Special Issue New Information Communication Technologies in the Digital Era)

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.
Keywords: agentic AI systems; AI alignment; personalization; ethical guardrails; superego agent; constitutional AI; real-time compliance; value alignment; AI safety; AI ethics agentic AI systems; AI alignment; personalization; ethical guardrails; superego agent; constitutional AI; real-time compliance; value alignment; AI safety; AI ethics

Share and Cite

MDPI and ACS Style

Watson, N.; Amer, A.; Harris, E.; Ravindra, P.; Zhang, S. Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values. Information 2025, 16, 651. https://doi.org/10.3390/info16080651

AMA Style

Watson N, Amer A, Harris E, Ravindra P, Zhang S. Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values. Information. 2025; 16(8):651. https://doi.org/10.3390/info16080651

Chicago/Turabian Style

Watson, Nell, Ahmed Amer, Evan Harris, Preeti Ravindra, and Shujun Zhang. 2025. "Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values" Information 16, no. 8: 651. https://doi.org/10.3390/info16080651

APA Style

Watson, N., Amer, A., Harris, E., Ravindra, P., & Zhang, S. (2025). Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values. Information, 16(8), 651. https://doi.org/10.3390/info16080651

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop