Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study

2026-04-09

AI Summary

This study addresses the limitations of traditional CRM systems, which rely on manual optimization of static rules and struggle to sustain personalized marketing effectiveness over time without ongoing human intervention. Through an 11-month longitudinal case study, the authors propose a human–agent symbiotic model in which humans initially lead strategy formulation and content design, after which an autonomous agent-based system operates independently. Employing a fixed component library and longitudinal A/B testing, the research demonstrates that the human-led phase significantly boosts user engagement metrics, while the subsequent fully autonomous phase continues to maintain positive effects. These findings empirically validate the capacity of agent-based systems to sustain marketing performance over the long term without continuous human oversight, offering robust evidence for the viability and sustainability of human–agent collaboration in personalized marketing.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Sustainability of Web economics

Abstract

In consumer applications, Customer Relationship Management (CRM) has traditionally relied on the manual optimisation of static, rule-based messaging strategies. While adaptive and autonomous learning systems offer the promise of scalable personalisation, it remains unclear to what extent ``human-in-the-loop''oversight is required to sustain performance uplift over time. This paper presents a longitudinal case study analysing a real-world consumer application that leverages agentic infrastructure to personalise marketing messaging for a large-scale user base over an 11-month period. We compare two distinct periods: an active phase where marketers directly curated content, audiences, and strategies -- followed immediately by a passive phase where agents operated autonomously from a fixed library of components. Our results demonstrate that whilst active human management generates the highest relative lift in engagement metrics, the autonomous agents successfully sustained a positive lift during the passive period. These findings suggest a symbiotic model where human intervention drives strategic initialisation and discovery, yet autonomous agents can ensure the scalable retention and preservation of performance gains.

Problem

• agentic personalisation
• human-in-the-loop
• marketing personalisation
• sustained performance
• autonomous agents

Innovation

• agentic personalisation
• autonomous marketing agents
• human-in-the-loop
• longitudinal case study
• scalable personalisation