Agentic Persona Generation with Critique-Refinement: An Industrial Evaluation
2026-06-08 • Software Engineering
Software Engineering
AI summaryⓘ
The authors present PerGent, a new method that uses large language models to create detailed user personas automatically. Unlike previous approaches that generate personas in one step, PerGent uses a loop where one AI creates a persona and another critiques and improves it repeatedly, using real data like interviews and job postings. They tested PerGent at a company called Kinaxis and found it made better personas than other methods and even matched expert-made personas while adding useful new information. The authors share insights from using PerGent in a real business setting.
personaslarge language modelsiterative refinementrequirements elicitationuser validationsoftware engineeringexpert evaluationautomationtextual data
Authors
Mohammad Hossein Amini, David Dewar, Shiva Nejati, Mehrdad Sabetzadeh
Abstract
Personas are widely used in software engineering to support requirements elicitation, design, and validation, but their manual creation is costly, time-consuming, and hard to scale. Recent LLM-based approaches automate persona generation from textual data; however, they typically rely on single-shot generation and subjective evaluations, limiting practical reliability. We present PerGent, an industry-grade method for persona generation built around an iterative critique-refinement loop. Specifically, PerGent uses a generator and a critic LLM agent, coordinated by an orchestrator, to iteratively refine personas using external resources such as interviews, surveys, and job postings through a critique-refinement loop with a user-defined maximum number of rounds. We deploy and evaluate PerGent in an industrial setting at Kinaxis, comparing it with three baselines, including one-shot methods. In an expert in-situ evaluation, PerGent achieved the highest expert approval rate (96.9%), exceeding all baselines. We further compare PerGent-generated personas with best-practice personas manually created by domain experts prior to the adoption of LLMs. Compared to baselines, PerGent reproduces a larger proportion of expert content while also contributing substantial new content beyond the pre-LLM personas. We conclude with lessons learned from deploying and evaluating PerGent at Kinaxis.