Breaking Down Barriers Assistant: Leveraging AI to Conduct Policy Analyses with Complex Data

Ujjwal Kc () and Jan Kabatek ()
Additional contact information
Ujjwal Kc: Melbourne Institute of Applied Economic and Social Research, https://findanexpert.unimelb.edu.au/profile/1026287-ujjwal-kc
Jan Kabatek: Melbourne Institute of Applied Economic and Social Research, https://findanexpert.unimelb.edu.au/profile/761978-jan-kabatek

Melbourne Institute Working Paper Series from Melbourne Institute of Applied Economic and Social Research, The University of Melbourne

Abstract: Evidence-based policy design increasingly relies on integrated administrative data, yet access to and effective use of these data remain constrained by technical and institutional barriers. This paper introduces the Breaking Down Barriers Assistant, an AI-powered analytical platform designed to democratise access to complex, linked administrative datasets for policy analysis. The system enables users to query secure, pre-aggregated Australian administrative and survey data using natural language and supports the full policy research cycle through three integrated tools: variable discovery, visual analytics, and automated reporting. Methodologically, the BDB Assistant combines Retrieval-Augmented Generation with controlled code generation and execution, ensuring that all analytical outputs are grounded in verified metadata, auditable Python code, and human-in-the-loop validation. Using benchmark comparisons with established platforms such as YouthView and the BDB Community Profiles, we demonstrate that the Assistant can accurately reproduce complex spatial and longitudinal policy analyses that traditionally require advanced technical expertise. The findings show that the system substantially reduces time-to-insight while maintaining strict standards of accuracy, transparency, and privacy. The BDB Assistant illustrates how responsibly governed generative AI can expand analytical capacity within government and the social sector, supporting more timely, rigorous, and locally targeted evidence-based policymaking.

Keywords: Evidence-based policymaking; Artificial Intelligence; Generative AI; Large Language Models; AI-Assistants (search for similar items in EconPapers)
Pages: 29pp
New Economics Papers: this item is included in nep-ain
References: Add references at CitEc
Citations:

Downloads: (external link)
https://melbourneinstitute.unimelb.edu.au/__data/a ... 546756/wp2026n04.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:iae:iaewps:wp2026n04

Access Statistics for this paper

More papers in Melbourne Institute Working Paper Series from Melbourne Institute of Applied Economic and Social Research, The University of Melbourne Melbourne Institute of Applied Economic and Social Research, The University of Melbourne, Victoria 3010 Australia. Contact information at EDIRC.
Bibliographic data for series maintained by Sheri Carnegie ().