Replication Materials for "Multi-Agent AI as Ex-Ante Policy Intelligence: Assessing NYC's Rent Freeze Through Explainable Deliberative Simulation"

This deposit provides the complete set of outputs produced by the NYC-BX-RENT-26 simulation, executed on 25 February 2026 using the GobernAI multi-agent AI framework. The simulation assessed Mayor Zohran Mamdani's New York City housing agenda, specifically the proposal to freeze rents in approximately 960,000 stabilised apartments through a zero per cent Rent Guidelines Board adjustment, together with two simultaneous Day-1 executive orders (LIFT Task Force and SPEED Task Force). The simulation predates the Rent Guidelines Board vote by approximately four months. The deposit comprises 31 reports organised across the three modules of the GobernAI framework — FACTUM (sectoral deliberation), ÁGORA (citizen impact modelling), and POLITEIA (strategic communication) — together with the integrated master synthesis reports. All reports were generated in Spanish, the working language of the simulation; English summaries of the key findings are integrated in Section 5 of the associated paper. The deposit serves as replication material for: Correia, C. (2026). Multi-Agent AI as Ex-Ante Policy Intelligence: Assessing NYC's Rent Freeze Through Explainable Deliberative Simulation. Data & Policy [manuscript under review, DAP-2026-0172]. The literal prompts governing individual agents and the proprietary segmentation logic of the ÁGORA module are not included in this public deposit; their proprietary character is identified explicitly as a limitation in Section 7 of the associated paper. These materials remain available from the corresponding author upon written request subject to non-disclosure agreement.