Prompting Democracy: A Field Experiment on Generative AI and Participatory Politics

Last registered on October 02, 2026

View Trial History

Pre-Trial

Trial Information

General Information

Title

Prompting Democracy: A Field Experiment on Generative AI and Participatory Politics

RCT ID

AEARCTR-0018990

Initial registration date

June 23, 2026

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published

June 29, 2026, 8:32 AM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Last updated

October 02, 2026, 7:04 AM EDT

Last updated is the most recent time when changes to the trial's registration were published.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Name

Saul Martinez Castellanos

Affiliation

European University Institute

Contact Primary Investigator

Other Primary Investigator(s)

PI Name

Vincenzo Galasso

PI Affiliation

Bocconi

Contact Investigator

PI Name

Matteo Giugovaz

PI Affiliation

Universitat Pompeu Fabra

Contact Investigator

PI Name

Matteo Muntoni

PI Affiliation

European University Institute

Contact Investigator

PI Name

Tommaso Nannicini

PI Affiliation

European University Institute

Contact Investigator

Additional Trial Information

Status

In development

Start date

2026-04-11

End date

2027-01-31

Keywords

Electoral

Additional Keywords

AI, Political economy

JEL code(s)

Secondary IDs

Prior work

This trial does not extend or rely on any prior RCTs.

Abstract

Generative AI can now be used to help citizens move from a mere social concern to a concrete, structured policy proposal. This creates a question for participatory politics: what changes when part of the work of generating a proposal can be supported by AI? AI may matter on the formulation side, by shaping the clarity, structure, feasibility, and appeal of the proposals citizens formulate. It may also matter on the reception side, by shaping how other citizens react to those proposals, especially when they know that AI was involved in producing them.

We study these questions in the context of Le Primarie delle Idee, an Italian participatory platform launched in April 2026. The platform allows registered users to develop policy proposals either with the support of a generative AI assistant or on their own. In the AI-assisted route, users interact with a multi-turn conversational facilitator based on a generative AI model, called AIdea and designed to help them turn an initial concern into a more concrete proposal. In the self-authored route, users draft their proposal directly using a template. Once submitted, proposals can be read, discussed, supported, and voted on by the user community.

The experiment therefore studies both the formulation and reception of policy proposals in an online political platform. On the formulation side, we ask whether AI-assisted proposals differ from self-authored proposals in quality, structure, and electoral appeal. Among users who receive AI assistance, we also ask whether the design of that assistance matters, by comparing a procedural, scaffolded version of the assistant with a more open-ended version and measuring effects on users' policy-reasoning skills. On the reception side, we ask whether disclosure matters: do users engage differently with a proposal when they are told whether it was AI-assisted or self-authored?

We answer these questions through three main randomizations: one over the proposal-development route and one over whether proposals display an authorship tag indicating that they were either AI-assisted or self-authored, plus a nested randomization over the version of the assistant assigned to users and a further randomization in the final voting voting of the platform.

External Link(s)

Live platform

Registration Citation

Citation

Galasso, Vincenzo et al. 2026. "Prompting Democracy: A Field Experiment on Generative AI and Participatory Politics." AEA RCT Registry. October 02. https://doi.org/10.1257/rct.18990-2.2

Sponsors & Partners

Experimental Details

Interventions

Intervention(s)

The platform offers two routes for developing a policy proposal: an AI-assisted route, in which users develop their proposal through a multi-turn conversation with a generative AI facilitator, and a self-authored route, in which users draft their proposal directly using a template. Within the AI-assisted route, the facilitator operates in one of two modes: a procedural, scaffolded style that guides the conversation through a structured sequence, or an open-ended style without a fixed sequence. Separately, the platform interface either displays or does not display a tag disclosing whether each proposal was AI-assisted or self-authored. Users are randomized over the proposal-development route, over the facilitator mode, and over whether the authorship-disclosure tag is shown.

Intervention Start Date

2026-06-25

Intervention End Date

2026-10-05

Primary Outcomes

Primary Outcomes (end points)

The primary outcomes, grouped by randomization, are:

1. Proposal-development route: proposal quality; platform engagement, including the ranking score and top-50 status; submission and proposal count; thematic and semantic dispersion; within-user proposal diversity; and linguistic polarization.
2. Facilitator mode: proposal quality; conversation length and how it concludes; coverage of four complexity components; and user initiative.
3. Authorship-disclosure tag: user-level and user–proposal engagement through supports, comments, event participation and sharing.
4. Final-vote advice: submission of any ballot; inclusion of a pillar among submitted ranked choices; and opening a pillar’s description.

Primary and secondary outcomes are specified in the updated pre-analysis plan.

Primary Outcomes (explanation)

Proposal quality is a 0–12 score covering complexity, language clarity and voter appeal, each comprising four binary criteria. Three independent LLM evaluators code each criterion; majority codes are summed into dimension and total scores. Platform engagement uses logged supports, comments, event participations and shares. The platform ranking score assigns three points per support, two per event participation and one per comment.

Dispersion and within-user diversity use CAP topic differences and pairwise semantic distances. Linguistic polarization indicates the presence of any of five prespecified hostile or polarizing language features. Secondary ideological extremism measures distance from the CHES scale midpoint, using the average ideological position of parties coded as supporting the proposal.

Conversation coverage scores four complexity components: trade-offs, implementation constraints, second-order effects and uncertainty. User initiative is the share of covered components first raised by the user, undefined when none is covered. Post-generation editing is a descriptive diagnostic measuring any modification and semantic distance between generated and submitted proposals. Final-vote outcomes are binary indicators of ballot submission, pillar selection and information gathering, coded zero when no corresponding action is recorded. Detailed definitions and aggregation procedures appear in the updated pre-analysis plan.

Secondary Outcomes

Secondary Outcomes (end points)

Secondary outcomes, by randomization:

1. Proposal-development route: self-assessed expected impact and approval; similarity to Italian political and programmatic texts; ideological extremism and related statistics; within-topic semantic dispersion; event organization; and logins per active week.
2. Facilitator mode: satisfaction with the AI-assisted experience and an open-text report of what the assistant was most useful for, collected from AI users at submission.
3. Authorship-disclosure tag: whether users open or submit proposals through the AI-assisted or self-authored route.
4. Final-vote advice: number of ranked choices submitted; submission of second- and third-place choices; placement of individual pillars first, second or third; and opening proposals linked to a pillar.

For the proposal-development route, instrumental-variable estimates supplement the primary intent-to-treat analysis for user-level outcomes defined for all assigned participants. IV analyses conditional on submission are exploratory. Post-generation editing is reported as a descriptive diagnostic.

Secondary Outcomes (explanation)

The engagement index is logins per active week. Mobilization indicates organizing at least one online or in-person event linked to a proposal. Expected impact, approval and AI satisfaction use fixed-response survey items at submission; the usefulness report is free text.

Political-text similarity is assessed by LLM evaluators against Italian party programs and policy initiatives. Ideological extremism is the distance from the CHES scale midpoint of the average position of parties coded as supporting a proposal. Related statistics include average ideological position and the shares supported by all or no parties. Within-topic dispersion averages semantic distances within treatment-arm and CAP-topic cells containing at least five proposals.

Route-choice outcomes indicate opening or submitting through each route. Final-vote outcomes count ranked choices (0–3) and indicate second-/third-place choices, each pillar’s rank-specific placement, and opening linked proposals. Voting and browsing indicators equal zero when no corresponding action occurs. Detailed definitions appear in the updated pre-analysis plan.

Experimental Design

During June 25–September 20, 2026, users received three orthogonal assignments at the individual level: AI-assisted versus self-authored proposal development (R1); procedural versus open-ended AI facilitation (R1.1); and visible versus hidden authorship tags (R2). Facilitator mode was assigned to all users and applied whenever they used AI. Existing users were randomized within registration-phase strata; subsequent registrants were assigned through a fixed eight-registration cycle. Route compliance was observed but not enforced.

A separate randomization (R3) concerns the October 2–4 final vote, in which registered users can rank up to three of twelve policy pillars. Eligible users receive no advice, comfort advice or outside-comfort-zone advice. Eligibility requires registration and qualifying activity before the September 20 closure, plus nonempty comfort and outside-comfort sets. Assignment occurs within eight prior-activity strata, with rerandomization to balance pillar-set membership. AI-framed recommendations are drawn uniformly from pillars linked to users’ prior activity or from the remaining pillars.

Analysis prioritizes intent-to-treat estimates using prespecified samples; proposal outcomes conditional on submission are interpreted with selection caveats. Full design and analysis details appear in the updated pre-analysis plan.

Experimental Design Details

Not available

Randomization Method

ssignment is implemented by computer. For the proposal phase (June 25–September 20, 2026), the research team randomized previously registered users within registration-phase strata, balancing the eight R1 × R1.1 × R2 cells. Subsequent registrants were assigned through a deterministic eight-registration cycle preserving the same proportions. These assignments are at the user level and remain fixed throughout the proposal phase.

R3 is randomized separately at the user level within eight prior-activity strata, targeting equal allocation to control, comfort advice and outside-comfort-zone advice. Candidate assignments are redrawn until each stratum meets its prespecified pillar-membership balance criterion

Randomization Unit

Individual (user). All four randomized dimensions, proposal-development route, AI-facilitator mode, authorship-disclosure tag and voting advice, are assigned at the individual user level. For users registered before the experimental start, randomization is stratified by registration phase. Note: the realized sample size is not yet known, as it depends on platform adoption over the experimental window; the figures below are planned targets derived from ex-ante power calculations and will be updated once data is received.

Was the treatment clustered?

Yes

Experiment Characteristics

Sample size: planned number of clusters

The realized number is not yet known, as it depends on platform adoption over the experimental window and data not yet received.

Sample size: planned number of observations

The realized number of individuals, proposals, and conversations is not yet known, as it depends on platform adoption over the experimental window and data not yet received.

Sample size (or number of clusters) by treatment arms

The three randomizations are orthogonal, so each user contributes to all three contrasts simultaneously; the arm sizes above are not additive across randomizations. Realized arm sizes are not yet known and depend on platform adoption; these are planned targets and will be updated once the realized sample data is received.

Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Ex ante calculations assume significance α = 0.05, power = 0.80 and a minimum detectable effect of 0.20 standard deviations. Repeated-proposal calculations assume two proposals per individual and within-individual correlation ρ = 0.50; R1 additionally assumes a first-stage coefficient κ = 0.80. Per-arm planning requirements are approximately 614 individuals for R1 participant-level analyses and 460 for proposal-level analyses; 393 AI users for R1.1 primary first-conversation and participant-level analyses, and 295 for proposal-level robustness analyses; and 393 individuals for R2 participant-level analyses. For R3, user-level comparisons require approximately 393 users per arm, or 1,179 across three arms. This also provides an equal-variance benchmark for pillar-specific advice-versus-control comparisons. Under common variances and uncorrelated control-set averages, the pillar-specific comfort-versus-outside-comfort contrast requires approximately 785 users per arm. Actual power depends on sample size, outcome variances and, for pillar-specific comparisons, the variances and covariance of weighted control-set averages. These benchmarks concern unadjusted tests; multiple-testing adjustments affect power.

Supporting Documents and Materials