Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJun 22, 2026Santa Cruz - Bolivia

DDRR-Trust: Auditor de Gobernanza e Inteligencia Artificial para la Tokenización Inmobiliaria

Facundo Espinoza Rojas, Gabriel Mamani Sandoval, David Salas Arriaga · Team Llajwitas Tech

Submitted to Global South AI Safety Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: DDRR-Trust: Auditor de Gobernanza e Inteligencia Artificial para la Tokenización Inmobiliaria

Open in a new tab (opens in new tab)
Share

DDRR-Trust es una herramienta innovadora de Gobernanza de Inteligencia Artificial diseñada para proteger a los inversores en el emergente mercado de la tokenización inmobiliaria en Bolivia. El problema fundamental radica en que la transferencia de un activo digital en la blockchain no otorga derechos legales de propiedad frente a terceros; la normativa boliviana exige estrictamente una escritura pública inscrita en el Registro de Derechos Reales (DDRR). A esto se suma la obligatoriedad de contar con licencias operativas de la ASFI y registros en la UIF para la prevención del lavado de dinero.

Ante la desprotección del ciudadano común frente a estos vacíos tecnológicos y legales, nuestra solución actúa como un auditor preventivo automatizado. El sistema utiliza modelos de Procesamiento de Lenguaje Natural (NLP) para extraer y analizar simultáneamente las cláusulas de los contratos de tokenización y los datos registrales del Folio Real. A través de un intuitivo sistema de semáforo visual, DDRR-Trust clasifica el nivel de riesgo en tiempo real.

La aplicación advierte al instante si la estructura jurídica de la inversión es sólida y segura (Semáforo Verde), o si, por el contrario, existen promesas ilegales de transferencia exclusivamente *on-chain*, falta de permisos regulatorios, hipotecas no declaradas o riesgos tributarios ocultos vinculados al IMT o el IUE (Semáforo Rojo). De esta manera, el proyecto cierra la brecha entre la innovación descentralizada y las instituciones tradicionales, utilizando la IA para democratizar el acceso a la seguridad jurídica y proteger el patrimonio de las personas.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. cool idea, but I would have really liked to see a demo for it. I think you could have fed the manuscript to Claude Code and possibly have gotten a good MVP out of that

  2. Impact: I feel the project is not really about AI safety at all, but rather about using AI to solve a different problem, which I feel is not in the spirit of the hackathon. What I mean is that "AI safety," even broadly defined, is about managing the risks associated with the development and deployment of AI systems, whereas the project the authors are proposing is about managing the risks associated with DeFi technologies, using AI systems as the technique. AI is the tool here, not the subject. From the project itself I cannot assess its impact in that domain, and I hope it is impactful (AI safety is not the only thing that matters in this world) but it is out of scope of the competition.

    Execution: The paper says it applied a "Review of Bolivian real-estate property law," an "Analysis of Fintech and virtual-asset regulation," an "Investigation of risks associated with tokenization," and "Case studies and international models," but I see only the generic bullet points associated with each, with no deeper description. Regarding DDRR-Trust, the authors claim to have built this system, but no details are given in the paper, there is no link to the prototype, and there are no actual results beyond the few bullet points that summarize them. Therefore, it is impossible to evaluate the quality of the work from the paper as given.

    Presentation: The paper reads as a summary of work that is never actually shown to the reader, and the writing looks AI-generated. It describes a finished system in the present tense while showing only hypothetical examples rather than real outputs, so it claims more completion than it demonstrates. At no point can I see the work itself in order to evaluate the proposal.

    In this review I may seem harsh, and I do not want to discourage the authors of what may be great future work. After all, the problem is real, so there is the market for a solution. However, I am judging what is written in this paper, and I would rather give honest feedback in a low-stakes setting like a hackathon than have the authors receive similar feedback later if they intend to develop a product from it. The work, as presented, could be rejected purely on the grounds of not showing what was actually done, and in the future the authors should take care to present their work better for the audience.

    Read full reviewShow less

Cite this project

@misc{rojas2026ddrrtrust,
  title = {{DDRR-Trust: Auditor de Gobernanza e Inteligencia Artificial para la Tokenización Inmobiliaria}},
  author = {Facundo Espinoza Rojas and Gabriel Mamani Sandoval and David Salas Arriaga},
  year = {2026},
  month = jun,
  note = {Submitted to Global South AI Safety Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/ddrrtrust-auditor-de-gobernanza-e-inteligencia-artificial-para-la-tokenizacin-inmobiliaria-0oi0}},
  url = {https://apartresearch.com/sprints/projects/ddrrtrust-auditor-de-gobernanza-e-inteligencia-artificial-para-la-tokenizacin-inmobiliaria-0oi0}
}

More from Global South AI Safety Hackathon

All 216 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026