Reitcircles: AI land registry parser pipeline

[GENERAL] Name and surname of main applicant

Reitcircles

[GENERAL] Email address of main applicant

info@reitcircles.com

Additional applicants

1. Tony Mönicke
2. Vinh Dang
3. Minh Vo
4. Giang Nguyen

[GENERAL] Please specify how many months you expect your project to last (from 2-12 months)

5

[GENERAL] Please indicate if your proposal has been auto-translated into English from another language.

No

[GENERAL] Does your project have any dependencies on other organizations, technical or otherwise?

No

[GENERAL] If YES, please describe what the dependency is and why you believe it is essential for your project’s delivery. If NO, please write “No dependencies.” .

No dependencies

[GENERAL] Will your project’s output/s be fully open source?

No

[GENERAL] If NO, please describe which outputs are not going to be open source. If YES, please write “Project will be fully open source.”

• We will open-source the model that will be trained.

[METADATA] Category of Proposal

RealFi

[METADATA] SDG rating

1. Reduced inequality : Now every individual can issue their own verification data via this platform that will ensure property rights globally.
2. Sustainable cities and communities : Now communities can use this platform to issue themselves NFT based on their asset requirements.
3. Decent work and economic growth: The marketplace will foster job creation in communities globally related to real world asset verification.

[IMPACT] Please describe your proposed solution.

Document AI

As part of the review process on the Reitcircles platform, different players in the ecosystem (legal, owner, notary, government etc.) would upload documents related to the verification process. And each of these documents needs to be reviewed.

Verified (KYC +Qualifications) Human agents are part of the review process. And the AI agent being created will help in parsing and extracting relevant information making the review easier for the agents.

• Following diagram illustrates the overall process of AI based flow of data.

• Also there will be UI/UX which will integrate with the above data pipeline and the backend API that will connect to it.
• So all the above components help in the process of verification on the platform.
• This platform also enables digitization of land registry and make maximum use of AI for this.

[IMPACT] How does your proposed solution address the challenge and what benefits will this bring to the Cardano ecosystem?

• The data and the model generated from the Document parsing will eventually feed into the blockchain, as utility will increase from real world projects, using similar process.
• The automation of document parsing leads to a faster and more robust verification process.

[IMPACT] How do you intend to measure the success of your project?

1. An initial working version of the product that can be integrated into the Reitcircles platform and provide real world usage, no matter how rudimentary.
2. Now we can upload documents and trigger an AI parsing for the relevant data (where the prompt engineering will evolve positively over time)
3. Reviewers will be able to get a feedback about relevant contents in the documents, and this should make review time and confidence score generation better.

[IMPACT] Please describe your plans to share the outputs and results of your project?

• We work on the principle of sharing what we use
• Hence the tools that will be used for decentralizing the core features of the project will be open sourced.
• This will include outsourcing the AI models and relevant documentation to use the same.
• APIs that will help other developers build on the platform will be kept open.
• Also we will open source tools that helps us decentralize the platform using the SPOs

[CAPABILITY/ FEASIBILITY] What is your capability to deliver your project with high levels of trust and accountability?

Reitcircles has achieved the following milestones already:

• A working portal with wallet based login
• An onboarding module with document upload and review
• Payment module for taking NFT payments and minting the same.
• House NFT creation based on documents and smart contract based verification.
• Portal based chat communication between members of the platform.
• Role NFT based access to the platform.

Our team brings in more than 40+ yrs of software development experience.

• Antonio Hernandez-Garduno: Platform lead in Smart contract development who is a PhD graduate from Caltech, leading security solutions.
• Tony Mönicke: Computer science graduate based in Berlin and working in cardano ecosystem for last 2+ years.
• Nilay Saha: Worked in leading multinational companies such as ASML, AUDI, Hilti and extensive experience in banking. Has 25+ years of development, solutions architecture and technical leadership experience in large/mid size industry.
• Huy Nguyen, Vinh Dang, Minh Vo: Developers working on the platform (frontend and backend)
• Giang Nguyen: UI/UX lead

[CAPABILITY/ FEASIBILITY] What are the main goals for the project and how will you validate if your approach is feasible?

• Enable real world assets (in this case real estate) to be digitized using NFT : We work on principle of garbage in garbage out. So verification forms the pillar of digitization.

Feasibility: Using KYC, legal verification of documents using digital signatures (wallet based) and using verified legal persons we ensure the above.

• Enable data ownership to the right set of individuals (data should be owned only by the owners of the assets): NFT as the source of truth.
• Feasibility: Our data is stored in permaweb and that becomes our source of truth reflected via NFT ownership.

• Reduce corruption in the area of real estate ownership verification: Data ownership with owners and verifiers acting independently (sourced by platform).
• Feasibility: Since data ownership is now distributed using NFT we reduce drastically the ability of centralised providers to manipulate the source of truth and hence reduce corruption

• Democratize process of verification : marketplace has to have enough verifiers registered and oracle based inputs leads to better judgement from the verifiers.

• Feasibility: Since we have an open marketplace professional verifiers can now be allocated jobs to be done for verification and hence remove the bottleneck of centralized verifiers.

[CAPABILITY/ FEASIBILITY] Please provide a detailed breakdown of your project’s milestones and each of the main tasks or activities to reach the milestone plus the expected timeline for the delivery.

1. Data collection & storage pipelines : 2 months
2. Design of the process & UI/UX : 2 months
3. Backend implementation of AI models: 4 months
4. Backend API implementation for connecting to models: 2 months
5. Unit and integration testing : 2 months
6. Document: 2 months

[CAPABILITY/ FEASIBILITY] Please describe the deliverables, outputs and intended outcomes of each milestone.

1. Data collection & storage pipelines : We need to research, download and store the relevant training data so that later processing becomes possible. In the end we create a process pipelines (in the cloud ) to enable this.
2. Design of the process & UI/UX : The above processes needs to be driven many a times from the frontend (events generated as part of the document review process). This UI/UX needs to be designed.
3. Backend implementation of AI models : This is the core deliverable where we take inputs from the steps 1/2 and use them to feed into the language models
4. Backend API implementation for connecting to models : In order to use the AI models we need to communicate from the frontend using API.
5. Unit and integration testing: Overall we need to test and integrate the different moving parts as mentioned above.
6. Documentation: We need to document all the processes/models created so that other can extend and rework it later if required.

[RESOURCES & VALUE FOR MONEY] Please provide a detailed budget breakdown of the proposed work and resources.

1. Data collection & storage pipelines : 4.2K
2. Design of the process & UI/UX : 8.4 K
3. Backend implementation of AI models : 24K
4. Backend API implementation for connecting to models. : 12K
5. Unit and integration testing : 12K

[RESOURCES & VALUE FOR MONEY] How does the cost of the project represent value for money for the Cardano ecosystem?

We are a bootstrapped project trying to execute on a very lean budget, using hourly rates of 25 $/hr for all of the persons concerned. Over time we have developed a set of good processes internally that enables us to rollout a professional product that meets the highest goal of the industry.

[IMPORTANT NOTE] The Applicant agreed to Fund10 rules and also that data in the Submission Form and other data provided by the project team during the course of the project will be publicly available.

I Accept