Crowdsourcing AI-Powered Transaction Tagging on Cardano

[Proposal setup] Proposal title

Please provide your proposal title

Crowdsourcing AI-Powered Transaction Tagging on Cardano

[Proposal Summary] Budget Information

Enter the amount of funding you are requesting in ADA

99600

[Proposal Summary] Time

Please specify how many months you expect your project to last

9

[Proposal Summary] Translation Information

Please indicate if your proposal has been auto-translated

No

Original Language

en

[Proposal Summary] Problem Statement

What is the problem you want to solve?

Fraudulent transactions on Cardano lack reliable labeling. Current methods are costly and fragmented, leaving users and developers without scalable, trustworthy fraud detection tools.

[Proposal Summary] Supporting Documentation

Supporting links

• https://arxiv.org/abs/2108.13487?utm_source=chatgpt.com
,
• https://q-medical-ai.com/

[Proposal Summary] Project Dependencies

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

Yes

Describe any dependencies or write 'No dependencies'

Using OpenAI’s AI models to train and suggest transaction labels

[Proposal Summary] Project Open Source

Will your project's outputs be fully open source?

Yes

License and Additional Information

We will open source all related smart contract code

[Theme Selection] Theme

Please choose the most relevant theme and tag related to the outcomes of your proposal

AI

[Campaign Category] Category Questions

Mention your open source license and describe your open source license rationale.

We will open source all smart contract code under the Apache 2.0 license. This license ensures transparency, allows anyone to use, modify, and distribute the code, and includes explicit patent protection for contributors. By adopting Apache 2.0, we foster trust, encourage community collaboration, and support broader adoption of our solution while safeguarding both developers and users.

How do you make sure your source code is accessible to the public from project start, and people are informed?

We will publish all source code on GitHub in a public repository from the very start of the project. Updates and releases will be announced through our social channels, including X (Twitter), to keep the community informed and engaged.

How will you provide high quality documentation?

We will provide high-quality documentation through a structured GitHub wiki, detailed README, and clear code comments. Additionally, we’ll publish guides and tutorials to ensure developers and users can easily adopt and build on our solution.

[Your Project and Solution] Solution

Please describe your proposed solution and how it addresses the problem

We propose to build a crowdsourcing platform integrated with AI models that enables the Cardano community to collaboratively label blockchain transactions. This system will combine human intelligence (crowdsourcing) and AI assistance (OpenAI models) to achieve scalable and accurate transaction tagging.

Key Features

• Crowdsourced Tagging: - Users contribute by tagging suspicious or notable transactions. - A reward/penalty mechanism ensures quality of contributions.
• AI-Assisted Labeling: - AI models trained with verified transaction datasets help suggest labels. - Community members validate or correct AI-suggested tags.
• On-Chain Evidence Storage: - Finalized tags are stored on Cardano through metadata or lightweight on-chain records. - Ensures transparency and auditability.
• Open API for Ecosystem Integration: - Wallets, dApps, and explorers can fetch tagged data. - Promotes safer usage across the ecosystem.

[Your Project and Solution] Impact

Please define the positive impact your project will have on the wider Cardano community

Our solution empowers the Cardano ecosystem by leveraging crowdsourcing and AI to generate accurate transaction tags, improving transparency, traceability, and user experience. By open-sourcing the smart contracts and training data pipeline, we foster community collaboration and innovation. This not only reduces friction in financial reporting and compliance but also sets the foundation for future DeFi, wallet, and analytics integrations. In the long term, it creates a community-driven knowledge base that scales with network growth, enabling both retail and institutional users to better understand and manage their blockchain activity.

[Your Project and Solution] Capabilities & Feasibility

What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?

We ensure trust and accountability by open-sourcing all code under the Apache 2.0 license, making development transparent from day one. Progress will be shared publicly on GitHub and social channels. To validate feasibility, we start with a working prototype, gather community feedback, and iterate through real-world testing with open datasets and user contributions.

[Milestones] Project Milestones

Milestone Title

System Architecture & Smart Contract Design

Milestone Outputs

Deliverable includes finalized system architecture diagrams, defined data flows for AI tagging pipeline, and initial smart contract design (data structure, core functions, and integration points with off-chain AI services). Documentation will describe interaction between on-chain and off-chain components, ensuring scalability and security.

Acceptance Criteria

• Architecture diagram approved and consistent with project goals.

• Smart contract design reviewed and covers transaction labeling logic.

• Documentation complete, versioned, and publicly available on GitHub.

Evidence of Completion

• GitHub repository containing system architecture files and documentation.

• Commit history showing collaborative review and refinements.

Delivery Month

2

Cost

10000

Progress

20 %

Milestone Title

Core Feature Development & AI Integration

Milestone Outputs

This milestone focuses on building the backbone of the Crowdsourcing AI Tag platform, combining blockchain smart contracts with AI training infrastructure. On the blockchain side, we will design and deploy core smart contracts that govern task creation, data submission, validation, contributor incentives, and reward distribution. These contracts will be deployed and tested on Cardano testnet. On the AI side, we will establish a modular training pipeline that allows submitted data to be pre-processed, validated, and integrated into training datasets for machine learning models.

Acceptance Criteria

• Functional smart contracts deployed on Cardano testnet handling task posting, submission, validation, and reward distribution.

• AI training pipeline capable of ingesting crowdsourced data and producing an updated baseline model.

• APIs connecting blockchain logic and AI training system fully functional and tested.

• Smart contract code reviewed

• Demonstration of end-to-end workflow: contributor submits data → data validated → data integrated into AI model training

• Documentation detailing contract architecture, training pipeline design, and integration approach delivered.

Evidence of Completion

• Source code of smart contracts published in a public GitHub repository.
• Deployment addresses of testnet smart contracts.
• Logs and datasets showing training runs with crowdsourced inputs integrated.
• Test reports demonstrating end-to-end workflow execution.

Delivery Month

4

Cost

59600

Progress

40 %

Milestone Title

Platform Beta Release

Milestone Outputs

This milestone focuses on deploying a beta version of the Crowdsourcing AI Tagging platform with core features fully integrated, including AI-assisted tagging, community contribution flows, and governance mechanisms for data validation. The beta release will include user onboarding, wallet-based authentication, contribution incentives, and real-time AI tagging suggestions. We will open the platform to a selected group of early adopters and the wider community to test system performance, scalability, and usability. Feedback collected will be systematically analyzed to refine both the AI model and the user experience.

Acceptance Criteria

• Beta version of the platform is publicly accessible via a testnet or controlled environment.

• AI-assisted tagging is active and demonstrably improves labeling accuracy.

• At least 50 community testers onboard and interact with the system.

• Collection and analysis of structured feedback (surveys, interviews, telemetry logs).

• Identification of at least three major areas of improvement and a clear plan for adjustments.

Evidence of Completion

• Publicly accessible beta platform URL and documentation.

• System usage logs and telemetry reports showing engagement metrics (number of users, number of tagged items, AI-human agreement rate).

• Published community feedback report summarizing findings and recommendations.

• GitHub repository updates with beta release code and changelog.

Delivery Month

2

Cost

20000

Progress

30 %

Milestone Title

Final Report & Demonstration Video

Milestone Outputs

This milestone focuses on the consolidation and presentation of the entire project’s results. We will prepare a comprehensive final report detailing the objectives, methodology, implementation, challenges, AI training progress, and the final outcomes. Additionally, a demonstration video will be created to summarize the development process and showcase the system in action. The outputs will ensure transparency, knowledge sharing, and easy communication of project results to both the Catalyst community and broader stakeholders. The video will highlight the integration of crowdsourcing with AI, system features, and real-world feasibility.

Acceptance Criteria

• A complete written final report is produced, covering the full lifecycle of the project, including architecture design, AI training methodology, implementation milestones, testing outcomes, and overall impact assessment.
• Project demonstration video is delivered, summarizing the project development, showcasing working features, and providing a clear visual explanation of results.
• Both report and video are disseminated through official communication channels

Evidence of Completion

• Published Final Report uploaded to the GitHub repository under a dedicated "Final Documentation" section.
• Published Demo Video hosted on Youtube and shared with the Catalyst community.
• Links to both report and video provided as verifiable evidence.
• Confirmation of community access and review (e.g., Catalyst feedback, GitHub stars, comments, or forum engagement).

Delivery Month

1

Cost

10000

Progress

10 %

[Final Pitch] Budget & Costs

Please provide a cost breakdown of the proposed work and resources

The costs of the team that will be assigned to this effort will compromise of

1 Smart Contract Engineer for 9 months ($2500/m *9 = $22,500)

1 AI Engineer for 9 months ($4000 * 9 = $36,000)

3 Full-Stack Developers for 9 months ($1500/m _ *3 * 9 = $40,500 )_

Total $99,000

[Final Pitch] Value for Money

How does the cost of the project represent value for the Cardano ecosystem?

Full-time Team

All members commit to working continuously for 9 months, ensuring progress, quality, and absolute focus on the project.

Having a dedicated full-time team minimizes risks of delays and guarantees that core features are completed on schedule.

Experience and Expertise

Smart Contract Engineer: Specialist in Cardano, ensuring smart contracts are secure, cost-efficient, and easy to audit.

AI Engineer: Experienced in developing and integrating AI, particularly critical since the project includes AI-driven components.

Full-stack Developers (3): Responsible for building the front-end, back-end, API integrations, UX/UI, and maintaining infrastructure.

Personnel Costs Based on Market Rates

Compensation is aligned with competitive industry averages in blockchain and AI, not exceeding international standards.

Examples:

Smart Contract Developer: $2,500 – $5,000/month

AI Engineer: $4,000 – $6,000/month

Full-stack Developer: $1,500 – $3,000/month

Ensuring Quality and Timeliness

AI and Smart Contract engineers are onboarded from the start to prevent bottlenecks, as these are the most critical areas.

3 Full-stack developers are engaged throughout the 9 months to ensure stability and scalability of the system.

AI Models & Infrastructure Costs

Personnel costs do not include expenses for AI API usage (e.g., OpenAI API), hosting, security, and data storage.

This demonstrates the team’s commitment to using the budget efficiently while accounting separately for infrastructure needs.

[Required Acknowledgements] Consent & Confirmation

Terms and Conditions:

Yes