Agentic DApp Testing SDK by Dquadrant

[Proposal setup] Proposal title

Please provide your proposal title

Agentic DApp Testing SDK by Dquadrant

[Proposal Summary] Budget Information

Enter the amount of funding you are requesting in ADA

100000

[Proposal Summary] Time

Please specify how many months you expect your project to last

6

[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?

Cardano developer community lacks an agentic testing framework/SDK that enables developers to test their apps in realistic scenario.

[Proposal Summary] Supporting Documentation

Supporting links

• https://github.com/cardanoapi/autonomous-agents
,
• https://agents.cardanoapi.io

[Proposal Summary] Project Dependencies

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

No

Describe any dependencies or write 'No dependencies'

No dependencies

[Proposal Summary] Project Open Source

Will your project's outputs be fully open source?

Yes

License and Additional Information

Apache-2.0 license

[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.

Apache-2.0 license

Rationale: Apache-2.0 license is one of the most flexible open source license used within Cardano community and most of the Intersect repositories like Cardano-node also adopts Apache-2.0 license.

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

We'll be contributing an existing open source project under the scope of this proposal. Here is the Github project link:

https://github.com/cardanoapi/autonomous-agents

How will you provide high quality documentation?

To keep the quality of documentation, we plan to use Docusaurus to structure the documentation and get feedback from the developer community. As the proposal is an SDK, we plan to provide high quality tutorials and examples on how to use the SDK.

[Your Project and Solution] Solution

Please describe your proposed solution and how it addresses the problem

Testing decentralized applications (DApps) on Cardano currently lacks agentic simulation of real-world behaviors.

• Existing testing frameworks are limited to unit and integration checks.
• They cannot capture adaptive decision-making from users, attackers, or validators under stress.
• Without agentic testing, developers risk deploying DApps that behave unpredictably in production, especially under Hydra scaling or adversarial conditions.

We will develop an Agentic DApp Testing SDK that introduces LLM-powered agents to simulate realistic, adaptive behaviors across Cardano DApps.

Key features:

• Agentic Testing: Agents reason with context, adapt strategies, and mimic real-world decisions rather than running static scripts.
• Diverse Roles: Simulate users, attackers, validators, liquidity providers, and DReps.
• LLM Integration: Large Language Models guide agents’ decision-making, enabling them to act autonomously within different DApp scenarios.
• Developer SDK: Simple libraries and APIs for integrating agentic simulations into CI/CD pipelines.
• Dashboard: Visualize agent interactions, performance data, and vulnerabilities.

This SDK transforms testing into a dynamic, adaptive environment that reflects how DApps will truly perform once deployed.

[Your Project and Solution] Impact

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

For Developers: Safer, more reliable DApps before mainnet deployment.

For the Ecosystem: Stronger resilience against exploits and bottlenecks.

For Governance: Agentic simulations extend beyond DApps into governance actions and Catalyst voting.

[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?

The Kuber Team comes from Dquadrant which is an enterprise member of Intersect and a trusted partner of IOHK, with active roles in working groups and the committees. We have over 5 years of Cardano delivery experience, contributing to hard forks, governance frameworks, and developer tooling.

Dquadrant is chosen by Intersect as one of the five trusted partners of the oversight committee for treasure withdrawals (check and balances) on basis of its contributions, its expertise, trust and transparency.

We are maintainers of the Autonomous Agent Testing tool and GovTool, with a strong reputation for quality assurance and end-to-end testing. Our track record includes the Playwright-enabled E2E Testing Wallet (GitHub), Kuber, KuberIDE, cardano-marketplace and mempool explorer. These open-source tools are in production and demonstrate consistent delivery.

This proposal is a direct extension of our existing work, making execution risk low.

Our established partnerships, delivery record, and ongoing maintenance of related tools demonstrate our capability to deliver this project reliably.

[Milestones] Project Milestones

Milestone Title

M1 – Research & Design

Milestone Outputs

• Design document detailing SDK architecture, agent roles, LLM integration approach, and identified DApp testing scenarios simulated roles like users, DReps, attacker etc.
• Github project and tickets created for major tasks

Acceptance Criteria

• A clear technical plan that defines all required components of the SDK, including specifications for agentic behaviors, LLM decision loops, and testing pipelines.
• Github project is publicly available and includes tickets for major tasks

Evidence of Completion

• Published research report and project plan in an open repository, reviewed by the community, with detailed scenario lists and design diagrams accessible online.
• Github project is publicly available and includes tickets for major tasks

Delivery Month

1

Cost

10000

Progress

10 %

Milestone Title

Milestone 2 – Core SDK & LLM Integration

Milestone Outputs

• Functional SDK implementing modular APIs for agent behavior simulation.
• Integration layer enabling LLMs to power reasoning-based agent decisions.
• Documentation and usage examples demonstrating SDK integration.

Acceptance Criteria

• SDK agents demonstrate adaptive behavior in test environments using LLM reasoning.
• Repository includes full code, installation guide, and developer examples.
• Successful execution of test cases showing functional agentic interactions.

Evidence of Completion

• Open-source repository with SDK, LLM modules, and developer documentation.
• Test results published validating agent decision-making and adaptive responses.

Delivery Month

3

Cost

60000

Progress

70 %

Milestone Title

Milestone 3 – Scenario Development

Milestone Outputs

Library of test scenarios covering normal, adversarial, and high-load use cases.

Simulation scripts for multi-agent behaviors against Cardano DApps.

Extended documentation for running and modifying scenario tests.

Acceptance Criteria

Agents run successfully across multiple DApp scenarios on Cardano testnets.

Simulations demonstrate adversarial behaviors and stress testing with measurable outcomes.

Scenario scripts and results are reproducible for developers and researchers.

Evidence of Completion

Scenario libraries, test reports, and simulation scripts published openly.

Community demo video showing agent-driven scenario execution.

Updated SDK release including scenario support and documentation.

Delivery Month

2

Cost

20000

Progress

90 %

Milestone Title

Milestone 4 – Dashboard, Testing

Milestone Outputs

Interactive dashboard for visualizing agent interactions, performance metrics, and reports.

Final SDK release with stable APIs and full documentation.

Comprehensive project report and educational workshop material.

Acceptance Criteria

Dashboard provides accurate, real-time data on agent simulations and outcomes.

Final SDK release validated in multiple DApp testing scenarios with full stability.

Close-out report summarizes project outcomes, lessons learned, and future improvements.

Evidence of Completion

Publicly available dashboard and SDK release on GitHub.

Final project report shared with the Cardano community and Catalyst.

Video presentation and workshop recording published for transparency and adoption.

Delivery Month

1

Cost

10000

Progress

100 %

[Final Pitch] Budget & Costs

Please provide a cost breakdown of the proposed work and resources

Milestone 1 – Research & Design (10,000 ADA)

Resources Used:

• Developers – research on LLM agent design and DApp testing methodologies.
• Project Lead – technical planning, scenario definition, and roadmap creation.
• Infrastructure – compute and storage for prototypes and documentation.

Milestone 2 – Core SDK & LLM Integration (60,000 ADA)

Resources Used:

• Developers – implementation of SDK framework, modular APIs, and agent behavior modules.
• Backend Engineer – infrastructure setup, CI/CD pipelines, and testing harness.
• Project Lead – architecture oversight and technical reviews.
• Infrastructure – cloud servers, Cardano testnet nodes, db-sync setup.
• LLM Costs – API usage for agent reasoning, validation, and performance testing.

Milestone 3 – Scenario Development (20,000 ADA)

Resources Used:

• Developers – creation of test scenarios (DeFi, NFT, governance, adversarial).
• QA Engineer – validation of reproducibility and scenario outcomes. Infrastructure – testnet deployments for multi-agent testing.
• LLM Costs – scenario simulations with adaptive multi-agent behaviors.

Milestone 4 – Dashboard, Testing & Close-Out (10,000 ADA)

Resources Used:

• Developers – build dashboard to visualize agent interactions and performance data.
• Project Lead – final report, and community presentation.
• QA Engineer – final stability and performance validation of SDK v1.0.
• Infrastructure – hosting for dashboard, repositories, and reporting tools.

[Final Pitch] Value for Money

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

For 100,000 ADA, the project delivers:

• A ready-to-use SDK for agentic DApp testing.
• LLM-powered adaptive agents for realistic simulations.
• Fully open-source outputs under Apache 2.0.
• Community engagement through reports, workshops, and code contributions.
• This solution can be used by any DApp developed on Cardano to speed up their time to market (mainnet) which is critical for the adoption of Cardano. It limits the time to be spend on preview testnet or pre-prod.

This solution positions Cardano at the forefront of agentic testing innovation in Web3.

[Required Acknowledgements] Consent & Confirmation

Terms and Conditions:

Yes