Market Knowledge Qualifier

The company appears to be a solo project named "Market Knowledge Qualifier", self-described as a system that filters financial trading knowledge for use in AI systems by applying reproducible rules and out-of-sample testing. The author, Domenico Derrico, built it alone with limited programming skills using tools like GPT-5.6, Next.js, React, and Python. It is presented as a beta version aiming to become a decision support system for traders and investment professionals.

What changed: The project evolved from an idea to a functional prototype, though no evidence of commercial traction or adoption exists. The author states they built it using AI reasoning capabilities but in a restricted environment due to concerns about LLM information reliability.

The single most important open question: Is there any evidence of real-world usage, customer feedback, or revenue generation beyond the author's own account?

• The description states that Market Knowledge Qualifier "ingest[s] PDF Papers, Github Repositories, TradingView Strategies, Natural Language Strategies" and extracts structured rules.
• It checks whether strategies are reproducible, verifies historical data availability, and runs one deterministic out-of-sample test over a rolling one-year window ending today.
• The system produces an "OOS Reliability Score" for each input.
• Only records with a score above zero enter the qualified dataset; those scoring zero are archived as rejected.
• Users can ask questions against qualified records, see citations and limitations, and explicitly opt in before general AI knowledge is used.

Inference: The product appears to be a filtering and validation tool for trading strategies or financial knowledge intended for use with LLMs. It is not described as a full trading platform or an investment advisory service.

• The tagline states: "Market Knowledge Qualifier automatically validates trading knowledge using reproducible rules and out-of-sample testing before making it available to AI systems."
• The author's write-up claims the system filters noise with a click, creating “filtered and certified knowledge for LLMs.”
• The project is positioned as addressing a problem where advisors give advice without understanding what they are talking about.
• The author describes their inspiration as wanting to build a model that creates “certified knowledge” for LLMs.

Inference: The positioning has evolved from an idea to a prototype, but there is no evidence of market validation or product-market fit beyond the author’s own description. The claim of certification and filtering is self-reported.

• The description states that the system is intended for “traders and investment professionists.”
• The author mentions transforming the frontend into a decision support system for these users.
• No specific customer segments or personas are described beyond this general category.

Inference: The target customer appears to be professionals in finance who rely on trading strategies or knowledge from external sources. However, no evidence of actual customers or user interviews is provided.

• There is no mention of pricing, monetization, or business model in the description.
• No information about revenue streams, subscriptions, or paid features is available.
• The project is described as a beta version built by one person.

Inference: The business model remains undefined. It is unclear whether this will be sold as a SaaS product, a tool for internal use, or something else.

• Built with: codex, gpt-5.6, next.js, openai, python, react, typescript, vitest.
• The author states they are not a programmer and built it by providing architecture and correcting outputs based on experience.
• The system is described as running deterministic out-of-sample tests over rolling one-year windows.
• Frontend challenges were noted due to the desire to use GPT reasoning in a restricted environment.

Inference: Technical delivery is limited, with no evidence of scalability or robustness. The reliance on GPT and manual correction suggests early-stage development.

• The project is described as a beta version.
• The author built it alone with few programming skills.
• No evidence of users, customers, revenue, or adoption is provided.
• There is no mention of any testing, feedback loops, or iteration history.

Inference: No traction or maturity signals are evident. The product is at an early stage and lacks real-world validation.

• No information about competitors or market landscape is provided in the description.
• The author does not reference existing tools for validating trading strategies or filtering financial knowledge.
• No mention of similar products or platforms in the space.

Inference: There is no evidence of competitive positioning or awareness of the broader market. This is a gap in the self-reported information.

• The project is described as built by one person with limited programming skills, raising questions about scalability and long-term maintenance.
• No revenue, customers, or adoption data are provided — all claims are self-reported.
• The system is described as a beta version, suggesting it is not yet production-ready.
• The author expresses concern about LLM information reliability, which may indicate technical or philosophical limitations in the approach.

Inference: High risk due to lack of evidence for traction, scalability, and product-market fit. The solo builder model raises concerns about long-term viability.

1. What specific financial or trading knowledge sources are currently supported?
2. How is the out-of-sample testing validated? Is there a mechanism to ensure reproducibility?
3. Have you tested the system with real traders or investment professionals?
4. What is the current architecture and how does it scale?
5. Are there any plans for monetization or commercial use beyond the beta stage?
6. How do you plan to address concerns about LLM reliability in a production environment?