Trade Evidence

The description states that Trade Evidence is a "simulation-first research platform for algorithmic trading." It monitors crypto assets, evaluates signals under risk controls, records blocked decisions, and preserves the complete lifecycle of simulated trades.

It separates:

• Canonical results (trusted research record)
• Shadow experiments (testing alternatives without contaminating canonical performance)
• Data quality checks
• Sample sufficiency gates
• Execution truth (distinguishing simulated from real-market execution)

For each simulated trade lifecycle, it preserves structured data including:

• Symbol and direction
• Entry/exit information
• Exit reason
• PnL metrics (gross, net, estimated costs)
• Maximum favorable/adverse excursion
• Giveback
• Data timestamps
• Experimental lane/cohort

The platform uses a web dashboard, backend APIs, PostgreSQL, Docker, automated tests, and Git-based deployment workflows.

Evidence Self-reported by author. No independent verification or demonstration of actual product usage.

The author positions Trade Evidence as an "evidence-first" platform for auditing algorithmic trading systems. It aims to make trading research "auditable by design."

Key claims:

• Separates trusted results from experiments
• Explains every simulated decision with traceable data
• Prevents contamination of canonical performance through shadow experiments
• Ensures sample sufficiency and data quality before promoting conclusions

The author notes that the platform existed prior to Build Week but was significantly expanded during the event. The expansion focused on audit capabilities, particularly around:

• Research Desk validation
• Canonical vs shadow isolation
• Data truth reconciliation
• Sample sufficiency gates
• Execution evidence

Evidence Self-reported claims about positioning and evolution. No external validation or market feedback.

The description does not identify specific target customers or personas. It mentions that the platform is for "algorithmic trading research" and monitors crypto assets, but does not name industries, roles, or types of users.

Evidence Not evidenced. The author does not describe who uses this system beyond themselves.

The description makes no mention of pricing, monetization, or business model. It states that Trade Evidence "does not provide financial advice and does not execute real-money trades in the submitted configuration."

Evidence Not evidenced. No indication of how the product would be sold or whether it has any commercial revenue streams.

The platform is built with:

• Backend APIs (FastAPI)
• Web dashboard (React)
• Database (PostgreSQL)
• Containerization (Docker)
• Version control (Git)
• Automated testing
• Deployment workflows (Git-based)

It integrates tools like:

• ChatGPT for architecture and documentation
• OpenClaw orchestrating Codex with GPT-5.6 Sol
• GitHub for code management

The author describes using these technologies to inspect repositories, identify contract inconsistencies, create regression checks, and produce validation evidence.

Evidence Self-reported technical stack and tooling. No demonstration of live system or operational delivery.

There is no evidence of traction, customers, or adoption beyond the author's own development work. The description states that the platform existed before Build Week but was expanded during it — implying it was not yet in production use.

The author notes challenges such as:

• Preventing valid-looking results from being misinterpreted
• Maintaining distinction between descriptive analysis and production-ready conclusions

These suggest early-stage development rather than a mature product with real-world usage.

Evidence Not evidenced. No revenue, customers, or usage data provided.

The description does not mention any competitors or competitive landscape. It focuses solely on the author's own solution without reference to existing tools in algorithmic trading research or audit systems.

Evidence Not evidenced. No comparison to other platforms or market positioning.

1. No commercial traction: The platform appears to be a personal project with no evidence of real-world usage, customers, or revenue.
2. Unverified claims: All descriptions are self-reported and unverified — including the existence of features like "canonical vs shadow isolation" or "data truth reconciliation."
3. Lack of clarity on product maturity: The author describes expanding functionality during Build Week, suggesting it was not yet a finished product.
4. No pricing or monetization strategy: No indication of how the platform would be sold or whether there is any commercial intent.
5. High reliance on AI tools: Heavy use of ChatGPT and Codex may indicate a prototype or experimental approach rather than a scalable solution.

Evidence Inferences based on lack of evidence for key business metrics, customer data, or product maturity.

1. What is the actual scope of your development work? Is this a full product or an experimental prototype?
2. Have you tested this system with any external users or teams in algorithmic trading research?
3. How do you plan to monetize Trade Evidence, if at all?
4. Can you demonstrate how the canonical vs shadow isolation works in practice?
5. What specific data quality checks are implemented and how are they validated?
6. Are there any known limitations or edge cases where the system fails to preserve evidence properly?
7. How do you ensure that sample sufficiency gates prevent false positives?
8. Do you have plans for integrating real-market execution data into the platform?