Simple Trade Copilot

The description states that Simple Trade Copilot IA is:

• A human-in-the-loop decision-support platform for B3 day trading.
• Not an auto-trader; it does not execute trades.
• Designed to help the operator understand market opportunities, timing validity, and risk before capital deployment.
• Built with a modern TypeScript stack including React, Next.js, Node.js, and SQLite.

It includes features such as:

• ON_TIME Radar: monitors asset states (FORMING, ON_TIME, STRETCHED, ENGINE_ACTIONABLE).
• Contextual Decision Engine: combines price action, volatility, volume, trend location, market regime, and microstructure.
• Risk-Aware Trade Planning: calculates entry, stop, target, and position sizing based on fixed monetary risk unit.
• Portfolio and Operation Tracking: shows active positions, daily capital context, executed operations, and current decision status.
• AI Conversation Layer: allows users to ask questions about market context without losing workflow.

The system is described as a protective cockpit, where the AI supports decisions, the platform exposes risk, and humans remain responsible for final action.

Evidence Self-reported by the author. No third-party validation or demonstration of actual functionality beyond mock mode.

The author positions Simple Trade Copilot IA as:

• A quantitative decision copilot, not an auto-trader.
• Focused on real-time radar, risk-first planning, audit trails, replay-driven learning, and AI-assisted engineering discipline.
• A tool to make complex retail trading safer by providing objective market context, risk controls, and explainable decision support.

It is also framed as:

• A personal statement: the author built it under constraints of limited time and leadership responsibilities, using AI to bridge a gap between idea and execution.
• A demonstration of how AI can reopen the door to hands-on creation for people with discipline but not unlimited time.

The claim evolution shows a shift from:

1. Initial inspiration (complexity of retail trading in Brazil)
2. Product definition (human-in-the-loop, AI-assisted support)
3. Technical realization (stack, architecture, replay logic)
4. Future vision (security hardening, broker-side guardrails, live microstructure shadowing)

Evidence All claims are self-reported and unverified.

The description states:

• The platform targets B3 day traders in Brazil, who face challenges due to oversimplified chart patterns, unrealistic promises, emotional decision-making, and market complexity.
• It is intended for individual retail traders navigating fast, complex markets shaped by liquidity, spreads, slippage, institutional flow, and high-frequency behavior.

The platform is described as:

• Not for replacing the human trader but protecting them with objective context and risk controls.
• Designed to help operators evaluate timing, understand risk, and make disciplined decisions.

There is no mention of institutional users or other financial sectors beyond B3 day trading.

Evidence Self-reported. No evidence of customer segmentation, personas, or adoption data.

The description does not contain any information about:

• Revenue streams
• Pricing models
• Monetization strategy
• Customer acquisition plans
• Subscription tiers or usage-based pricing

It is unclear whether the platform will be offered as a SaaS product, a one-time tool, or part of a larger ecosystem.

Evidence Not evidenced.

The author reports:

• Built with Next.js 16, React 19, TypeScript, and SQLite.
• Market data layer uses Cedro Crystal integration for B3 data ingestion.
• Includes replay and oracle layers to evaluate strategies without risking real capital.
• AI-assisted development using Codex and GPT throughout the build process.
• Platform runs in a controlled mock mode for demos, with no live market dependency.

The architecture emphasizes:

• Traceability, replayability, and operational safety.
• Canonical radar frames, freshness checks, and stale-state handling.
• Throttling persistence and aggressive pruning to avoid database issues (e.g., 14GB WAL incident).
• Separation of signal quality from frequency.

Evidence Self-reported. No evidence of production deployment or scalability testing.

The description does not provide any evidence of:

• Revenue
• Customers or user base
• Product usage metrics
• Market traction or adoption
• Beta testing or pilot programs
• Product maturity beyond prototype/demo stage

It is clear that this is a hackathon submission, and the author explicitly states it is a “Build Week version” designed as a protective cockpit.

Evidence Not evidenced.

The description does not mention:

• Direct competitors
• Market size or share
• Competitive advantages or differentiation
• Existing tools in the Brazilian B3 trading space

It is implied that the platform addresses a gap in retail trading support, but no comparison to existing platforms or services is made.

Evidence Not evidenced.

Inferences based on self-reported information:

1. Solo Development Risk: The entire product was built by one person (Uilson Nardocci), which raises questions about scalability, long-term maintenance, and feature depth.
2. Lack of Live Testing: The platform is described as running in mock mode for demos; no evidence of live trading or real-world validation.
3. AI Dependency Risk: Heavy reliance on AI tools (GPT, Codex) may create dependency risks if those services change or become unavailable.
4. Limited Scope: The focus is on B3 day trading only, with no indication of expansion plans or broader applicability.
5. Unproven Commercial Viability: No evidence of monetization strategy, pricing model, or customer demand.

Evidence Self-reported. These are inferences drawn from lack of evidence and project constraints.

1. Has the platform been tested in any live trading conditions beyond mock mode?
2. What is the plan for securing real market data access and integrating with brokers?
3. How does the team intend to scale beyond a solo developer?
4. Are there plans to monetize or commercialize this product?
5. What are the key assumptions behind the replay-driven learning approach, and how were they validated?
6. Is there any intention to expand beyond B3 day trading into other markets or asset classes?
7. How will the platform handle regulatory compliance in financial services?