Today+X

The description states that Today+X is a tool that allows users to input natural-language questions about hypothetical global events and receive structured, visualized consequences. It uses AI to generate causal chains, which are rendered in a 3D globe with geographic impact points, connections, severity levels, confidence scores, and uncertainty indicators.

It includes:

• A cinematic 3D Earth visualization
• Scenario playback over time
• Integration of world data, market signals, logistics activity, risk alerts, intelligence briefings
• Saved analyses and reusable scenarios
• An intelligence dashboard for deeper analysis

The system is built with a full-stack architecture using Next.js, React, FastAPI, Python, Neo4j, and OpenAI API. AI output is constrained by a versioned JSON schema and validated server-side before rendering.

Inference This is a prototype or proof-of-concept product designed to demonstrate an idea rather than a production-ready solution.

The description states that Today+X aims to be a more transparent way to explore plausible futures — not as predictions, but as structured scenarios people can inspect and question. It positions itself as a tool for understanding uncertainty, not certainty.

It emphasizes:

• Transparency in reasoning
• Responsibility in communicating uncertainty
• Visual exploration of consequences
• Separation between sourced data and generated scenarios

Inference The positioning is clear: it’s a scenario planning tool focused on visualizing plausible outcomes from hypothetical inputs, not a forecasting or decision-support platform.

The description does not name specific customer segments or personas. It implies the product targets users who might be interested in global risk analysis, strategic planning, or understanding complex systems — such as analysts, policymakers, or researchers.

Inference The likely ICP includes professionals working with geopolitical, economic, or environmental risk — but no explicit targeting is stated.

There is no evidence of a business model or pricing structure in the description. The project was submitted to a hackathon and has no mention of monetization, subscriptions, or paid features.

Inference No commercial model is evident from the self-reported description.

The system uses:

• Frontend: Next.js, React, TypeScript, React Three Fiber, Three.js, Tailwind CSS, Framer Motion
• Backend: FastAPI, Python, Pydantic, OpenAI API
• Data handling: Neo4j for graph retrieval, strict schema validation
• AI integration: Controlled output via JSON schema and server-side validation

The architecture is described as designed around a “strict scenario contract” to ensure safety, testability, and predictability.

Inference The technical stack suggests a modern, scalable approach with emphasis on control over AI outputs and data integrity. However, no evidence of deployment or performance metrics is provided.

There is no evidence of traction, revenue, customers, or usage beyond the hackathon submission. The project was built in a short timeframe (a hackathon), and there are no references to user testing, feedback loops, or product iteration.

Inference This is a prototype with no demonstrated market adoption or maturity.

The description does not mention competitors or existing tools in the space of scenario planning, risk visualization, or AI-powered global analysis. It does not reference similar platforms or products that might be used for comparison.

Inference No competitive landscape is described; this may be a novel idea or one that lacks clear market context.

• Unproven commercial viability: No evidence of revenue, customers, or monetization.
• Prototype nature: Built for a hackathon with no indication of further development or production use.
• Unclear target audience: No defined customer segments or personas.
• No data on AI performance or accuracy: The system uses constrained AI but does not report how well it performs in practice.
• Limited validation: No mention of user testing, feedback, or iterative improvements.

Inference The project is untested in real-world conditions and lacks any evidence of traction or commercial potential.

1. What specific use cases have you identified for this tool beyond the hackathon?
2. Have you tested it with any users or stakeholders? If so, what feedback did you get?
3. How do you plan to validate the accuracy and utility of AI-generated scenarios?
4. Is there a roadmap for moving from prototype to production-ready product?
5. What are your plans for monetization or scaling beyond the hackathon?
6. Are there any existing partnerships or pilot programs with potential users?