Vicariously

The description states that Vicariously is a ChatGPT-native exploration game where players travel through real places using conversation as an interface. It allows users to:

• Register a persistent identity;
• Begin in one of eleven reviewed starting countries;
• Explore nearby meaningful locations (learning, civic, heritage, transport);
• Walk to chosen destinations;
• Preserve and continue journeys from previous conversations.

It uses ChatGPT as the interface and interpreter, while a secure remote service manages identity, position, journeys, and structured results. The experience is described as being built through two AI workflows: one for ideation (using ChatGPT 5.6 Sol) and one for implementation (using Codex 5.6 Luna).

Inference The product appears to be a persistent virtual exploration game that uses AI to interpret user intent, validate journeys, and maintain state across conversations.

The authors claim that Vicariously explores a third possibility: travelling through the real world from a persistent virtual position, using conversation as the interface. It is positioned as an alternative to traditional maps or location-based games.

They state that:

• The real world becomes the game board.
• ChatGPT does not merely describe but becomes the way you explore.
• The experience is built around four properties: Position, Choice, Consequence, Persistence.

The project’s positioning evolved from a speculative idea to a working prototype. It was built for the OpenAI 2026 hackathon, suggesting it is in early-stage development or proof-of-concept form.

Inference Vicariously positions itself as an experimental, AI-native approach to geographic exploration that challenges traditional game design and map-based navigation.

The description does not explicitly state a target customer or ideal customer profile (ICP). It describes the experience as being for players who want to explore real-world locations through conversation, but no demographic, behavioral, or usage data is provided.

Inference Based on the narrative, the intended users are likely AI enthusiasts, gamers interested in persistent virtual worlds, and explorers of geography through digital tools. However, this is inferred from the self-reported description, not verified.

There is no evidence of a business model or pricing structure in the description. The authors do not mention monetization, subscriptions, or any commercial framework.

Inference The project appears to be in an early stage (hackathon submission), and no commercial model has been described or evidenced.

The project is built using:

• ChatGPT 5.6 Sol for ideation and architecture.
• Codex 5.6 Luna for implementation.
• Tools such as Auth0, GitHub, OpenAI, MCP, and TypeScript.

It uses a secure remote service to manage identity, position, journeys, and structured results, while ChatGPT remains the interface.

The system is described as having three clear layers:

1. Real-world geographic evidence;
2. Durable Vicariously state;
3. ChatGPT interpretation and narration.

It also separates identity management from conversation memory to ensure trust in persistence.

Inference The technical architecture suggests a modular, AI-native approach, with separation of concerns between AI interpretation, backend state, and user interface.

There is no evidence of traction or maturity beyond the authors’ own description. The project is described as a proof-of-concept built for a hackathon. No data on users, revenue, customers, or usage is provided.

The authors state that the current proof is deliberately focused and that future steps include deeper exploration of place, but no actual progress toward commercialization or adoption is reported.

Inference Vicariously is in an early stage of development, likely a prototype or proof-of-concept. No traction or maturity signals are evident.

The description does not mention any competitors. It positions Vicariously as a novel approach to geographic exploration using AI and conversation, but no comparison with existing tools or platforms is made.

Inference It is unclear whether Vicariously directly competes with other location-based services or games, as no competitive context is provided in the description.

• No evidence of traction or adoption: The project appears to be a prototype with no verified users or revenue.
• Unproven commercial viability: No business model or monetization strategy is described.
• Unclear scalability: The system relies on ChatGPT and specific AI models (e.g., 5.6 Sol, Luna), which may not be scalable or stable in production.
• Limited scope: The current version is deliberately focused, with many features still in development.

Inference The project is highly speculative and lacks any evidence of real-world usage or commercial viability.

1. What is the source of truth for geographic data and journey validation?
2. How does Vicariously handle edge cases, such as invalid destinations or failed journeys?
3. Are there plans to expand beyond the current eleven reviewed starting countries?
4. Has the team tested the experience with real users, and what feedback was received?
5. What is the long-term vision for monetization or commercialization?
6. How does the system ensure identity continuity without relying on email or user-provided identifiers?