BaziLantern

The description states that BaziLantern is an engine for BaZi (Four Pillars) astrology. It builds on traditional Chinese systems and integrates ancient texts and schools to produce structured outputs. It includes:

• A deterministic TypeScript engine that calculates charts, hidden stems, Ten Gods, luck cycles, formations, symbolic relationships, scores, confidence, and source status.
• An AI layer that explains the results but does not alter core data.
• A mobile-first Life Audit UI presenting results across six dimensions.
• A four-layer memory mechanism for user interaction and dream processing.

The author states this is a “first-ever” engine of its kind, more complex than calculus, integrating all relevant texts and schools for master-agreed readings. It also models chain reactions within an inner circle of events.

Inference The product appears to be a hybrid of rule-based computation and AI explanation, designed for transparency in an ancient practice.

The author positions BaziLantern as the inverse of typical AI astrology products — not starting with chat but with calculation and evidence. It claims to offer:

• Deterministic chart generation.
• Inspectable results and confidence levels.
• Source status for major conclusions.
• No silent rewriting by AI.

It also states that it avoids ambiguity by not fabricating certainty, and that the AI layer is used only for narration, not computation.

Inference The positioning is to offer a more trustworthy, transparent, and structured approach to BaZi astrology than existing tools — especially those relying on chatbots.

The description does not clearly identify the target customer or ideal customer profile (ICP). It mentions:

• A mobile-first UI.
• Use by 25 friends for testing.
• A dream mechanism and memory system for personal reflection.

It also states that the tool is for “self-reflection and cultural exploration,” not for medical, legal, financial, or predictive advice.

Inference The ICP likely includes individuals interested in traditional Chinese astrology, seeking structured insights over chatbot-style interaction. However, the lack of customer data makes this speculative.

There is no evidence of a business model or pricing structure in the description. The author does not mention monetization, subscriptions, or any revenue-generating mechanism.

Inference The business model remains unknown; it may be early-stage or non-existent.

The author states that the system uses:

• A deterministic TypeScript engine.
• GPT-5.6, OpenAI Codex, React, Next.js, and TypeScript for development.
• Evidence contracts and semantic versioning.
• Regression tests and freeze guards to prevent drift.
• AI narration downstream of deterministic computation.

It also mentions a four-layer memory mechanism and dream processing, though it is not yet implemented.

Inference The technical architecture shows an attempt to separate computation from AI narration, which may signal intent toward robustness and traceability.

The description mentions:

• Testing on 25 friends.
• An accuracy rate over 80% in that testing.
• A production demo for judges to test.
• Five English chart-card rarity prototypes generated from a custom prompt system.
• The image generation path is still under validation.

It does not mention any commercial users, revenue, or adoption beyond the author’s circle.

Inference The project shows early maturity and a functional prototype but lacks evidence of broader traction or commercial viability.

There is no mention of competitors in the description. The author contrasts BaziLantern with typical AI astrology chatbots, but does not name or describe other players in the space.

Inference The competitive landscape is unclear. It may be competing with general AI astrology tools, but no specific comparison is made.

Key risks and red flags include:

• Lack of external validation or customer data beyond 25 friends.
• No evidence of commercial traction or revenue.
• Unproven scalability or adoption beyond the author’s circle.
• The memory mechanism is described as complete but not yet implemented.
• No mention of localization, localization strategy, or international expansion plans.
• The use of GPT-5.6 as a development tool raises questions about whether it could be used in production or if it's just for prototyping.

Inference The project is early-stage and lacks commercial evidence, raising concerns about viability and scalability.

1. What is the source of the 80% accuracy rate in testing with 25 friends? Was it measured against known outcomes or subjective agreement?
2. How does the system handle missing data (e.g., birth time, location) — and what are the implications for confidence scores?
3. Is there any plan to expand beyond the author’s circle of 25 friends for real-world testing?
4. What is the current status of the dream mechanism and memory system? When will they be implemented?
5. Are there plans to monetize or commercialize BaziLantern, and what business model are you considering?
6. How do you plan to scale beyond a single developer (the author)?
7. What is the long-term vision for localization and internationalization?