Moxa Point Finder

Moxa Point Finder helping users navigate moxibustion points and traditional wellness concepts through conversational guidance.

Overview

Moxa Point Finder began as a practical question.

While researching moxibustion, I noticed that beginners often struggle with the same challenges:

• unfamiliar terminology
• difficulty locating points
• uncertainty about where to begin
• overwhelming amounts of information

Many existing resources assume prior knowledge.

The goal of Moxa Point Finder is to make these concepts more approachable through guided conversation, visual support, and structured knowledge retrieval.

What started as a learning aid gradually evolved into an exploration of AI-assisted education and conversational system design.

Why I Built It

One of the recurring challenges in Traditional Chinese Medicine is accessibility.

Experienced practitioners can navigate concepts such as meridians, points, constitutions, and symptom patterns naturally.

Beginners often cannot.

I wanted to explore whether an AI assistant could reduce that barrier while still remaining grounded in reliable source material.

The project also became an opportunity to experiment with retrieval systems, conversational UX, and constrained AI interactions.

Core Question

How can conversational AI make complex knowledge easier to access without sacrificing accuracy or overwhelming the user?

Architecture

The assistant combines conversational AI with retrieval, workflow logic, safety validation, and visual learning support.

Rather than relying on the language model alone, multiple layers help guide responses toward useful and reliable outcomes.

Key Components

Product Evolution

Iteration 1 — Body Mapping Interface

Initially I experimented with a visual body interface where users selected pain locations directly.

The concept looked interesting but introduced unnecessary friction and required users to visit a dedicated website.

Iteration 2 — Web Assistant

ZenMoxa Web Assistant

The next version evolved into a conversational web assistant capable of generating recommendations and treatment plans.

While technically more capable, it still required users to leave their existing workflows and visit a separate platform.

Final Direction — Messaging First

The project ultimately shifted toward Telegram and WhatsApp.

Messaging platforms dramatically reduced friction because users could access the assistant within tools they already used daily.

This decision improved accessibility more than any individual AI improvement.

Technology Stack

AI Layer

• Google AI Studio
• Gemini API
• Prompt Engineering
• State-Aware Workflows

Backend

• Node.js
• TypeScript
• Express
• Railway

Conversation Layer

• Botpress

Channels

• Telegram
• WhatsApp (In Progress)

Knowledge Layer

• RAG
• Semantic Search
• Structured Knowledge Base

Frontend Prototypes

• React
• Tailwind CSS

Current Status

The assistant is currently deployed through Telegram, with WhatsApp integration in progress.

Current work focuses on improving conversational quality, expanding knowledge coverage, refining retrieval workflows, and integrating the system into the broader Flow Temple platform.

Lessons Learned

The biggest surprise was how much of the challenge existed outside the language model itself.

Generating responses was relatively straightforward.

Designing workflows, handling edge cases, validating outputs, managing conversation state, and creating a smooth user experience turned out to be the more interesting engineering problem.

The project reinforced the idea that useful AI products are rarely just prompts—they are systems.