Conversational AI Engineering · 2024–2025 · Honda Motor Co.

Bilingual AI Safety Companion

Cloning a domain expert's personality into a trusted, bilingual AI safety companion.

🔒

This is an internal Honda Motor Co. product. Product name and expert identity are confidential. This case study describes the design process, technical architecture, and interaction decisions — happy to discuss in detail during a conversation.

Duration

10+ months

Role

Conversational AI Designer & Engineer

Tools
FigmaGemini APINeo4j (Graph+Vector RAG)FastAPIReact 19Qwen3-TTSMuseTalk

Overview

A bilingual (JP/EN) conversational AI system that models the personality of a real domain expert to deliver trusted cycling-safety guidance in their authentic voice. The core challenge: Japan's cycling regulations are dense and inaccessible — the existing resources are dry and intimidating. The solution makes compliance feel like talking to a knowledgeable friend, not reading a rulebook.

The Problem

Japan's bicycle safety regulations are scattered across dense legal documents. Most cyclists don't know the rules. Existing educational resources are formal and off-putting. The design challenge: how do you make regulatory content engaging and trustworthy enough that people actually absorb it?

54+Personality traits modeled
2Languages (JP/EN)
GraphRAG architecture
VoiceCloning integrated

Research & Discovery

Multimodal personality analysis — video transcripts, speaking patterns, humor markers, linguistic fillers

Linguistic extraction — sentence endings, discourse markers, characteristic JP/EN code-switching patterns

Regulatory document structuring — chunking cycling rulebook for accurate, citable RAG retrieval

Conversational UX — balancing authentic personality with factual accuracy and citation requirements

Key Insight

Personality isn't just tone — it's trust. Users engaged more deeply and retained information better when the AI felt like a real person with opinions, warmth, and humor rather than a neutral information retrieval system.

Design Process

1

Personality modeling — extracting 54+ behavioral and linguistic traits via multimodal Gemini analysis

2

Prompt engineering — encoding fillers, humor style, sentence length, warmth markers into system prompts

3

Initial RAG — FAISS vector search for regulatory retrieval (returned correct but shallow answers)

4

Migration to Graph+Vector RAG (Neo4j) — connected regulations surface together in one coherent response

5

Voice avatar integration — MuseTalk for animated face lip-synced to Qwen3-TTS voice cloning output

6

Frontend — React 19 component library within Honda design system constraints

Critical Pivot

FAISS-only retrieval returned isolated regulation fragments — when a rule connected to three others, users got one. Migrating to Neo4j Graph+Vector RAG let the system traverse the knowledge graph and respond with full regulatory context in a single natural response. This was the turning point from 'accurate but choppy' to 'genuinely feels like an expert.'

Results

Authentic personality validated through user testing — participants reported feeling they were talking to a real expert

Bilingual responses with natural Japanese discourse markers and appropriate cultural humor

Source-cited answers grounding every factual claim in specific regulation articles

Full voice avatar prototype with lip-synced animation received GM stakeholder approval

Reflection

The hardest design challenge wasn't the RAG pipeline or the voice cloning — it was crafting a system where every filler word, every joke, every moment of hesitation was a deliberate design decision that built trust. The engineering was in service of humanity.

Conversational UXPersonality DesignGraph RAGBilingual AIVoice Cloning