Challenge Framing
MindMirror predictions and scores were useful but difficult to interpret conversationally, while unconstrained assistants would introduce hallucination and out-of-scope risk in a sensitive domain.
MindMirror Conversational AI Agent
Rather than building a general chatbot, this service was intentionally constrained around psychology interpretation. That tradeoff improves relevance, trust, and production safety.
Case Study
Overview
Project Overview
What I built, the problem, and the solution
Built a memory-aware AI service that turns structured MindMirror predictions into grounded conversational explanations using user-specific retrieval, cache reuse, and corrective web search with explicit domain restrictions.
Solution Strategy
I designed a LangGraph-based orchestration flow with domain routing, user-scoped retrieval, hybrid memory, semantic cache reuse, and corrective search rules that stay inside psychology.
Project Highlights
Five-route guarded router for direct, RAG, memory, web-search, or reject decisions.Hybrid memory design with short-term turns and distilled long-term facts.CAG semantic cache plus weak-context corrective search.SSE graph streaming for stage-level execution visibility.
Gallery
Product screens and workflow snapshots
Selected screens show the visible product experience and the operational surfaces behind each project. Projects without captured assets keep a structured placeholder until real screenshots are available.
Module 04Frame 01
MindMirror Conversational AI Agent
Python 3.10FastAPI
Guarded route selection
Every request enters a controlled route decision before retrieval or synthesis is allowed to run.
Module 04Frame 02
MindMirror Conversational AI Agent
Python 3.10FastAPI
Personalized context assembly
Memory, user predictions, and optional corrective search are composed into a bounded context package.
Module 04Frame 03
MindMirror Conversational AI Agent
Python 3.10FastAPI
Streaming execution view
Node-level SSE events make graph progress and request timing observable in real time.
Tech Stack
Built with tools chosen for reliability and iteration speed
Agent orchestration, guarded retrieval, personalized memory, domain safety, and operational observability for AI-backed products.
Backend
- FastAPI
AI / ML
- Python 3.10
- LangGraph
- LangChain
- OpenAI
Data
- Supabase
- Chroma
DevOps
- Tavily
Key Features
Guarded routing
The router enforces domain restriction before retrieval or generation begins.
User-scoped retrieval
Prediction data is resolved against canonical user identity before context assembly.
Personalized memory
Short-term conversation state and long-term facts are recalled under a strict token budget.
Operational transparency
SSE streaming and observability hooks expose graph progress, latency, and debugging context.
Architecture
System architecture designed as a readable engineering story
Each layer stays explicit so reviewers can quickly understand where interface, orchestration, persistence, and service responsibilities live.
01
API Surface
Chat, streaming, health, graph, and memory endpoints expose the service to MindMirror clients and developers.
FastAPISSEPydantic
02
Agent Orchestration
LangGraph coordinates recall, routing, cache, retrieval, synthesis, and memory write-back.
LangGraphLangChainOpenAI
03
Persistence + Retrieval
Supabase stores operational memory and user data while Chroma supports semantic cache lookup.
SupabaseChromaTavily
System Flow
Key stages broken down as a readable execution path
The pipeline section keeps the most important engineering steps visible without collapsing them into generic bullet lists.
01
Recall
Load recent turns and long-term facts under a bounded context budget.
Supabasetoken budgeting
02
Route
Classify the query into a safe execution path and reject non-psychology requests.
OpenAILangGraph
03
Retrieve
Resolve user identity, fetch prediction context, or expand into corrective search when internal evidence is weak.
SupabaseTavilyChroma
04
Synthesize
Generate grounded explanations, then persist cache hits and memory-worthy facts for future turns.
OpenAILangGraph
Timeline
A case-study flow that explains how the system took shape
This timeline keeps the implementation story concise: what was framed first, what was hardened next, and what ultimately made the project production-ready.
01
Phase 01
Domain-bounded assistant design
Constrained the assistant to psychology and MindMirror contexts before retrieval logic was added.
02
Phase 02
Memory and cache personalization
Introduced short-term recall, long-term fact distillation, and semantic cache reuse for repeated queries.
03
Phase 03
Operational instrumentation
Added streaming graph visibility and observability hooks to support debugging and cost inspection.
Challenges
Technical constraints, decisions, and the reasoning behind them
Each challenge is tied to a concrete design choice and a specific outcome.
Solution
Added layered routing constraints, a fixed safe route set, and reject paths before retrieval and synthesis.
Outcome
Improved trust and reduced generic-chatbot drift.
Solution
Separated short-term memory from distilled long-term facts and enforced a strict recall budget.
Outcome
Maintained personalization without degrading answer quality.
Solution
Combined exact cache keys with semantic similarity matching scoped by user, route, and context hash.
Outcome
Improved repeat-query efficiency while staying personalized.
Results
Metrics and outcomes presented for quick technical review
The emphasis here is signal, not decoration: key numbers, verifiable outcomes, and the context needed to interpret them responsibly.
7nodes
Execution Graph
Recall through memory write-back in a reusable LangGraph flow.
5
Route Types
Direct, RAG, memory, web search, and reject.
500tokens
Recall Budget
Memory context stays constrained and intentional.
30 / 90d
Memory Policy
Short-term turns plus 90-day long-term fact retention.
Key Results
- Built a guarded conversational layer over structured MindMirror prediction outputs.
- Implemented a 7-node LangGraph workflow with routing, memory, cache, retrieval, and write-back stages.
- Enabled user-scoped explanations through Supabase-backed retrieval and hybrid memory.
- Improved repeat-query efficiency with cache reuse and weak-context correction paths.
Business Impact
Product value
Turns raw behavioral inference tables into an explainable conversational experience that feels more useful to end users.
Engineering value
Shows a mature AI system design mindset: scoped behavior, explicit routing, memory policy, observability, and fallback control.
Continue