Sifu Quest
Client project: Sifu Quest (Project Owner)
Technical Deep Dive
Built an AI-powered career coaching platform with multi-provider LLM orchestration (Anthropic + OpenRouter), 5 specialized coaching modes, persistent memory system, and enterprise-grade security on Next.js 16 + Supabase.
Client Context
Career-seekers needed personalized AI coaching across DSA, system design, interview prep, job search, and business ideas — with persistent memory and multi-model flexibility.
Execution
Designed a provider abstraction layer supporting Anthropic and OpenRouter with intelligent fallback routing, BYOK encryption (AES-256-GCM), dynamic prompt assembly from user memory files, and SSE-based streaming with provider-specific parsers and optimistic UI updates.
Outcome
Reduced Time to First Token from 3-4s to 1-2s through parallelization, prompt caching, and eager triggering. Implemented GDPR-compliant data architecture with Row Level Security, sliding-window rate limiting (30 req/min), and Sentry observability across Client/Server/Edge runtimes.
“Architected multi-provider AI coaching platform with real-time SSE streaming, achieving 50-60% TTFT improvement (3-4s → 1-2s) and 90% prompt cache hit rate through 5 layered optimizations.”
Core Stack
Metrics
ttft_improvement
50-60%
cache_hit_rate
90%
coaching_modes
5
rate_limit
30 req/min