Deliverables
- OCR and summarization pipelines for documents and images
- Schema-based structured output and validation
- Caching, retries, cost control, and quality logging
- Admin review flows and user-facing result screens
Back to services
Service
AI and LLM Automation Development
Connect document summarization, OCR, structured generation, and search assistance into real product workflows.
LLM calls are turned into product data pipelines with schemas, caching, validation, and operational logs.
Expected Outcomes
- Automate repetitive document processing
- Stabilize LLM output as product data
- Control cost and latency for production usage
Core Technologies
LLMOpenAI APIClaude VisionOCRNestJSPython
Related Projects
Own productSelf-planned, launched, and operated
JodalN
A production-grade public procurement SaaS that collects Korean G2B bid data, summarizes attached documents with LLMs, and supports high-speed search.
Proof
Cloud SQL snapshot (2026-08-26): recorded 135,997 instrumented user activities and 830,889 live bid-notice rows
Next.js 15NestJS 11TypeScriptPrismaPostgreSQLLLM+4
Status: Live
Own productSelf-planned, launched, and operated
PourLog
A six-language coffee tasting SaaS across iOS, Android, Web, Admin, and API, with OCR-assisted record creation and a TypeScript monorepo.
Proof
Built iOS, Android, Web, Admin, and API surfaces from one product architecture
ExpoReact NativeTypeScriptNestJSNext.jsPostgreSQL+4
Status: Live
Own productSelf-planned, launched, and operated
Redictionary (WordBrain)
An AI-powered English-Korean vocabulary learning service combining structured dictionary generation, Redis caching, TTS audio, and quizzes.
Proof
Built a full-stack vocabulary service with React, NestJS, Redis, OpenAI, and Google Cloud
NxTypeScriptReactViteNestJSRedisJSON+4
Status: In Development / deployment history