Flutter App Delivery
Business screens, state management, API integration, media upload, edge states, and Android/iOS/OHOS release adaptation.
Jacky Chou
Flutter / Android / Java / AI Engineering
Since 2015, I have delivered production-facing mobile apps and business systems across Flutter, Android, Java backends, admin platforms, RAG knowledge bases, and MCP/Agent workflows.
I focus on complete delivery: product flows, native capabilities, backend APIs, AI boundaries, real-device verification, and deployment evidence.
11+ yrs
App and business system delivery since 2015
Full-stack
Flutter, Android, Java backend, Vue admin
AI-ready
RAG, MCP, Agent workflows, local LLM validation
Capability Matrix
A practical stack for shipping client-ready products: mobile experience, native capability integration, backend systems, AI boundaries, and delivery evidence.
Business screens, state management, API integration, media upload, edge states, and Android/iOS/OHOS release adaptation.
Permissions, camera, location, QR scanning, push, sharing, WebView/MethodChannel, Gradle builds, and real-device debugging.
RAG, embeddings, pgvector, OpenAI-compatible providers, local models, MCP tools, Agent workflows, and human handoff boundaries.
Selected Work
The selected cases emphasize responsibility, architecture, AI control boundaries, native app capabilities, and validation signals.
Primary Flutter Case
Flutter / Android / iOS / OpenHarmony
A multi-platform B2B Flutter app covering property listings, customers, workbench, messages, profile flows, native capabilities, and release verification.
Real-device screenshots and release evidence
Mainstream app capability coverage
Native Android capability integration
AI Workflow
Flutter + Vue + Spring Boot + RAG
An AI-first support workflow where knowledge-base answers are attempted first and low-confidence or out-of-scope questions move into human tickets.
Controlled AI response boundaries
Human handoff and audit trail
Reusable MVP pattern for small businesses
AI Data Product
Flutter + Spring Boot + LLM
A data-to-report workflow that uploads CSV/Excel files, computes metrics asynchronously, and generates reviewable Chinese business reports.
Backend-owned metric calculation
Reviewable AI narrative generation
OpenAI-compatible and local model validation
Knowledge AI
Spring Boot + pgvector
Document upload, chunking, embeddings, Top-K retrieval, source citation, and out-of-scope handling for enterprise knowledge Q&A.
Source-backed answers
Out-of-scope protection
Reusable enterprise Q&A base
Java Full-stack
Spring Boot + Vue Admin
A reusable operations platform base covering authentication, RBAC, audit trails, customers, tickets, approvals, and smoke validation.
Reusable backend starter pattern
Admin workflow and API integration
Docker and smoke-test evidence
Proof Evidence
The portfolio is structured around evidence: delivery scope, architecture, validation, AI boundaries, and communication-ready project narratives.
Case studies include screenshots or productized visuals, architecture nodes, validation evidence, and role boundaries.
AI cases emphasize source citations, out-of-scope handling, human handoff, and replaceable model providers.
Mobile apps, Java backends, Vue admin systems, RAG, Agent workflows, deployment, and verification are presented as one delivery system.
Core case-study repositories are kept private to protect project context, but code, commit history, build logs, and runtime evidence can be shared through authorized review when needed.
Contact