AI Engineer — agentic systems & trustworthy AI. I put agents inside messy enterprise work — legacy migration, QA, banking, internal tooling — and make the result governed, verifiable and production-grade, with a multi-agent engineering team that runs around the clock under my own operating process. Not demos.
I'm an AI engineer in Vietnam who deploys agents into real engineering work — not demos. My strongest work lives where AI meets messy reality: automating a legacy-to-microservice migration across dev and prod, building the agentic engine of a commerce platform, and taking a multi-agent banking system from zero to a national Top 7 in 48 hours.
I don't just use AI to code — I run a multi-agent engineering team around the clock: architect, backend, frontend, tester and security as governed AI roles under an operating process I wrote myself. Blocking quality gates, author-never-checks-their-own-work, and every recurring failure becomes a failing test. Background spans computer vision and cloud-native MLOps; I contribute upstream to OpenCode (174k★).
Not ten side projects. The same written process — architect, backend, frontend, tester, security as governed AI roles — pointed at ten different problems. Here are eight of them plus the writing — what each one is, then the screen itself. About a minute.
Four roles, one thread: taking work that was manual, messy and high-risk, and making an agent do it under gates a human can audit.
Each of these exists because a process needed to run without me watching it.
A digital bank branch run by a team of AI experts (credit, legal, product, ops), judged live on stage. Approval gates enforced at the tool layer, a source reference on every number, full trace on every step. ~35k LOC, 202 commits in ~40h. Watch the demo ▶ · Code ↗
A messaging network where AI agents plug in as contacts. Go control plane: signed-webhook delivery with retries & circuit breakers, fixed block vocabulary (agents can't draw their own approve buttons), append-only hash-chained ledger, atomic in-ledger settlement.
Fresh agents run task batches, deterministic checks plus a calibrated scorer (94% agreement with human verdicts) grade them, batched edits pass a strict accept/reject gate, and the result is certified on locked test sets. Trained 5 banking-CRM skills to the domain's 85% bar; the framework caught 10 of its own harness bugs before they could corrupt a score. Runs on a subscription runtime — a ten-task round costs essentially nothing beyond ~3.5 minutes.
Personal AI operating system — project / finance / automation tracing OS built in ~11 hours across 15 sprints by orchestrating an AI dev team under a self-authored process. 27k LOC, 1,089 tests, 12 modules, 0 live bugs.
Observability + config management over Claude Code sessions: live tracing on SSE, cost and token-burn analytics, and 6 config managers (agents, skills, MCP, plugins, status line, hooks).
AI-agent team orchestrator — Kanban + chat + real-time SSE. Registry pattern: a new specialist team is 1 registry entry + 1 MCP + 1 prompt, zero new code.
"Jira for AI agents" — API test lifecycle (Postman + MCP), human-AI dual path (human owns setup, AI writes test logic), scoped agent tokens, audit trail, PII scrubber (AES-GCM).
Five-phase pipeline (research → personalize → QA → classify → draft) with phase-gated evals. Business logic lives in agent prompts; Python is a thin tool layer — hot-swap subagent ↔ SDK with no call-site change.
The agentic engine of a Direct-to-Consumer commerce platform — the production system behind my current role.
Vietnam AI Innovation Challenge 2026 — NIC · Meta · SHB. Walked in, built a deployed multi-agent banking system in 48 hours, defended it live in front of the judges.
Every one of these is deployed and open right now. Click through and use it.
Top 7 VAIC 2026 — watch the 48h build walkthrough
A network where AI agents plug in as contacts
Shared task board for humans + AI agents — MCP-native
Control plane for Claude Code — tracing, cost, config
Multi-store commerce admin — sessions, deploys, cost
Personal AI-OS — projects, finance, automation
AI that builds & runs a D2C business
Registry-driven AI team orchestrator
QA & governance for AI agents
Agent-first outbound pipeline
What I learned running agents against real deadlines, written down so it's repeatable.
A no-build-first method for scaling solo-founder efficiency — separating the experimental phase from production so you test concepts fast before committing engineering resources.
Read the post MethodologyTools and skills are weights, your questions are the dataset, and the scorer is the loss function — why building an agent is a training run, and why the human holds the key.
Read the post ProcessHow an AI team builds an app end to end without a human blocking the loop — kickoff, sprints, three verify gates, and the genealogy where every rule traces back to a real failure.
Read the post ProcessA training loop for agent skills: fresh agents on task batches, deterministic checks plus a calibrated scorer, batched edits through a strict gate, certified on locked test sets.
Read the postOpen to AI Automation / Solution Architect roles, and to building agent systems that ship real value for engineering & ops teams.