AI-native engineering consulting
Helping engineering teams ship dramatically faster with AI-native tooling.
I'm Wei Sun, CTO at Arcade. I work hands-on with engineering teams to install a practical AI coding workflow — Claude Code, Conductor, CodeRabbit — then train the engineers and set the operating rules so the speed holds up in review.
What an engagement looks like
Every engagement starts with a short call and ends with your team running the system without me.
-
Diagnostic call 30 minutes
We map where your team actually loses time — drafting, review, merge flow, or tooling gaps. No prep required, and you'll leave with a clearer next step either way.
-
Scoped plan about a week
You get a concrete written proposal: which tools, how they fit your codebase and review process, the rollout sequence, and what it will cost.
-
Deployment and training 2–4 weeks
I configure the stack against your actual repositories, train your engineers, and hand off a written operating playbook — running system, not slide deck.
After handoff, ongoing advisory is available month to month — refining prompts, review policy, and tool choices as the stack evolves. Optional, and only if it makes sense for your team.
The stack
I recommend and configure the tools I use every day in my own engineering work.
Claude Code
Agentic coding in your codebase. I set up project conventions, permissions, and workflows so agents produce code your senior engineers are willing to merge.
Conductor
Running multiple coding agents in parallel, each in its own isolated workspace — so one engineer can drive several workstreams without the sessions colliding.
CodeRabbit
AI review in your pull-request flow. Configured well, it holds the quality bar so faster output doesn't turn into review chaos.
Plus the surrounding process: review policy, usage norms, and quality guardrails. The tools change fast — the operating model is what keeps working.
About Wei
I'm CTO at Arcade, where I lead engineering and ship product daily with the same AI-native workflows I help other teams adopt. Before that, I was CTO and then CEO of Upduo, which was acquired by Arcade in 2025. Earlier in my career, I worked on machine learning at Apple.
I studied at MIT and have spent my career at the intersection of engineering leadership and applied AI. When agentic coding tools started getting good, I didn't delegate the evaluation — I rebuilt my own workflows from scratch, found what works, and systematized the results into repeatable playbooks.
Now I help other engineering leaders do the same thing, without the months of trial and error.
- Current
- CTO, Arcade
- Previously
- CTO & CEO, Upduo (acquired by Arcade, 2025)
- Earlier
- Machine Learning, Apple
- Education
- MIT
If your team has AI seats but delivery hasn't changed, let's talk.
Email a few lines about your team and where delivery feels slow. I'll reply with an honest read on whether I can help — typically within one business day.