Ma Chi ·
How to Ensure Quality in AI Software Engineering
AgentsZone's roundtable of 19 AI coding pioneers explores how probabilistic LLM systems can ensure code quality through deterministic constraints and independent validation.
Twenty years in software development across infrastructure, cloud-native, and open banking.
Core thesis: the productivity gap in the AI era comes from institutions, not tools. When the executor shifts from human to Agent, the old institutions designed for humans — code review, manual testing, tacit knowledge passed through conversation — all break down. High-productivity teams share one trait: they’ve built engineering institutions matched to Agent characteristics — closed-loop control (specifications define input, automated verification checks output) and continuous evolution (specifications, tests, and processes themselves must iterate).
This methodology is systematized in the Harness Engineering Playbook, collectively authored by the AgentsZone community, covering the full path from reliable single-Agent programming to multi-Agent parallelism to organization-level governance.
AgentsZone has hosted over twenty seminars, bringing together frontline practitioners from Ant Group, Tencent, Midea, PingCAP, securities firms, K12 education, and civil engineering, covering topics from test constraints and team building to end-to-end delivery and agentic operations.
Articles by Ma Chi
Ma Chi ·
The Missing Role in Software Engineering: Why We Need a Code Supervisor
Lovable, valued at billions, had user debt amounts, home addresses, and API keys extracted in 47 minutes. Software has product managers, architects, developers, testers, and ops — but lacks one role that civil engineering calls a "supervisor."
Ma Chi ·
Learning from PingCAP: Building Your Company's AI-Native Software Team
A response to PingCAP CTO Edward Huang's "Vibe Engineering 2026.1." Huang rewrote TiDB's PostgreSQL compatibility layer with AI, achieving near-production quality code. But he spends 90% of his time evaluating AI output. How do ordinary teams replicate this?
Ma Chi ·
Forward Deployed Engineer: Silicon Valley's Rebranded Delivery Consultant
In 2025, Silicon Valley is swept up in a Forward Deployed Engineer (FDE) hiring frenzy. OpenAI, Anthropic, Databricks and others are all recruiting FDEs. Is this genuinely new, or just a fancy name for the traditional delivery engineer?
Ma Chi ·
Alibaba's qwen-code Was Too Hasty
Alibaba's qwen-code CLI is a fork of Google's Gemini CLI. Legally fine under Apache 2.0, but from a product management perspective, this was a rash decision. Users discovered the /init command still generates GEMINI.md instead of QWEN.md — a leftover from an incomplete fork audit.
Ma Chi ·
Using Iterative Methodology to Deliver Industrial-Quality Software with AI
Complaints that AI-written code is unusable? The problem is not correctly applying iterative methodology. Iteration means repeatedly approximating a fixed goal through multiple attempts. In software development, iteration applies to every stage — from requirements to implementation and testing.