Eric J Ma's Website

In this blog post, I share my experience using a coding agent to build a Bayesian model live, highlighting how agents can dramatically speed up work, but only when paired with real expertise. I found that every prompt I gave was rooted in years of judgment, and the agent amplified my strengths while exposing its own blind spots. Ultimately, the more you know, the more leverage these tools provide. Curious how agents can make your expertise even more valuable, and where they might trip you up? Read on to find out.

In this blog post, I share how my coding agent learned from my mistakes and automatically patched its own skills using a new OpenCode plugin I built called opencode-autolearn. Over ten days, it observed my coding sessions, extracted lessons, and updated its memory and skills without any manual intervention. I explain the architecture, design decisions, and real-world impact, including how it fixed a tricky Convex migration bug on its own. Curious how an agent can truly learn from your workflow and get better every session? Read on to find out!

In this blog post, I share how git worktrees have become my go-to solution for juggling multiple branches without the hassle of stashing, committing unfinished work, or cloning repos. I explain what worktrees are, how they differ from clones, and why they're perfect for quick reviews, hotfixes, and parallel development. I also cover common pitfalls and cleanup tips. Curious how worktrees can simplify your workflow and keep your projects organized? Read on to find out!

In this blog post, I share the key lessons I learned building voice-first AI apps, where voice is the main way users interact. From the importance of documentation and API-first design to the necessity of transcripts and centralized voice operations, I cover what works, what doesn't, and how to debug the invisible. The magic of voice-controlled UIs is real, but so are the engineering challenges. Curious about the pitfalls and breakthroughs of building with voice as the primary interface? Read on to find out more.

In this blog post, I explore the concept of an "agent harness", the combination of tools, environment, hard controls, and soft controls that shapes what an AI agent can and cannot do. I illustrate these ideas with three real-world examples. Curious how these controls impact the behavior and capabilities of different agents? Read on to find out!

In this blog post, I share my three-tier framework for multitasking with agent harnesses: one focused foreground task, one or two lightly supervised background tasks, and as many automated shadow tasks as you want. I explain how each tier works, how notifications keep you in control, and why a simple priority list is still essential. I also discuss how to move tasks down the chain for more effortless productivity. Curious how this system could help you multitask better without feeling overwhelmed?

In this blog post, I share my hands-on experience comparing three coding agent harnesses: Codex, cmux + OpenCode, and Cursor. I break down their features, workspace management, notification systems, automation capabilities, and open source status, highlighting what sets each apart. Curious which harness might boost your productivity or fit your workflow best? Read on to find out!

In this blog post, I reflect on co-teaching a BioIT World workshop about the value of standardizing data science workflows. I share stories from my experience at Moderna, discuss how to choose what to standardize, and highlight the importance of people and culture in making standards stick. I also touch on how evolving technology and AI are lowering the cost of standardization. Curious about where to start and how to get your team on board?

In this blog post, I reflect on the evolving role of data scientists in the age of AI and LLMs. I argue that our core mission remains rigorous measurement, not full-stack development. While AI tools make building easier, the real value comes from defining and evaluating what truly matters. I share why measurement should be led by those closest to the problem and how data scientists can best contribute. Are we losing sight of what makes data science essential in the rush to build with AI?

In this blog post, I share my experiment at ODSC East 2026, where I analyzed talk abstracts to uncover the conference's true zeitgeist. By categorizing sessions into five key zones—agentic AI systems, LLM engineering, data infrastructure, applied AI, and governance—I reveal how AI builder culture is evolving into systems culture. I also reflect on my own workshop experience and the shifting focus from models to repeatable systems. Curious about what trends are shaping the future of AI conferences?