Eric J Ma's Website

In this post, I share a philosophy on career growth and resilience. Instead of doing the bare minimum or succumbing to frustration, I encourage you to view your work as a personal investment. By doing your best work for yourself, you build professional instincts, a strong reputation, and the character to handle both success and failure. Whether you're navigating a tough job market or rebounding from a mistake, the wealth you accumulate in skills and reputation is yours to keep forever. Ready to invest in yourself?

In this blog post, I share the patterns that have made my experience with coding agents much more productive, from planning with AI and writing docs/tests first, to using AGENTS.md as a knowledge base and leveraging command line tools. I also discuss pacing your agent, letting it write temporary tools, and developing your own productivity boosters. Want to know how these strategies can make your agent-assisted programming smoother and more effective?

In this blog post, I share my journey building a domain-specific statistics agent to help researchers design better experiments, inspired by the challenges of limited access to statisticians in pharma and biotech. I discuss the pitfalls of "folk statistics," the importance of prompt engineering, and the lessons learned through iterative testing and refinement. Curious how an AI agent can elevate experimental design and what it takes to make it truly helpful?

In this blog post, I share how coding agents like Cursor, GitHub Copilot, and Claude Code can access files across your entire file system—not just your current workspace. By simply referencing explicit file paths, you can pull code, documentation, or configs from any repository without complex workspace setups or copying files. I explain practical workflows and tips for cross-repository access, making coding and writing more seamless. Curious how this can simplify your development process and boost productivity?

In this blog post, I share how I discovered PocketFlow, a minimalist framework for building LLM-powered programs using graph-based flows instead of complex loops. By rethinking my approach, I replaced 307 lines of agent orchestration code with just 4 lines, making my agents more modular, clear, and easy to visualize. I walk through practical examples, show how to build and visualize agent architectures, and reflect on the benefits of graph-based thinking for LLM applications. Curious how this shift can simplify your own AI projects?

In this blog post, I share practical strategies for letting coding agents work autonomously while minimizing risks, like setting intelligent boundaries for command approvals, using plan mode, and writing prescriptive prompts. I also discuss real-world lessons learned from agent mishaps and offer tips for managing multiple agents safely. Curious about how to empower your coding agents without losing control?

In this blog post, I share how combining AI coding assistants with Marimo notebooks can supercharge your Python development and data science workflows. I walk through handy features like the `--watch` flag for live updates, the `marimo check` command for code quality, and even advanced options like MCP and built-in AI editing. Curious how you can automate and speed up your notebook workflow while keeping your code clean?

In this blog post, I share my first impressions of Anthropic's skills repository, comparing its token-efficient, customizable approach to the more standardized MCP server model. I break down the strengths and trade-offs of each, from creative workflows to technical utilities, and raise open questions about distribution and cross-vendor support. Curious about which approach might fit your workflow best?

In this blog post, I share what I learned building LlamaBot: the real challenge in AI-assisted development is keeping AI agents up-to-date with evolving documentation. I explain how the Model Context Protocol (MCP) lets LLMs access dynamic, queryable knowledge bases, solving the obsolescence problem and enabling smarter, context-aware AI assistants. Curious how you can make your documentation instantly accessible to any AI agent?

In this blog post, I share my hands-on comparison of DSPy and LlamaBot for building structured LLM applications, using a real-world expense extraction example. I explore how each framework handles schema design, type safety, and prompt optimization, highlighting their strengths and trade-offs. Curious which approach might best fit your next LLM project?