Latest
30
Oct
I Built CLI Tools for Claude Code. Here's What I Learned About Designing for AI Users
I built agent-friendly interfaces for my Python library following every recommended pattern—JSON output, discovery commands, enhanced errors. Then Claude hallucinated flags that don't exist and ignored the documentation I wrote for it.
7 min read
27
Oct
What Top 10% Actually Means (For a Lawyer Who Codes)
177K monthly downloads. Top 10% of 700K packages. Zero revenue, one maintainer, weekend work. Here's what "success" actually means for open source maintainers—and what I'd tell anyone considering building their own tools.
5 min read
21
Oct
Why Prompt Engineering Felt Wrong (And What Skills Changed)
I sat in a standing-room-only prompt engineering workshop feeling anxious—not because I was behind, but because I don't use any of these frameworks. Turns out my instinct was right. That same month, the technology shifted from prompts to persistent agent skills
4 min read
18
Oct
Lawyers Got Prompt Engineering Wrong (And Why That Matters)
At TechLawFest 2025, Singapore lawyers packed a workshop on prompt engineering. Meanwhile, the technology shifted: agent skills became available. This isn't about better prompts—it's about who controls the decision-making logic. From 3-page prompts to reusable systems.
10 min read
10
Oct
Open Source, AI, and Why October Matters
This Hacktoberfest, I'm not contributing code—I'm maintaining my own. Two years after redlines went viral, I'm adapting it for AI agents. The lesson: tools that don't work with AI will fade. Open source needs to evolve with how people actually work.
6 min read
06
Oct
When AI Makes You Look Busy, Not Productive
A new term is making headlines: "workslop"—AI-generated work that looks polished but lacks substance. Research found 40% of workers encountered it last month, costing $186 per employee in cleanup time. For resource-constrained lawyers, you can't spend time fixing what's irretrievably broken.
5 min read
01
Oct
Singapore Court Rules on AI Hallucination: A Reality Check for Small Firms
Singapore's High Court just handed down what might be its first formal ruling on AI-generated fake cases in legal practice (2025 SGHCR 33). For resource-constrained practices, this case validates a hard truth - you might be better off avoiding AI entirely.
4 min read
29
Sep
Beyond the Harvey Drama: The Real Lessons for Solo Counsel
While legal tech Twitter argues about Harvey's performance, solo counsel should focus on the real lesson: Harvey created a replicable blueprint for making AI feel safe and professional to skeptical lawyers. Here's how to apply their approach when evaluating any legal AI tool.
4 min read
22
Sep
The Solo Counsel Reality: What MinLaw's AI Guidelines Miss About In-House Practice
Singapore's AI guidelines assume enterprise resources and committees. But what about solo counsel making real AI decisions with limited budgets and shadow tools? This consultation misses practitioners who need guidance most.
11 min read
20
Sep
AI Just Beat Lawyers (And Why That's Actually Good News)
Most people look for headline numbers when reading surveys. But digging deeper into the preliminary findings from legalbenchmarks.ai reveals possible pathways for legal tech buyers and in-house legal departments.
4 min read