Thoughts on software engineering, payments, and building products.
Money movement is largely irreversible, which makes payments one of the harder places to point an autonomous agent. Here is how I currently think about putting one there safely.
An agent is only as capable as the tools you give it, and tools are where the real engineering — and the real risk — lives. How I build safe, focused MCP tools for payment operations.
Agents produce code faster than anyone can read it, and the deepest cost is comprehension debt, not bugs: software that runs while no one understands it. Verification can let you trust code you never read; that is necessary, and it is not the same as understanding it. What property-based testing, simulation, and proof can buy, and what they can't.
Five agentic coding patterns I keep reaching for — sequential, operator, split-and-merge, agent teams, and headless — plus the machinery (CLAUDE.md, subagents, slash commands, plan-first) that makes delegation repeatable and verifiable.
Why a one-shot RAG pipeline hit its ceiling on real regulatory questions, and how rebuilding Ordinance as an agent put the engineering in the harness around the model.
The model is just one input into a running agent. The harness around it — prompt, tools, context, subagents — is the engineering discipline that decides whether an agent ships.
How I built Ordinance — a retrieval-augmented generation system that answers questions about HK compliance with cited, verifiable responses across 224 government documents.
Welcome to my blog. I'll be writing about software engineering, payments, and building products.