Writing
Notes from the middle layer.
Essays on AI agents, the engineering around them, and the design choices that make software feel calm.
I cloned a shipping coding agent and read it the way I read a paper — to see which design decisions survive contact with production. Here are the ones worth stealing.
EngineeringWhen an agent misses a case, the reflex is to teach it that case in the system prompt. That's whack-a-mole. The fix is structural.
EngineeringLoop engineering took off in coding because coding ships with a free oracle. Everywhere else, you have to build one.
EngineeringA daily digest agent reported "all sources fetched" — while quietly dropping one. The bug wasn't the fetch. It was the missing guardrail.
EngineeringThe thing worth getting right keeps moving up a level — prompt, context, harness, loop. The hard part was never the while-loop.
EngineeringStop adding a tool for every request. Autonomy is a stack of composition types with two layers of glue, not a single trick.
EngineeringI migrated a production agent onto a server runtime, ran the whole playbook, then rolled it all back. Sometimes the senior move is not adopting the thing.
EngineeringStandard tool-calling can't express composition. So stop picking tools — let the model write the code that calls them.
EngineeringReliable agent UX isn't about preventing errors — it's about making the wrong answer cheap to notice and undo.
DesignEveryone treats agent memory as one framework, and compares the options as if they're rivals. They answer different questions — here's the map.
EngineeringVector RAG, RAGFlow, GraphRAG, PageIndex, an LLM wiki, Obsidian — they get lumped together as rivals. They aren't even at the same layer. A field guide to which one fits which job.
EngineeringI scored two agent frameworks across eleven dimensions. Strip the weights and they tie. The gap was never about quality — it was about who I am.
EngineeringEveryone is racing to build a smarter index. The labs that build the models quietly went the other way — toward plain text the agent reads and tidies itself.
EssayA bigger context window buys you a better goldfish. Persistence is a different problem — and most of the work happens between the prompts.
EssayEvery retry feels free in isolation. Stacked across a session, they are where latency, cost, and confusion quietly accumulate.
Engineering