Architecture

Written with Claude. Writing the Counterfactual Made the Answer Obvious The problem we were solving is simple to state: every piece of equipment in an engineering assessment report needs a defensible replacement cost. Where did that number come from? How confident are we in it? Could a client or a peer reviewer trace it back to a source? Answering those questions for hundreds of items across dozens of projects is the whole job. The system we built to do it had one sentence at its core: put the correct number into a file safely. ...

Written with Claude. The direction I wasn’t using Last week I wrote about the spec-to-kill method. Short version: I had an MCP server I’d built six months earlier, cargo-culted into eleven tools, genuinely useful but Rube Goldberg. I couldn’t decide whether to clean it up or rip it out. So Claude and I specced the best possible version (handler separation, schema validation, four clean tools), and then I asked whether even the ideal version earned its keep. The answer was no. grep handled the dataset. The spec became the teardown blueprint. ...

Written with Claude. The Swiss army knife you have to hold a certain way I run a field data collection platform for building assessments. The app has AI agents that look up equipment costs, write condition narratives, validate data, and generate reports. Those agents need to find cost records in a database, do deterministic math (no LLM arithmetic on dollar amounts), and write results back to a JSON file. ...

I built Memory Bank for my home infrastructure repo. Three months later, I finally applied it to the system that actually makes money. Then during a real project, the whole data architecture changed.