Case studies — Brandon Crenshaw

Case studies — Brandon CrenshawHow the hardest projects were built: the problem, the architecture, the decisions, and the numbers that can be checked.

Lobstack: A receipt for every model call — An OpenAI-compatible gateway whose real output is not the routing. It is the line underneath: which model served the call, what it cost, and what any saving was measured against.

Circuit: The conversation is the canvas — An MCP server that turns a sentence into a workflow board and then runs it one deterministic step at a time — on the connectors you already gave Claude, holding no credentials of its own.

GLOWUP: The app holds no secrets — A consumer photo-analysis app where the phone never sees a model key, every result passes a schema and hard bounds before it is saved, and minors never get a generated image.

ROAM: The model never makes up a number — Travel ranking where deterministic engines compute every score and fact, and the language model may only explain them, with its citations checked against the evidence it was given.

Jobhunter: Retrieval was the easy half — A job-search agent that scored roles with hybrid retrieval, then learned the expensive way that a plausible email address is not a contact. One in four inferred addresses delivered; published ones, nine in ten.