Hello, I'm Vikram Rao

A static portfolio has exactly one job — presenting information. I hit the same wall three times trying to make this one do more, and each time the fix looked the same before I'd even planned it that way.

The first cover-letter generator worked in an afternoon and was wrong in ways I didn't notice until much later. This is the story of the two separate times it broke, and what each one taught me about not trusting a model with the truth.

Giving an AI agent real access to a repository is fine, until you can no longer tell whether it acted or just proposed. Here's how I built the scaffolding that keeps that line visible — and where I got it wrong before I got it right.

Every time I added a new Claude call site, I wrote the same five lines of plumbing again and told myself it was fine because the feature was different. By the fourth time, it wasn't fine anymore — and the fix wasn't "write a better prompt."

`structuredGenerate()` fixed how a Claude call is shaped. It said nothing about what gets fed into one — and that turned out to be the harder problem, one I'd already half-solved by accident in the tables I'd built for an entirely different reason."

Structured data tells you what's true. It doesn't tell you how much of it to show a model, or in what order — and the two times I got that wrong looked nothing alike on the surface, but broke for the exact same reason.

A single well-crafted prompt has no seam to insert a check into. The moment I split one into named stages, I got something a prompt can never give you — a place to put a gate before the output ever reaches anyone.

A pipeline stops a model from deciding what's true. It doesn't automatically tell you why any given decision came out the way it did — and the honest version of that answer includes a security gap I've narrowed but not closed.