2 posts tagged with "llm"

We're in the "vibe coding" era. AI coding agents — Cursor, Claude Code, Copilot, Devin, and their growing kin — are no longer writing toy snippets. They're scaffolding entire features, refactoring modules, and wiring up API endpoints in seconds. The promise is intoxicating: describe what you want, get working code.

The reality is more nuanced. These agents are prolific, but not infallible. They hallucinate API signatures. They skip edge cases. They introduce subtle bugs that compile cleanly and pass a first glance. And crucially, they do all of this fast — far faster than any human code review can keep up with.

So here's the question that matters more than ever: what catches the mistakes an agent makes?

Large Language Models have shown the world its incredible versatility. One of its most remarkable powers is to turn fuzzy human language into executable code. This not only helps engineers improve their productivity but also enables non-technical people to achieve what used to require help from developers.

Generating analytical data queries is one of the most popular use cases of LLM-based code generation. What can be cooler for business analysts than to ask a question in plain human language and get a visualization in seconds? Traditionally, only big boys like PowerBI and Google Sheets could offer features like that, but now LLM has democratized AI capabilities and lowered the bar. In this post, I'll demonstrate a simple implementation and will also cover an important but often overlooked topic: access control.