· Ruby Jha · architecture-decisions
The Decision Chain That Got Structured Output to 100%
How Instructor, flat schemas, and two-phase validation got me to 100% structured output success across 580 LLM-generated records.
Tag: synthetic-data
- · Ruby Jha · project-deep-dives
How I Calibrated an LLM Judge That Approved Everything
My first LLM judge had a 0% failure rate. That meant it was useless. This is the story of calibrating it to actually catch failures, and building a correction loop that took synthetic data failures from 36 to zero.
- · Ruby Jha · project-deep-dives
Building 9 AI Projects (While Working Full-Time)
Why I am building 9 AI systems from scratch while working full-time as an Engineering Manager. The portfolio, the progression, and what I have learned so far.