Vinay C · Staff Software Engineer · Intuit
The hard part of AI isn't the model. It's everything around it.
I'm Vinay — 14 years, five companies, tens of millions of users. I build the evaluation harnesses, golden datasets, and guardrails that make generative and agentic AI trustworthy in production. Everything I learn goes into the notebook below, free.
Latest from the notebook
All notes →RAGA Framework, Part 7: Beyond RAG: Evaluating AI Agents with Ragas
Part 7 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 6: Who Evaluates the Evaluator? The Limits of LLM-Based Metrics
Part 6 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 5: How to Fix a RAG Pipeline Using Evaluation Results
Part 5 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 4: Your Evaluation Is Only as Good as Your Test Data
Part 4 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 3: Evaluating a RAG Pipeline with Ragas: A Minimal Working Example
Part 3 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 2: Four Metrics That Reveal Why Your RAG System Is Failing
Part 2 of a series on evaluating LLM apps with Ragas.
NotesRAGA Framework, Part 1: Why and how can you evaluate your LLM App?
Part 1 of a series on evaluating LLM apps with Ragas.
Models are commodities. Judgment is not.
The advantage was never the LLM you picked. It's the eval harness, the golden datasets, and the guardrails that tell you — reliably, daily — when the system is wrong.
Work with me
For teams
Consulting
RAG evaluation, agentic systems, architecture reviews, and getting a team productive with AI tooling — grounded in what actually breaks in production.
Consulting →For engineers
Mentoring
A resume torn apart, real mock interviews, and someone keeping you honest month to month as you move into AI engineering.
Mentoring →For hiring managers
Track record
Case studies of work shipped at Intuit, Microsoft, and SAP — GenAI regression evaluation, platform reinvention, and a granted patent.
Case studies →