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 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.
LLM FundamentalsZero Token Architecture: AI engineers should always start with this!
This weekend I watched this talk on Zero Token Architecture:
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 →