Kartik N V J K (@kartik-nvj)

I write when an idea won't leave me alone 🧠 Building AI agents and the tools to build AI agents. Love connecting AI with other fields and yapping about all of them. Follow along if that's your kind of thing.

Kartik N V J K

About

Available for

Kartik N V J K's blogs

My agent said the refund went through. The ticket went to the one team that could not fix it.

I captured a hundred agent failures a week and fixed three. The bottleneck was curation.

Eval the Signature, Not the Program: How I Fixed My DSPy Evaluation

My CI evals were green. A regression still paged me at 3 AM.

LlamaIndex makes RAG easy to build and hard to debug. Here is how I evaluate it.

Kartik N V J K

About

Available for

Kartik N V J K's blogs

My agent said the refund went through. The ticket went to the one team that could not fix it.

I captured a hundred agent failures a week and fixed three. The bottleneck was curation.

Eval the Signature, Not the Program: How I Fixed My DSPy Evaluation

My CI evals were green. A regression still paged me at 3 AM.

LlamaIndex makes RAG easy to build and hard to debug. Here is how I evaluate it.

Kartik N V J K

About

Available for

Kartik N V J K's blogs

My agent said the refund went through. The ticket went to the one team that could not fix it.

I captured a hundred agent failures a week and fixed three. The bottleneck was curation.

Eval the Signature, Not the Program: How I Fixed My DSPy Evaluation

My CI evals were green. A regression still paged me at 3 AM.

LlamaIndex makes RAG easy to build and hard to debug. Here is how I evaluate it.

Search Hashnode

Kartik N V J K

About

Available for

Kartik N V J K's blogs

My agent said the refund went through. The ticket went to the one team that could not fix it.

I captured a hundred agent failures a week and fixed three. The bottleneck was curation.

Eval the Signature, Not the Program: How I Fixed My DSPy Evaluation

My CI evals were green. A regression still paged me at 3 AM.

LlamaIndex makes RAG easy to build and hard to debug. Here is how I evaluate it.