Millan Kaul

Blogs

Recent posts

I made AI Judge - Day 06

less than 1 minute read

Evaluating the logic behind having an LLM judge another LLM’s output. Establishing a helpfulness rubric and confronting definitions.

Five examples are enough to start - day 04

less than 1 minute read

You don’t need thousands of test cases to begin. Five carefully chosen examples are more than enough to boot up your AI evaluation pipeline.

I tested a longer prompt - day 03

less than 1 minute read

Increasing the complexity of prompt inputs to see how the LLM judge responds and analyzing its limits when prompt length grows.

My first AI eval was boring - day 02

less than 1 minute read

Setting up a basic LLM evaluation only to find the initial results predictable, but discovering why simple tests are the best place to start.

Why AI Agents Need a Test Harness

4 minute read

AI agents do not become reliable because the model is bigger. They become reliable because the harness around the model is testable, observable, and continuo...

Where MCP Shines

less than 1 minute read

“Single LLMs hallucinate. Multi‑agent systems multiply the problem.”

How MCP Works?

1 minute read

“MCP handshake → tool call → your code runs. 3 minutes to understand.”

Why MCP?

1 minute read

“Last week my LLM swore the 2024 World Cup winner was ‘Moon United FC’. It was confident, detailed, and 100% hallucinated.”

When to Use MCP?

1 minute read

MCP = LLM lifeline when models hallucinate most.

What is MCP?

1 minute read

Model Context Protocol (MCP) = Standardized way for LLMs to discover and call your external tools/data.