Building Apps for Startups with Ademar Tutor

How should an AI agent do machine learning for someone who can't check its work?

Three ways an agent can do machine learning for you, and what I built to test the third one.

Jul 19 • Ademar Tutor

April 2026

Don't Remove the Human From the Loop. Give Them a Better Role.

How test-driven machine learning made AutoML usable for people with zero data science background

Apr 3 • Ademar Tutor

1

March 2026

AI agents work better when you give them less freedom

A neuroscience paper showed me how to build better AI data teams for businesses.

Mar 24 • Ademar Tutor

January 2026

Deploying a full-stack LLM judge system on Azure Container Apps

I wanted to deploy the LLM-as-a-Judge I recently developed.

Jan 30 • Ademar Tutor

Prompt templates evaluation contracts

Versioned rubrics in the database

Jan 22 • Ademar Tutor

LLM-as-a-Judge Offline Evaluation for Ordinal Scores

Pearson r + QWK + ±1

Jan 17 • Ademar Tutor

3

LLM-as-a-Judge for Sales Coaching

Designing an Auditable Evaluator Pipeline

Jan 9 • Ademar Tutor

3

December 2025

Vibe Coding 2025: Context Engineering, DAGs, and the Shape of Modern Coding

A Coder’s Review of Cursor from Chat Prompts to Agentic Workflows

Dec 27, 2025 • Ademar Tutor

1

August 2025

Is Today a Good Day to Sell Coffee?

A Beginner’s Guide to Decision Trees

Aug 14, 2025 • Ademar Tutor

2

June 2025

Design Thinking–Driven: From ML Ops to AI Engineering

How ML Teams can thrive in the Age of Plug-and-Play AI

Jun 30, 2025 • Ademar Tutor

1

March 2025

February 2025