Building Cool Stuff with AI – Landeros Labs

Automating B2B Lead Generation with AI and Intelligent Regex

A technical deep dive into building LNKD-AI, a browser-based automation tool for high-precision data enrichment.

Summary of Chapter 3: Finite MDP

RL

This chapter formalizes the reinforcement learning problem using the framework of Markov Decision Processes (MDPs).

Summary of Chapter 2: 10 arm testbed

RL

Notes based on the book Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.

Summary of Chapter 1: The Reinforcement Learning Problem

RL

Notes based on the book Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.

LinUCB for ad selection

RL

This guide details the Contextual Upper Confidence Bound (LinUCB) algorithm.

Building collaborative and content based reccomendation systems

Reccomendation

Imagine you’re scrolling through Netflix, trying to decide what to watch. Netflix shows you personalized recommendations - movies and shows it thinks you’ll love. How does…

Building a Dual-Pipeline Name Anomaly Detection System with FAISS and Embeddings

Vector

Detecting synthetic identities at scale using semantic embeddings and character-level features

Tesseract vs. EasyOCR — From Quick Wins to Robust Pipelines

OCR

Tesseract

I wrote this post because I had to re-learn OCR recently. I kept forgetting the details, configs, and gotchas — so this is my reference to stay sharp. If you’re in the same…

Building Real-World AI Systems with PydanticAI: Lessons from Anthropic’s Agent Design Patterns

Agents

Pydantic

As AI continues to reshape industries—from legal and healthcare to marketing and customer service—developers face a growing need to build robust, modular, and intelligent…

Level Up Your SmolAgents: Practical Patterns for Building Effective Agents

Agents

The world of AI is buzzing with excitement about agents, and rightfully so. However, amidst the hype surrounding complex frameworks and specialized libraries, a crucial…

Building Intelligent Customer Service Agents with Pydantic-AI and LLMs

Agents

Man I was blown away by how simple and effective building agents in pydantic has been for me this weekend.

Marketing Mix Model Comparison

Marketing

Imagine trying to bake a cake without knowing how much flour, sugar, or eggs to use. You might end up with a disaster! Similarly, in marketing, blindly allocating budgets…

Identifying Fraud with Isolation Forest

Fraud Detection

Fraud detection is a critical task across various industries, from finance to e-commerce. Traditional rule-based systems often struggle to keep up with the evolving tactics…

Email Campaign Effectiveness Predictor

Marketing

RandomForest

In this blog post, we’ll develop a model that predicts the likely open rates, click-through rates, and conversion rates for email campaigns based on historical data and…

Markov decision process intuition - marketing example

Graph

Markov

Markov Decision Processes (MDPs) might sound like a complex mathematical concept, but they’re incredibly useful for making decisions in uncertain environments. In this post…

ad-optimization-with-multi-armed-bandits

Imagine you’re running a website with multiple ad variants. Which ad should you show to maximize clicks? This is a perfect application for the multi-armed bandit (MAB)…

Building and Optimizing a Customer Segmentation Model

Marketing

In today’s data-driven marketing landscape, understanding your customers is crucial for tailoring effective marketing strategies. One powerful technique for gaining these…

Understanding Multi-Armed Bandits: A Gateway to Reinforcement Learning

MAB

Multi-armed bandits (MAB) represent one of the simplest yet most profound examples of the exploration-exploitation dilemma in reinforcement learning. In this blog post…

Understanding Markov Decision Processes in Deep Reinforcement Learning

DRL

Markov Decision Processes (MDPs) form the theoretical backbone of modern reinforcement learning, including deep reinforcement learning. In this post, we’ll explore how MDPs…

The Bellman Equation: The Foundation of Deep Reinforcement Learning

RL

MDP

The Bellman equation, named after Richard Bellman, is one of the most fundamental concepts in reinforcement learning. It provides a recursive relationship between the value…

Reinforcement Learning: A Comprehensive Overview

RL

These equations form the foundation for many RL algorithms, which aim to find or approximate the optimal value functions and, consequently, the optimal policy.

Marketing Mix Modeling

Marketing

Marketing Mix Modeling (MMM) is a powerful technique used to measure the effectiveness of various marketing activities and understand how they contribute to sales or other…

Quant Trading: Asset Class Selection

Trading

As a seasoned quantitative trader who relies on statistical analysis to thrive in the dynamic world of trading, one of the fundamental questions that drives my strategy is…

Scraping home prices in Ensenada Mexico

Nestled in the heart of Ensenada, Baja Califronia, Mexico is an amazing port city that has always been a part of my life,(since Covid) I’ve built a home that is not just a…

Learning Statistics and Probability with SciPy and Python

Statistics

This Jupyter Notebook provides a comprehensive guide to the fundamentals of statistics and probability, using SciPy and Python for practical implementation and visualization.