series about Reinforcement Learning (RL), following Sutton and Barto’s famous book “Reinforcement Learning” [1]. In the previous posts we finished dissecting Part I of said book, which introduces fundamental solution techniques which form the basis for many RL methods. These are: Dynamic Programming (DP), Monte Carlo methods (MC) and Temporal Difference Learning (TD). What separates …

Introduction to Approximate Solution Methods for Reinforcement Learning Read More »

Image by Editor   Contents# Introduction# 1. OpenClaw# 2. OpenHands# 3. browser-use# 4. DeerFlow# 5. CrewAI# 6. LangGraph# 7. OpenAI Agents SDK# 8. AutoGen# 9. GPT Researcher (~26k ⭐)# 10. Letta# Wrapping Up # Introduction  If you want to learn agent engineering by doing instead of just reading about it, the best way is still to fork real repos, run them locally, and change them for your own …

AI Engineering Hub Breakdown: 10 Agentic Projects You Can Fork Today Read More »

(TFL) is a statutory body responsible for London’s public transport network, managing buses, the Underground, Docklands Light Railway, Overground, and major roads. Their ‘Open Data’ policy means that they share much of their internal data with the public, which they say is currently powering over 600 apps for Londoners. One interesting data source they share …

Using Causal Inference to Estimate the Impact of Tube Strikes on Cycling Usage in London Read More »

Image by Author   Contents# Introduction# Choosing A Local Artificial Intelligence Coding Assistant# Meeting The Prerequisites# Following The Step-By-Step Setup Guide# Configuring OpenCode To Use Ollama And Qwen3-Coder# Using OpenCode With Your Local Artificial Intelligence# Understanding The OpenCode And Ollama Integration# Exploring Practical Use Cases And Examples# Troubleshooting Common Issues# Following Performance Tips For A Smooth Experience# Wrapping Up # Introduction  We live in an exciting era …

Seeing What’s Possible with OpenCode + Ollama + Qwen3-Coder Read More »

a second: as a data scientist, you’ve been through this scenario (chances are, more than once). Someone stopped you mid-conversation and asked you, “What exactly does a p-value mean?” I am also very certain that your answer to that question was different when you first started your data science journey, vs a couple of months …

What Does the p-value Even Mean? Read More »

Image by Author   Contents# Introduction# Understanding Why Local AI Matters for Customer Data# Transcribing Audio with Whisper# Analyzing Sentiment with Transformers# Extracting Topics with BERTopic# Building an Interactive Dashboard with Streamlit# Reviewing Practical Lessons# Conclusion # Introduction  Every day, customer service centers record thousands of conversations. Hidden in those audio files are goldmines of information. Are customers satisfied? What problems do they mention …

I Vibe Coded a Tool to That Analyzes Customer Sentiment and Topics From Call Recordings Read More »

Today in the Gemini app, we’re unveiling a new image editing model from Google DeepMind. People have been going bananas over it already in early previews — it’s the top-rated image editing model in the world. Now, we’re excited to share that it’s integrated into the Gemini app so you have more control than ever …

Image editing in Google Gemini gets a major upgrade Read More »

In my last article, I shared how to use MCP to integrate LLMs into your full data science workflow. I also briefly mentioned another .  A skill is a reusable package of instructions and optional supporting files. It helps AI handle a recurring workflow more reliably and consistently. At a minimum, it needs a SKILL.md …

Beyond Prompting: Using Agent Skills in Data Science Read More »

Image by Editor   Contents# Introduction# Understanding Why This Stack Works# Reviewing Prerequisites# Step 1: Installing uv# Step 2: Creating a New Project# Step 3: Adding Dependencies# Step 4: Configuring Ruff (Linting and Formatting)# Step 5: Configuring Ty for Type Checking# Step 6: Configuring pytest# Step 7: Examining the Complete pyproject.toml# Step 8: Writing Code with Polars# Managing the Daily Workflow# Changing the Way You Write Python with …

Python Project Setup 2026: uv + Ruff + Ty + Polars Read More »

Today, we’re introducing Gemini 3.1 Flash TTS, the latest text-to-speech model that delivers improved controllability, expressivity and quality — empowering developers, enterprises and everyday users to build the next generation of AI-speech applications. Starting today, 3.1 Flash TTS is rolling out: Improved speech quality and controllability We’ve improved the overall speech quality of Gemini 3.1 …

Gemini 3.1 Flash TTS: New text-to-speech AI model Read More »