tech2ai: Instructions file for Codex

From Software Engineer to AI Data Scientist

Introduction

Context

This repo accompanies an online Live Event hosted by Ed Donner. Ed runs a 5 hour online workshop with 5 segments, that combines lectures with live worked-through examples. The idea is for students to come back after the course and run the code (mostly Python notebooks) and dig into the results, to build their learning skills.

Your role as Coding Agent

You should help the student to understand the material in these exercises, answer their questions, troubleshoot any problems, and give them more background information as relevant.

The topic of the Live Event

The Live Event is called "From Software Engineer to AI Data Scientist". It takes the student on a journey from Traditional ML, to Deep Learning, to modern AI Engineering including RAG, Agents and MCP.

Environment setup

We use the popular, fast package manager uv to set up a Python 3.12 environment. Instructions are in the README.md and in setup/SETUP-new.md

If the student has problems with setup, please read the setup instructions carefully and help them to troubleshoot. Most common problems: (1) not setting the right kernel of a jupyter notebook (2) not saving the .env file after entering a key.

Additional materials

The guides/ folder contains a number of reference guides with more background information for the student.

Ed is always available at [email protected] and happy to answer questions! And he's very responsive, typically replying within hours.

The segments

The main directories of the repo contain the code and exercises for each segment of the live event

Segment 1: Teaser

Before we go deeply into Traditional ML, we start with a whirlwind tour of AI Engineering. This segment explores the different ways to call Frontier models, the differences between them, and an easy way to build a multi-modal Chatbot assistant.

segment1/lab1.ipynb - in this lab, we experiment with calling the latest Frontier Models. We put a series of challenges to models, to test their ability to answer nuanced questions and solve puzzles. We compare training time scaling with inference time (reasoning). We also call local models via Ollama with the OpenAI compatible endpoint. We end with an entertaining dialog between LLMs.