Session 1: Foundations for AI-Assisted Analytics Work

This session uses Codex, a coding agent, to investigate a dataset and answer a question about it while keeping the analysis understandable, reviewable, and traceable. The example dataset is two decades of library checkout records.

The session covers how prompts and an AGENTS.md rules file determine what Codex produces, how to establish what the data represents before analyzing it, and how to produce a trend analysis in which each result is traceable to its code.

Complete the environment and assistant setup before starting: Complete setup

Page	Questions	Objectives
Coding Agents for Analytics Work	What can a coding agent do, and what must its output satisfy?	Identify the understandable, reviewable, and traceable requirements for agent-produced analysis.
Prompting and Project Rules	How do prompts and an AGENTS.md file determine what Codex produces?	Write prompts and project rules that produce reproducible notebook artifacts.
Understanding the Data Before Analysis	What does one row represent, and which file answers which question?	Investigate data structure before plotting or interpreting trends.
Planning and Running an Analysis	How have physical and digital checkouts changed over time, and how can Codex help plan a new visualization?	Select the correct dataset, account for partial years, compare visualization approaches, and trace results to code.
Managing Context in Coding Agent Conversations	What belongs in the conversation, and what belongs in project files?	Distinguish working context from saved project context and decide where verified facts, decisions, and workflow rules should live.
Homework: Extend the Keyword Analysis	How can a messy keyword field be investigated with more than one model or method?	Extend the subject-tag analysis, compare approaches, and identify what should remain human-reviewed.