Week 2 · Learning from the best

 Unpacking coding agents — then building your own.

 Reverse-engineer Codex. Discover that the same architecture explains Claude Code. Then transfer the pattern into a completely different domain: a Job Search Agent that thinks before it acts.

 Course GSU CIS 4394 Agentic AI

 Instructor Dr. Xinyu Fu

 Term Fall 2026

 Format Hands-on studio class

 📡 
 Agent Radar · this week Agents are getting real power Three stories from the past few days — physical power, economic power, and a containment incident. Think → Act → Coordinate → Spend → Affect the physical world. 
 → 

 📝 
 After class Week 2 Summary Scavenger-hunt answer key (nine layers → real Codex files) · join your GA1 group on iCollege · Opal / Fleet / ADK tutorials with videos · Quiz 1 readings + five sample questions. 
 → 

 Start here

 The path through today

 Work through the four parts in order. Do Prep before you come to class — the session starts with building, not with account recovery.

 00 
 Before class Student prep Accounts, installs, the guided reading, and what to bring. Fifteen minutes now saves the whole build sprint later. 
 → 

 01 
 Part 1 Unpack Codex Click through the nine layers of a coding agent, then watch the agent loop run — step by step — as Codex fixes a failing test. 
 → 

 02 
 Part 2 The same lens on Claude Code Does the architecture we extracted explain a competing product? Sort what is shared from what differs. 
 → 

 03 
 Part 3 Build the Job Search Agent Transfer the architecture to a new domain. Choose Opal, Fleet, or Codex + Python — with full step-by-step instructions. 
 → 

 04 
 Part 4 Break it, grade it, submit it Four required tests, the evidence standard, ten deliverables, and the rubric. 
 → 

 Discussion question If Codex had the exact same model — but no access to files, shell commands, tools, state, or permissions — would it still be Codex?

 See the answer 
 No — you would have a chatbot that talks about code. Everything that makes it Codex — reading files, running tests, applying patches, pausing for approval — lives in the harness . The model supplies reasoning; the product is the loop built around it. Part 1 takes this answer apart layer by layer.

 Today’s arc

 Reverse-engineer → compare → transfer → build

 Unpack Codex
 What architectural ingredients turn a language model into a coding agent?

 Compare Claude Code
 Does the same architecture explain a competing product — or is it product-specific?

 Transfer & build
 Keep the reasoning pattern; swap the goal, environment, tools, and safety boundary.