Day 1 PBL Guide Codex Client

Day 1. Planning Requirements Definition Guide

A university-level guide summary for non-majors and planners: set up a project Workspace with Codex Client and develop specs for teamwork.

Part 1. Why Codex? (5 min)
Part 2. Lab goals (5 min)
Part 3. Follow along (20 min)
Part 4. How it works (10 min)
Part 5. PBL mission (10 min)
Part 6. Extra Skill Tasks (15 min)

The key difference between ChatGPT and Codex Client

A regular ChatGPT web chat and the project-based, multi-file Codex Client take different approaches to designing requirements.

Compared Regular ChatGPT (web browser) Codex Client (Workspace-based)
What it sees Only the one-off text typed in the input box Every file in the project folder (Workspace)
How files are handled Copy and paste result code from the screen by hand AI creates and partly edits the chosen markdown files directly
Multi-file reasoning You must upload earlier files by hand every time to update linked content When one plan changes, it reasons about linked files at the same time

Project-based development

We set a dedicated folder on the desktop, automation, as the AI Workspace and practice there. Under this folder structure, AI fully links the input-output chain of each spec file, from the step 0 summary notes to the step 5 email report.

Today's final output

Starting from a long, raw meeting transcript, you'll produce a final approved spec with lint errors fixed, and even send a decision request email.

  • 📄 requirements-specification.md: combined business requirements and flow doc
  • 📧 Plan approval request email: a draft to the CEO (decision maker) to settle open policies

Lab data pipeline (interactive map)

Click each step to update the card below with how data is transformed (Input -> AI -> Output).

P
Prep. Folder setup
S0
Step 0. Clean transcript
S1
Step 1. Analyze notes
S2
Step 2. Write FR sentences
S3
Step 3. Add scenarios
S4
Step 4. Write questions
S5
Step 5. Combine & email
Prep. Set up a local work folder and connect AI Workspace Config
📥 Workspace (Input Environment)
Desktop
The file explorer on the learner's computer
automation/ (create empty folder)
Codex AI ➔ Setup Workspace
📤 Connected result (Output Workspace)
Codex Client chat
AI workspace with the folder active
[Folder connected] Select a project to control linked project files

Create a dedicated local folder and open that path in Codex AI or your editor, so there's a channel to read and write markdown spec docs.

Create an [automation] folder on your local desktop and launch Codex Client.

Follow-Along Guide & Real Codex Client UI Flow

Click the buttons on the left in order to see **where to act (red guide box)** — where a learner actually clicks and types in Codex Client.

How It Works & Context Dependency Map

A logical architecture map of how AI sees files in the project folder and carries planning forward step by step.

Raw transcript (meeting-notes-raw.md)
▼ (Step 0: clean out noise)
Summary planning notes (meeting-notes.md)
▼ (Steps 1–3: roles/features/normal·exception flows in detail)
Requirements doc (functional-requirements.md)
↔
Open questions (open-questions.md)
▼ (Step 5: combine docs and share a decision request email)
Write the combined requirements spec and report
▼ [Roadmap linking to the next sessions]
Database model design (ERD)
Back-end API spec
Front-end wireframes

The markdown specs produced at each step don't stop at planning. In the Day 2 ~ Day 10 course, they carry forward as the key base data (Context) Codex uses to automatically write DB ERD designs, back-end API specs and front-end wireframe code.

PBL Mission: Handle a New Requirement and Send with the Gmail Plugin

PBL real-world task

The CEO adds a new policy and the feedback loop kicks in

During development, the CEO added a new requirement at the end of the meeting notes.
"Let's add account deletion too. When a user deletes their account, all booked counseling sessions must be cancelled automatically and refunded right away."

Mission steps

  • 1. Edit the source file: add the CEO's made-up extra lines (account deletion and automatic booking cancellation) to the bottom of your local meeting-notes-raw.md.
  • 2. Tell Codex Client to update the spec: in the AI prompt box, type "Using the new conversation in meeting-notes-raw.md, update functional-requirements.md with the account deletion feature (FR-005) and the booking cancellation exception flow that follows."
  • 3. Update the combined doc and questions: lint-check the changed requirements, then use the connected **Gmail plugin** to send the CEO an approval email about open issues related to account deletion right away.

📌 Extra Skill Task Summary — Business Understanding & Domain Discovery

We add 3 Tasks to the Day 1 curriculum to clearly link technical skills and AI teamwork skills. The goals and outputs of the existing Tasks/Missions stay the same; the extra Tasks go deeper in designing, building and checking those results.

1. Extra Tasks and Skill Map

Task ID Extra Task Area Tech Skill AI Skill
ADD-D01-T01 Define the service problem and Personas HYBRID TECH-BA TECH-DDD AI-CTX AI-ANA AI-DOC
ADD-D01-T02 Sort Features into Domains TECH TECH-BA TECH-DDD AI-ANA AI-REV
ADD-D01-T03 Review the Domain Map and responsibility boundaries AI TECH-DDD TECH-ARCH AI-CTX AI-REV AI-DOC

2. Learning flow and outputs

ADD-D01-T01 Define the service problem and Personas → ADD-D01-T02 Sort Features into Domains → ADD-D01-T03 Review the Domain Map and responsibility boundaries

  • • Input Context: service idea, existing Day 1 requirements outputs, candidate users
  • • Combined Day output: Service Overview, Persona, Feature List, Domain Map, Responsibility Map
  • • Files to submit: 01_SERVICE_OVERVIEW.md, 03_DOMAIN_MAP.md
  • • AI role: Domain Analyst

3. Day 1 lab assignments (Missions 1 ~ 4)

  • • Mission 1: Plan a pet home care and pet sitter matching service (Step 9)
  • • Mission 2: Spec space booking and IoT control for a self-service study café (Step 10)
  • • Mission 3 (Skill Mission 1): Design Personas, Domain Map and Bounded Contexts for a short-form VOD & live commerce platform (Step 11)
  • • Mission 4 (Skill Mission 2): Design data ownership and Domain boundaries for a smart B2B mobility & vehicle control platform (Step 12)

4. Shared Done Checklist

  • ✅ Results of the 3 extra Tasks link to the existing Day 1 outputs.
  • ✅ Every Task has evidence of both Tech Skill and AI Skill.
  • ✅ Reasons for accepting, changing or rejecting AI suggestions are recorded.
  • ✅ Outputs of all 4 lab assignments (Missions) can be completed.
  • ✅ Results can be reused as input for the next Day (User Flow & Sequence design).