← All series & guides

OpenAI

ChatGPT

16 of 30 parts live

OpenAI ChatGPT from everyday chat through product map, Work mode, Codex, and Custom GPTs — one continuous path.

Start with part 1 →

Getting started

  1. 1 What ChatGPT is (plain English) ChatGPT is OpenAI’s AI assistant family, not one single app. This Part 1 map separates company, models, and products so you can start on web, mobile, or desktop without hype, ranking wars, or treating chat answers as a source of record.
  2. 2 Free, Go, Plus, Pro, Business, Enterprise without hype Free, Go, Plus, Pro, Business, and Enterprise differ mainly in capacity, features, and admin control, not in magic truth. This Part 2 explains each rung, why Go exists, and how to choose a plan without FOMO. Re-check chatgpt.com/pricing before you pay.
  3. 3 Web and mobile: first 30 minutes Part 3 of Learn ChatGPT from scratch. A guided first half hour on chatgpt.com and mobile so you leave with one real output and a clear map of web, phone, and what to skip for later.
  4. 4 Desktop app: Chat, Work, and Codex in one place Part 4 of Learn ChatGPT from scratch. How the desktop app puts Chat, Work, and Codex in one place, what Free still limits, and how to pick a mode without burning usage on the wrong door.
  5. 5 Memory, custom instructions, and Projects Part 5 of Learn ChatGPT. Custom instructions set standing prefs, memory can stick facts you can edit, Projects scope chats and files, and scheduled tasks appear on some paid tiers. You leave knowing what to turn on, what to review, and what to keep out of sticky context.
  6. 6 Voice, images, and files for everyday tasks Part 6 of Learn ChatGPT. Voice, images, and files turn everyday work into multimodal chats, with study mode and limited free deep research when available. You leave with a paste and upload ladder so you never drop SSN, passwords, or raw HR into a consumer chat.
  7. 7 Connectors and apps (Drive, calendars, etc.) Connectors and apps link ChatGPT to Drive, mail, Slack, CRMs, and more. Climb from plain chat to uploads, read-only access, write actions, and scheduled work only as far as the job needs, with IT policy first at work.
  8. 8 Privacy, work rules, and when not to use it Privacy, company policy, and the right tool matter more than clever prompts. Use this series-end guide for when not to use ChatGPT, a good-enough checklist, and what to read next on the AMS product map and tutorials.

Product map

  1. 9 Chat vs Work vs Codex Part 1 of ChatGPT product map. Plain English on Chat, Work, and Codex: what each mode is for, how usage differs, and a chooser you can use before you open the wrong door on desktop, web, or mobile.
  2. 10 Custom GPTs vs plain chat Part 2 of ChatGPT product map. When a Custom GPT earns its keep versus plain chat: saved instructions, knowledge files, plan limits on creating GPTs, and why a GPT is a recipe, not a full software product.
  3. 11 Models chooser in plain English Part 3 of the ChatGPT product map: Instant, reasoning, Pro tiers, and Work or Codex models without FOMO. Start on the default, upgrade only when a clear prompt still fails. Names change; the decision rule does not.
  4. 12 API and builders’ tools (light) Part 4 closes the ChatGPT product map: ChatGPT Plus or Pro is not free unlimited API. Open platform.openai.com only if you build software that calls models. Most AMS readers stay in the app until that day.

Everyday use

  1. 13 First week of useful tasks (write, plan, learn) Part 1 of the ChatGPT everyday tutorial: a Mon-Fri week in plain Chat with write, plan, and learn buckets. One real deliverable per day, worked prompts, and no Work or Codex tourism.
  2. 14 Better answers with structure and examples Part 2 of the ChatGPT everyday tutorial: role, goal, constraints, example, and format. Weak vs strong prompts, micro-examples, and a diagnose-patch-rerun loop when Chat is wrong.
  3. 15 Long docs and multi-file work Part 3 of the ChatGPT everyday tutorial. How to handle long documents and multi-file work with chunking, indexing, quote checks, Projects, and a no-secrets recipe you can reuse at work.
  4. 16 Studying and explaining hard topics simply Part 4 of the ChatGPT everyday tutorial. Study hard topics with explain-simply loops, quizzes, teach-back, Study Mode ideas, and the mistakes that turn “learning” into copy-paste theater.
  5. 17 Email, meetings, and workplace writing Part 5 closes the ChatGPT everyday tutorial: audience-first emails, meeting agendas, action lists, and who/what/when follow-ups. Never auto-send. Check policy. Next: Work, then Codex, then Custom GPTs. Scheduled · August 10, 2026

Work mode

  1. 18 What Work mode is for Work mode is the agent for multi-step office jobs: files, apps, decks, sheets, and docs you still review. Part 1 of the ChatGPT Work tutorial separates Work from Chat and Codex so you stop burning usage on the wrong door. Scheduled · August 11, 2026
  2. 19 First agentic task with approvals Part 2 walks one low-risk agentic task with approvals: owned notes into a short status deck, tight tool access, and human review before anything leaves your desk. First Work run on purpose, not by accident. Scheduled · August 12, 2026
  3. 20 Multi-step jobs and checking results Part 3 of the ChatGPT Work tutorial. Run multi-step jobs as a goal-plan-act-checkpoint loop: review the plan, steer mid-run, check usage, and finish with a result checklist that catches workslop before anyone else sees the file. Scheduled · August 13, 2026
  4. 21 When Work beats Chat (and when it does not) Part 4 closes the ChatGPT Work tutorial. Use a decision table for when Work beats Chat, when Chat is enough, and which wrong doors to avoid. Then continue to Codex and Custom GPTs with a series recap you can reuse on Monday. Scheduled · August 14, 2026

Codex & coding

  1. 22 Open coding features and first project Codex is the coding agent surface in the ChatGPT desktop app (with Chat and Work). Part 1 of the ChatGPT Codex tutorial: open a project, ask orientation questions, make one tiny change, and review the diff before you commit. Scheduled · August 15, 2026
  2. 23 Exploring a repo safely Part 2 of the ChatGPT Codex tutorial. Explore a repo safely: ask for a map with real paths, bound what you will not touch, then make a small change. Branch first. Keep secrets out of chat. Do not silent-deploy to production. Scheduled · August 16, 2026
  3. 24 Skills, tasks, and scheduled help (as product offers) Skills, tasks, and scheduled help in ChatGPT Codex are power-ups, not day-one defaults. Climb a complexity ladder, hedge product renames, and never leave high-stakes deploys unattended. Scheduled · August 17, 2026
  4. 25 Review, tests, and not trusting green checkmarks After Codex edits, do not ship on green checkmarks alone. Read the diff, run tests, hunt secrets, check scope, and keep a human on the commit. Diff smells and undo patterns included. Scheduled · August 18, 2026
  5. 26 Git-friendly habits for beginners Part 5 closes the ChatGPT Codex tutorial with beginner git habits: branch per task, small commits, clear messages, PR review, and never force-pushing blind. Learn undo basics, recap the series, and continue to Custom GPTs. Scheduled · August 19, 2026

Custom GPTs

  1. 27 Build a simple GPT for a repeating task Part 1 of the Custom GPTs tutorial. Build one simple GPT for a repeating job: clear instructions, no actions yet, non-secret knowledge only, and a Preview test set before you share. Scheduled · August 20, 2026
  2. 28 Instructions, knowledge files, and actions (light) Part 2 of the Custom GPTs tutorial. Structure instructions (role, audience, steps, format, refuse, example), version knowledge files without secrets, and treat actions as a later, higher-risk layer. Scheduled · August 21, 2026
  3. 29 Share with a team without creating chaos Part 3 of the Custom GPTs tutorial. Share a team recipe without chaos: name one owner, keep version notes, control edit rights, route bug reports, and retire stale GPTs. Personal convenience is not company policy. Scheduled · August 22, 2026
  4. 30 When a Custom GPT is the wrong solution Part 4 closes Custom GPTs and the ChatGPT track on AMS. Use a chooser for when a GPT is wrong (one-offs, live systems, code, secrets, KPIs), recap all six ChatGPT series, and optionally continue to Gemini or Phase P. Scheduled · August 23, 2026