Skip to content

AI Developer Tools · Free preview

ChatGPT and Claude for Developers

Use ChatGPT and Claude for real software work and check every answer against a real codebase: prompts that hold up, debugging, tests that catch bugs, SQL and shell, code review, data and research, projects and skills. Then build with the Claude and OpenAI APIs: structured output, tools, retries, caching, cost and evaluations, ending with an acceptance-tested capstone.

Intermediate · professional developers
About 315 min reading
30 authored sections

Before you start: Comfortable reading JavaScript or TypeScript, with HTTP, JSON and basic SQL, and Node.js 22.18 or newer. ChatGPT or Claude on any plan covers most exercises; the few that need a paid feature say so and offer another route. The API sections run against an included offline mock, so no API key or paid service is required.

Plan for 15–25 hours of hands-on work in addition to reading. This is an initial estimate; setup and extensions vary.

Open before purchase

A useful preview, not a teaser

Read these complete sections to judge the technical depth, teaching style, and architecture standard before buying.

Preview 1

What you will be able to do

Free preview · for developers who can read JavaScript or TypeScript

Preview 2

Choose the product, the model and the effort

Free preview · Claude facts checked on 7 October 2026; ChatGPT controls checked on 4 October 2026

Preview 3

A first session you can check

Free preview · everything you need is on this page

Start the free preview

Complete curriculum

30 sections · a check for every exercise + an acceptance-tested capstone

Part 1 · Get started

  1. What you will be able to doFree
  2. Choose the product, the model and the effortFree
  3. A first session you can checkFree

Part 2 · Prompts and answers you can trust

  1. Write prompts as work ordersCourse Pass
  2. Spend reasoning where the problem is hardCourse Pass
  3. Steer the second answerCourse Pass
  4. Work with long documents without losing detailsCourse Pass
  5. Catch invented answers before they reach your codeCourse Pass

Part 3 · Everyday engineering

  1. Find your way around an unfamiliar codebaseCourse Pass
  2. Debug from evidence, not from the first plausible causeCourse Pass
  3. Write new code from a specification you can runCourse Pass
  4. Get tests that catch bugs, and prove that they doCourse Pass
  5. SQL, regular expressions and shell, checked against real dataCourse Pass
  6. Review, refactor and document a pull requestCourse Pass
  7. Learn a new tool fast, without learning it wrongCourse Pass

Part 4 · Data, research and files

  1. Analyze data by computing, not by readingCourse Pass
  2. Research a technical question, then check the sourcesCourse Pass
  3. Make files and small tools, then open them yourselfCourse Pass
  4. Screenshots, charts and voiceCourse Pass

Part 5 · Make the assistant yours

  1. Set up projects and memory so the next chat starts aheadCourse Pass
  2. Skills, plugins and connectorsCourse Pass
  3. Hand off a bigger task with a brief you can checkCourse Pass

Part 6 · Build with the APIs

  1. Make your first API call, and read everything that comes backCourse Pass
  2. Structured output and toolsCourse Pass
  3. Retries, caching and cost: what production addsCourse Pass
  4. Evaluate a prompt the way you test codeCourse Pass

Part 7 · Work safely, then prove it

  1. Use assistants at work without leaking or being ledCourse Pass
  2. Capstone: check for duplicates before an issue is filedCourse Pass
  3. Check what you can now doCourse Pass
  4. References and how to keep this currentCourse Pass