AI for Developers: A Practical First Month with LLM APIs
by Priya Raman
Make assistants a genuine part of your workflow, not a party trick abandoned by Friday.
LM Created by Laura Mbeki
Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.
7 modules · 52 lessons · 7h of material
7 lessons running 54m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
8 lessons running 1h 4m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
8 lessons running 1h 8m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
8 lessons running 1h 8m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
7 lessons running 58m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
7 lessons running 56m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
7 lessons running 52m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.
Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.
7 modules · 52 lessons
7h total length
Short list, and deliberately so. If you meet these you can start today.
Almost every developer has tried an assistant and almost none have made it stick. The pattern is familiar: a spectacular first week, a growing suspicion that verifying the output costs more than writing it, and a quiet return to old habits. This course is the antidote.
The organising idea is fit. Some tasks are a superb fit for a model and some are actively worse with one, and the difference is predictable rather than mysterious. You will learn to recognise both within seconds. Then you work through the tasks that genuinely fit: understanding an unfamiliar codebase, writing the boring adapter layer, translating between languages, generating test cases, reviewing your own diff, drafting documentation, and untangling a configuration file that someone left behind in 2019.
Verification gets its own long module, because trusting output you have not checked is how teams get burned. You will learn cheap checks that catch most errors, when to demand a citation, how to make a model contradict itself deliberately, and which categories of answer to never accept without running.
The course finishes with workflow: assistants in the editor against assistants in a browser tab, keeping project context reusable, the etiquette of AI-assisted work in a shared repository, and an honest section on what to disclose to your employer and clients.
Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.
Reviews are written by people who bought this course. We publish the critical ones too.
4.0
Rated 4.0 out of 5Course rating · 1 review
Gemma Sinclair
Senior developer
The chapter on what these tools are genuinely poor at is worth more than most of what has been written on the subject, and the reusable project context idea has stayed with me. Some of the middle sections tell an experienced developer things they already do without thinking. Even so, nothing else I have read on this keeps its head half as well.
Prompt engineer and AI workflow designer
Laura went independent after seven years of agency work and now designs the prompt libraries that sit behind other people's products. She treats prompting as engineering: versioned prompts, a held-out evaluation set, a regression run before anything ships, and a token budget you have to hit. Her packs are the ones she uses with her own clients — briefing, rewriting, summarising, review — rather than sanitised examples, and each comes with notes on where it fails. She keeps every pack working across ChatGPT, Claude and a small open model, so the technique outlives the model.
One-time payment · lifetime access