Claude Code in Parallel: From Idea to Merged PR
Run several Claude Code sessions at once without collisions, ask for options before Claude builds, check its proof instead of its word, and keep quality high as you ship more.
8 lessons
Course catalog
Browse all published courses.
Lesson 1 of every course is free. One whole course is free. One payment of $10 opens all 19 courses in the catalogue today. What's included →
19 courses
Write the Loops: Your Job After AI Writes the Code
AI writes the code. What is left is the job around it: framing the problem, steering the agent, and validating what it produces. You will also find where the work piles up once coding stops being the slow part. Predict, drag and decide your way through nine short lessons. For engineers and the people who manage them.
9 lessons
Agents That Remember: Context Engineering & Memory
Build agents that remember. An agent's memory is just plain markdown files it reads, searches and updates for itself. Set that up and the agent gets better at your work every time it runs. You will keep deep detail out of the context window with progressive disclosure. You will stop two agents overwriting each other, using hashing and versioning. And you will decide what stays read-only and what an agent may rewrite. Predict, drag and decide your way through.
7 lessons
Three Checks Before You Back a Trend
Something new is growing fast and everyone is arguing about whether it matters. This course gives you three checks you can run yourself. You practise on measured cases from the last twenty years, including two that grew enormously, looked unstoppable, and fell. By the end you will not call the winner every time. You will stop being fooled twice by the same shape.
7 lessons
The Prompting Playbook: Debug a Production Prompt
Your production prompt worked, then you moved to a new model and the test cases started failing. This is the repair method, in order. Build a small eval suite of control, edge and capability-boundary cases, so you can tell a real improvement from a feeling. Strip the pasted-website cruft and the untrue persona. Carve the prompt into tagged sections so role, policy, guidelines and tone stop competing. Add an output contract and enforce it in the harness with a stop sequence. Then isolate one failing case at a time and find the instruction that made the wrong answer the compliant one. Worked end to end on a messy customer-support prompt for a fictional telco, then run on a prompt of your own. Based on “The Prompting Playbook” by Margot van Laar, Code with Claude.
7 lessons
Get More From ChatGPT Without Better Prompts
When an answer disappoints, most people rewrite the question. There are faster fixes, and you already own them. Set how long ChatGPT thinks before it answers. Check what it remembers about you. Write your standing instructions once instead of retyping them every time. Seven short lessons, one control each, and an honest look at when the wording still matters.
7 lessons
Sort Tickets, Applications and CVs with Jev
Somebody spends their morning reading the same kind of thing over and over, answering the same question about each one. Most of that is not writing. It is one question, asked again and again, and the answer is one word. There is a kind of AI built only for answers like that. People call it a decision model. The steps here work with any decision model. The one you set up is called Jev. You write the one question, and the list of answers it is allowed to give. Every answer comes back with a number saying how sure it was. You decide which answers you accept, and which few get a second look. Eight short lessons. You finish with one filled-in card for a job of your own — hand it to your assistant, or to a developer.
8 lessons
Create with Google AI
A beginner→advanced tour of Google's generative creation stack - Gemini Omni, Nano Banana, Lyria 3, Flow with Veo 3.1, and NotebookLM. Three modules, nine lessons: foundations, asset studio, pro pipeline. Ends with an end-to-end capstone and the SynthID / ethics lesson every creator needs.
9 lessons
AI for Decision-Makers
A hands-on, interactive course for managers, founders and operators — tool-agnostic. Turn data into a one-page insight, red-team a plan with a branching decision sim, decide from long docs, brief your team in the right voice, catch AI before it costs you, and run a weekly executive routine.
7 lessons
AI Foundations: Think, Prompt, Verify
A hands-on, interactive on-ramp to using AI well — tool-agnostic. Learn how AI actually works, which tool for which job, prompting with context, catching hallucinations, and keeping your data private. Predict, then reveal, then prove it.
7 lessons
The AI Growth Engine
A hands-on, interactive course for marketers, creators and solo founders — tool-agnostic. Turn one idea into a week of content, research your audience, keep your brand voice, personalize outreach without spamming, set up a no-code automation, and run a weekly growth loop.
7 lessons
Claude Cowork Foundations: 5 Day-One Fixes
A calm, interactive walkthrough of the five fixes that get your Claude Cowork foundation right — reading files in Obsidian, a lean CLAUDE.md, the Memory Diet, migrating projects, and the workstation-vs-skill check. Built around a predict-then-reveal deck so each one actually sticks.
7 lessons
Create with OpenAI
A beginner-to-advanced tour of OpenAI's stack: GPT-5.5 modes, Memory + Projects, Canvas + Tasks, GPT Image 2, the Realtime voice trio, Code Interpreter, Codex on CLI, Cloud and Mobile, and AgentKit — plus the limits, watermarking and refusal layer every shipper must own. Three modules, nine lessons.
9 lessons
Gemini 3 for Work
A hands-on, interactive walkthrough of the five Gemini 3 updates that actually matter at work — multimodal understanding, long-document memory, Workspace search, generative interfaces (Dynamic View) and context engineering — plus a bonus on making Gemini push back. Toggle each “leap”, then prove it.
7 lessons
Learn Smarter, Land the Job
A hands-on, interactive course for students and early-career — tool-agnostic. Study with active recall, research with real sources, tailor your resume to the job, rehearse with an AI mock-interview, use AI ethically, and run a weekly job-hunt routine.
7 lessons
Mastering Claude Code
Anthropic's “Mastering Claude Code in 30 minutes” workshop (by Boris Cherny, who built Claude Code), rebuilt as a hands-on interactive course. Learn it by doing — Q&A, agentic editing, planning, feedback loops, CLAUDE.md, and custom tools. Three modules, eight lessons.
8 lessons
Mastering Claude Cowork
Learn Cowork's seven core capabilities by doing — local file access, persistent memory, connectors, skills, projects, the browser extension and its limits, and scheduled automation. Three modules, nine lessons.
9 lessons
OpenClaw — Zero to Confident
A hands-on, interactive beginner→next-steps OpenClaw series. Learn what OpenClaw is, get comfortable in the workspace, build your first project, make it better rather than bigger, and see where it leads — by doing, not just reading. Two modules, six lessons.
6 lessons
Your Personal AI
A hands-on, interactive course on using AI for everyday life — tool-agnostic. Off-load your inbox & calendar, plan trips and meals, decode money, prepare for health questions (safely), learn a new skill, and run a 15-minute weekly reset. Toggle each before/after to feel the difference.
7 lessons