✦ Velza Academy · AI-Powered Professional
Three weeks of live, hands-on work on the skills that make AI reliable. Prompts and context, memory across steps, work that runs and checks itself, and how to tell what broke when it breaks. No coding background needed.
✦ Your instructor
Mike Wheeler is an AI and Salesforce trainer and O’Reilly author. He has taught well over 500,000 global learners on major platforms such as edX, LinkedIn Learning, Pearson, and Udemy, and he built the first generative AI course on edX. He teaches for non-coders, working backward from your career goals.
✦ The curriculum & schedule
Six live sessions over three weeks: three teaching sessions plus three optional office hours. All times Central. Can’t make one live? Every session is recorded.
Most of what makes AI useful is not the prompt, it is what the AI knows when you ask. We start with prompts that get you what you actually asked for, then spend the rest of the hour on context: what to hand the AI up front, what to keep in a project or a shared folder it can reach, and what to connect so it pulls from live sources instead of guessing. A bad answer is not always a bad prompt, and you will learn to tell the difference. You leave with a setup for organizing what your AI needs to know.
Job-market intel and open Q&A, shared across the August Velza Academy cohorts.
How to make your AI remember what happened yesterday instead of starting over every time. How to set up work that runs on its own, checks itself, and knows when to stop. And why anything that grades its own homework will tell you it did great. Work in a terminal or a desktop app, whichever you prefer.
Job-market intel and open Q&A, shared across the August Velza Academy cohorts.
Why AI work that went fine last month quietly stops working, and how to catch it. Telling the AI what to do makes good results more likely. It does not guarantee them. This session is about the checks that do. When something breaks you will know where to look instead of rewriting the prompt and hoping.
Job-market intel and open Q&A, shared across the August Velza Academy cohorts.
Most of what makes AI useful is not the prompt, it is what the AI knows when you ask. We start with prompts that get you what you actually asked for, then spend the rest of the hour on context: what to hand the AI up front, what to keep in a project or a shared folder it can reach, and what to connect so it pulls from live sources instead of guessing. A bad answer is not always a bad prompt, and you will learn to tell the difference. You leave with a setup for organizing what your AI needs to know.
Job-market intel and open Q&A, shared across the September Velza Academy cohorts.
How to make your AI remember what happened yesterday instead of starting over every time. How to set up work that runs on its own, checks itself, and knows when to stop. And why anything that grades its own homework will tell you it did great. Work in a terminal or a desktop app, whichever you prefer.
Job-market intel and open Q&A, shared across the September Velza Academy cohorts.
Why AI work that went fine last month quietly stops working, and how to catch it. Telling the AI what to do makes good results more likely. It does not guarantee them. This session is about the checks that do. When something breaks you will know where to look instead of rewriting the prompt and hoping.
Job-market intel and open Q&A, shared across the September Velza Academy cohorts.
Most of what makes AI useful is not the prompt, it is what the AI knows when you ask. We start with prompts that get you what you actually asked for, then spend the rest of the hour on context: what to hand the AI up front, what to keep in a project or a shared folder it can reach, and what to connect so it pulls from live sources instead of guessing. A bad answer is not always a bad prompt, and you will learn to tell the difference. You leave with a setup for organizing what your AI needs to know.
Job-market intel and open Q&A, shared across the October Velza Academy cohorts.
How to make your AI remember what happened yesterday instead of starting over every time. How to set up work that runs on its own, checks itself, and knows when to stop. And why anything that grades its own homework will tell you it did great. Work in a terminal or a desktop app, whichever you prefer.
Job-market intel and open Q&A, shared across the October Velza Academy cohorts.
Why AI work that went fine last month quietly stops working, and how to catch it. Telling the AI what to do makes good results more likely. It does not guarantee them. This session is about the checks that do. When something breaks you will know where to look instead of rewriting the prompt and hoping.
Job-market intel and open Q&A, shared across the October Velza Academy cohorts.
✦ What you’ll learn
Seven things that decide whether AI works once or works every time. Hover any one for what it means.
✦ What you’ll walk away with
Companies are adopting AI faster than they can find people who know how to operate it.
These are in-demand skills. They show up on AI certification exams, they show up in job listings, and they carry over to whatever tools your company already runs. You do not need a certification to start using them.
✦ What’s included
Three teaching sessions plus three optional office hours, live over three weeks. Sundays at 7:30-8:30 PM Central.
Every session is recorded, and you keep access to the replays for a full year, so you can rewatch any time you need them.
You leave each session with something you can use at work the next day. Week one, a setup for organizing what your AI needs to know. Week two, a way to keep track of what happened and a second pass that checks the work. Week three, a way to find out why something broke.
✦ Questions, answered
You do not need a coding background, and you will not be asked to learn a language. The AI generates the commands and explains what they do. Your job is to direct the work and verify the result, not to write it from scratch. Work wherever you are comfortable: a terminal, a desktop app work surface, or locally.
It is if you have used AI chat before, want to run real work through it rather than just ask it questions, and are willing to check its output instead of trusting it. You do not need a coding background. It is not the right course if you are a working software developer looking for depth on agent frameworks or SDKs. This is the just-enough version: enough to run the work and verify it, without becoming an engineer.
Prompting is one of five layers we cover. The other four (context, memory, loops, and the harness) are what separate an AI workflow that works once from one that works every time.
We stay tool-agnostic on purpose. The concepts transfer across whatever you or your employer already run. Bring the AI tool you actually use. Demos are recorded in one tool so you can see the whole thing work end to end, and we name the equivalents as we go.
Every session is recorded and shared, and you keep access to the replays for a full year, so you can watch or rewatch any of them on your own schedule. The optional Friday office hours are recorded too.
Self-study stalls. A live cohort gives you a fixed three-week pace, the chance to ask questions in real time, weekly hands-on work, and optional office hours. You actually finish.
You can request a full refund within 24 hours of the start of the first live session.