Velza Academy VELZA ACADEMY AIPP
Cohort
Enroll

Velza Academy · AI-Powered Professional

Learn practical AI Engineering on work you already do.

AI-Powered Professional takes your workflows from prompt to completion. Start with Prompt and Context Engineering, add Memory, State, Loop, and helper-agent systems, then surround the work with a harness that checks what happened and shows you what broke. No software-development background needed.

AIPP official certification badge
Choose your cohort
Next cohort starts in 00d 00h 00m 00s $149 $99Save $50Code LAUNCH applied automatically

Your instructor

Mike Wheeler, founder of Velza Training and Consulting

Learn from Mike Wheeler

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.

500,000+ global learners taught O’Reilly author As Seen on edX, Pearson, LinkedIn Learning & Udemy

The curriculum & schedule

Your 6 live sessions

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.

Session1
Sunday, August 2
7:30-8:30 PM Central

Prompt & Context Engineering

Most of what makes AI useful is not how you ask, it is what the AI knows when you ask. This week builds both.

  • The five parts of a prompt that make it answerable: objective, context, constraints, examples, output format
  • How to tell a prompt problem from a model, data, or retrieval problem, so you stop rewriting prompts that were never the issue
  • The three places context lives, memory, knowledge stores, and live connectors, and how to pick the right one
  • How to give the AI the background it needs up front so it stops guessing
  • You build your own context setup and leave with it working
Week 1
Session2
Friday, August 7
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the August Velza Academy cohorts.

Session3
Sunday, August 9
7:30-8:30 PM Central

Memory, State & Loop Engineering

How to make AI work run on its own, remember what happened, and check itself. You follow along in a terminal or a desktop app, whichever you prefer.

  • Where information lives between steps, and what durable memory gives you that a fresh chat does not
  • How to set up work that observes, decides, acts, verifies, and knows when to stop
  • Handing pieces of a job to helpers without losing control of the result
  • The tracker: a running record of what happened, so a failure becomes a fixable ticket instead of a shrug
  • The judge: a second pass that scores the work and never sees the author's own opinion of it, because nothing grades its own homework honestly
Week 2
Session4
Friday, August 14
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the August Velza Academy cohorts.

Session5
Sunday, August 16
7:30-8:30 PM Central

Harness Engineering: Making AI Reliable

AI work that ran fine last month quietly stops working. This week is the checks that catch it before it costs you.

  • Why a model plus a harness is the whole system, and the six parts the harness supplies
  • The difference between telling the AI what to do and checking what it actually did
  • How to catch drift, when yesterday's setup silently stops matching today's reality
  • How to find which layer broke when a workflow fails, instead of rewriting the prompt and hoping
  • You leave able to look at a broken AI workflow and say where to look first
Week 3
Session6
Friday, August 21
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the August Velza Academy cohorts.

Session1
Sunday, September 6
7:30-8:30 PM Central

Prompt & Context Engineering

Most of what makes AI useful is not how you ask, it is what the AI knows when you ask. This week builds both.

  • The five parts of a prompt that make it answerable: objective, context, constraints, examples, output format
  • How to tell a prompt problem from a model, data, or retrieval problem, so you stop rewriting prompts that were never the issue
  • The three places context lives, memory, knowledge stores, and live connectors, and how to pick the right one
  • How to give the AI the background it needs up front so it stops guessing
  • You build your own context setup and leave with it working
Week 1
Session2
Friday, September 11
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the September Velza Academy cohorts.

Session3
Sunday, September 13
7:30-8:30 PM Central

Memory, State & Loop Engineering

How to make AI work run on its own, remember what happened, and check itself. You follow along in a terminal or a desktop app, whichever you prefer.

  • Where information lives between steps, and what durable memory gives you that a fresh chat does not
  • How to set up work that observes, decides, acts, verifies, and knows when to stop
  • Handing pieces of a job to helpers without losing control of the result
  • The tracker: a running record of what happened, so a failure becomes a fixable ticket instead of a shrug
  • The judge: a second pass that scores the work and never sees the author's own opinion of it, because nothing grades its own homework honestly
Week 2
Session4
Friday, September 18
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the September Velza Academy cohorts.

Session5
Sunday, September 20
7:30-8:30 PM Central

Harness Engineering: Making AI Reliable

AI work that ran fine last month quietly stops working. This week is the checks that catch it before it costs you.

  • Why a model plus a harness is the whole system, and the six parts the harness supplies
  • The difference between telling the AI what to do and checking what it actually did
  • How to catch drift, when yesterday's setup silently stops matching today's reality
  • How to find which layer broke when a workflow fails, instead of rewriting the prompt and hoping
  • You leave able to look at a broken AI workflow and say where to look first
Week 3
Session6
Friday, September 25
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the September Velza Academy cohorts.

Session1
Sunday, October 4
7:30-8:30 PM Central

Prompt & Context Engineering

Most of what makes AI useful is not how you ask, it is what the AI knows when you ask. This week builds both.

  • The five parts of a prompt that make it answerable: objective, context, constraints, examples, output format
  • How to tell a prompt problem from a model, data, or retrieval problem, so you stop rewriting prompts that were never the issue
  • The three places context lives, memory, knowledge stores, and live connectors, and how to pick the right one
  • How to give the AI the background it needs up front so it stops guessing
  • You build your own context setup and leave with it working
Week 1
Session2
Friday, October 9
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the October Velza Academy cohorts.

Session3
Sunday, October 11
7:30-8:30 PM Central

Memory, State & Loop Engineering

How to make AI work run on its own, remember what happened, and check itself. You follow along in a terminal or a desktop app, whichever you prefer.

  • Where information lives between steps, and what durable memory gives you that a fresh chat does not
  • How to set up work that observes, decides, acts, verifies, and knows when to stop
  • Handing pieces of a job to helpers without losing control of the result
  • The tracker: a running record of what happened, so a failure becomes a fixable ticket instead of a shrug
  • The judge: a second pass that scores the work and never sees the author's own opinion of it, because nothing grades its own homework honestly
Week 2
Session4
Friday, October 16
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the October Velza Academy cohorts.

Session5
Sunday, October 18
7:30-8:30 PM Central

Harness Engineering: Making AI Reliable

AI work that ran fine last month quietly stops working. This week is the checks that catch it before it costs you.

  • Why a model plus a harness is the whole system, and the six parts the harness supplies
  • The difference between telling the AI what to do and checking what it actually did
  • How to catch drift, when yesterday's setup silently stops matching today's reality
  • How to find which layer broke when a workflow fails, instead of rewriting the prompt and hoping
  • You leave able to look at a broken AI workflow and say where to look first
Week 3
Session6
Friday, October 23
2-3 PM Central

Office Hours Optional

Job-market intel and open Q&A, shared across the October Velza Academy cohorts.

What you’ll learn

The layers 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

By the end, you’ll be able to

AI Engineering is becoming part of professional work.

The job is larger than writing a prompt. Someone has to define the requirements, supply the right context, manage state across steps, control the loop, check the result, and know what to inspect when the workflow fails. Those skills carry across models and tools because they belong to the system around the AI.

What’s included

Everything that’s included

6 live sessions

Three teaching sessions plus three optional office hours, live over three weeks. Sundays at 7:30-8:30 PM Central.

1-year replay access

Every session is recorded, and you keep access to the replays for a full year, so you can rewatch any time you need them.

Weekly hands-on projects

Each session is an AI Engineering build, and the cohort tool carries your system across all three weeks. Week one, a project setup and a Prompt Pack built for your industry in the cohort's Blueprint Builder. Week two, a tracker on a real job of yours, plus a judge that scores the finished work against a standard you fix in advance. Week three, a guide and a sensor on the rule you most need to hold, each with an owner, a scope, and an off switch, plus a map of your whole workflow that shows the piece nothing checks. Every week also ships a LABS brief you run at your own pace, with every named resource linked.

The AI Workflow Builder, yours to keep

A browser tool built for this cohort. It generates a prompt pack shaped to your industry in week one, and the tracker, standard, and judge you build on top of it in week two are yours afterwards. Nothing installs and nothing expires when the class ends.

The Blueprint Builder turns your industry blueprint into a Prompt Pack of ready to paste prompts and Project instructions.

Certificate of completion

Finish the cohort and you get a personalized certificate showing your name, your track, the live session dates, and the hours of live instruction, with a public verification link your employer can check for reimbursement. Print it, save it as a PDF, or share it on LinkedIn.

Your certificate is personalized with your name and track, and carries a public verification link.

Reserve your seat in the next cohort.

$149 $99Save $50Code LAUNCH is applied automatically. Nothing to type.

See cohorts
Cohort:

Questions, answered

Frequently asked

Do I need to write code?

You do not need a software-development background, and you will not be asked to learn a programming language. This is practical AI Engineering at the workflow and system level. The AI can generate commands and explain what they do. Your job is to define the work, direct it, inspect the evidence, and verify the result. Work wherever you are comfortable: a terminal, a desktop app work surface, or locally.

Is this the right course for me?

It is if you have used AI chat before and want to learn practical AI Engineering by building a real workflow around your own work. You do not need a software-development background, and working developers are welcome too. The focus is the requirements, context, state, loops, controls, and evidence around the AI rather than agent-framework or SDK internals.

How is this different from a prompting course?

Prompting is the first layer of the AI Engineering stack. Context determines what the model knows, memory and state carry the work across steps, loops control what happens next, and the harness checks the result. The course teaches you to engineer the complete workflow rather than keep polishing one prompt.

What do I actually leave with?

A Prompt Pack built for your industry in the cohort's Blueprint Builder, which keeps your entries from week to week and adds a section each week: prompts and project instructions, then a loop with a tracker and a judge, then a harness with a guide, a sensor, and an owner for each. You also get a LABS brief every week, the demo files to rerun the session examples yourself, and a course library with the decks and replays for a full year. These are verifiable artifacts you built, and stories you can tell in an interview.

What tools will we use?

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.

What is the Blueprint Builder?

It is a browser tool built for this cohort. It generates a prompt pack shaped to your industry in week one, and the tracker, standard, and judge you build on top of it in week two are yours afterwards. Nothing installs and nothing expires when the class ends.

What if I can’t make a session live?

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.

Why a live cohort instead of studying on my own?

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.

Do I get a certificate of completion?

Yes. When your cohort ends, you receive a personalized certificate of completion by email. It shows your name, the track, the live session dates, and the hours of live instruction, and it carries a certificate number with a public verification address your employer can confirm it against, which is what most reimbursement forms need. It is a certificate of completion for the live course, not the certification itself. That one comes from the certifying body when you pass their exam.

What is your refund policy?

You can request a full refund within 24 hours of the start of the first live session.