A 12-session course on running Agile ceremonies with AI — built by a working Senior Scrum Master in healthcare, not by a consultant who read the docs.
You've used ChatGPT. Maybe you've asked Copilot to summarize a meeting. It worked, sort of, and then you went back to doing it by hand.
This course is for Scrum Masters, RTEs, and delivery leads who want the next thing: not better prompts, but repeatable machinery — the sprint report that builds itself every Friday, the refinement prep that takes ten minutes instead of an hour, the agent that drafts your retro questions from what actually happened.
It is not for you if you're brand new to AI. Start with the free AI for Scrum Masters course instead — it's free, it always will be, and this course assumes it.
Most course ladders are a scam: the advanced tier is the beginner tier with longer prompts.
Here's the actual difference. Beginner teaches you to do one task with AI. Advanced teaches you to build systems your team runs on — and, just as importantly, to know when not to.
Three things you won't find in the free tier:
1. Workflows, not prompts. Chained, repeatable pipelines across Jira, Copilot and Rovo. You finish each session with an artifact you keep and reuse, not a chat transcript.
2. Agents. The fastest-moving thing in this space and the biggest gap in the free catalogue. What an agent actually is, how to build a scoped one for Agile work, what's already sitting inside the enterprise licence your company pays for — and where they fail.
3. Judgment. How to tell when the output is confidently wrong. What to never delegate. How to defend an AI-assisted artifact when a stakeholder, an auditor, or a skeptical engineer asks who wrote it. Written from healthcare, where that question has teeth.
Roughly 20–25 minutes per session. Self-paced, no cohort, no deadlines. Certificate on completion.
Coming later: an Expert tier on leading AI enablement across multiple teams. Founding buyers get the founding price on that too, whenever it ships.
Every agent demo you have ever seen was a success case. The agent reads the board, writes the summary, everyone nods. That's not dishonest — it's just not the part you need to prepare for.
Here's the part you need to prepare for. An agent writes your sprint summary. It's well structured. The tone is right. Every sentence in it is true. And it doesn't mention that the integration work is blocked, because the blocker was recorded as a comment on a subtask rather than as a status change, and the agent didn't look there.
You skim it. It reads fine. You send it to your stakeholders.
Nothing about that output looks wrong, because nothing in it is wrong. That's the failure mode. Not error — omission, delivered fluently.
Omission. The most dangerous and the least discussed. Wrong sentences get caught; missing ones don't. Nobody proofreads for absence. And the things most likely to go missing are exactly the things recorded off the happy path — a blocker in a comment, a dependency in a linked ticket, a concern someone raised verbally in standup.
Fabrication. Ask for something the data doesn't contain and you may get it anyway, complete with plausible names and dates. Practitioners in the Atlassian community have reported agents producing entirely fictional releases when the underlying data had nothing to offer. The invented material is not flagged as invented. It looks exactly like the real material.
Stale confidence. The agent answers from whatever slice of the board it pulled, with no sense that the world moved. In a live sprint, "as of some point earlier today" and "now" are different answers, and only one of them is useful in a stakeholder meeting.
The instinct is to add "tell me what you're unsure about" to the prompt. It feels responsible. It doesn't work — the model's self-reported uncertainty doesn't reliably track where it's actually wrong. You get a confident answer with a confident-sounding caveat attached, and you've learned nothing.
You cannot ask the thing that was confidently wrong to notice it was confidently wrong. Verification has to come from outside the output.
These don't make the agent right. They make checking cheap, which is the thing that determines whether you actually check.
1. Scope hard. Current sprint only. This board. This label. A narrow question has a narrower space to be wrong in.
2. Make it cite. Every claim tagged with the ticket ID it came from. This is the highest-leverage one — it turns verification from "reread everything and hope" into "click three links." Anything that can't be sourced becomes visible immediately.
3. Make it declare absence. "List anything you looked for and could not find." This is the direct counter to the omission failure, and almost nobody does it.
4. Make it flag inference. "Mark anything you inferred rather than read." Separates what's in Jira from what merely sounded plausible.
"Review all AI output" is a policy that lasts about three sprints. Then a release goes sideways, everyone's busy, and it quietly stops. Reviewing everything is how you end up reviewing nothing.
Sort by what a wrong answer costs instead:
A retro summary that's slightly off wastes five minutes. A capacity forecast that's confidently wrong plans your next sprint into a wall.
Three properties separate the review habits that last from the ones that die in March.
Structural, not diligent. If it depends on remembering to be careful, it decays. If it's a step in something that already happens, it survives.
Attached to an existing ceremony. The sprint report gets checked in the five minutes before review, because that slot already exists and has a forcing function. A standalone "AI review checkpoint" on your calendar will be gone by the third sprint.
Author separated from verifier. Whoever ran the prompt is the worst person to catch its errors — they already believe it. Where the stakes justify it, someone else looks.
Short list, and it's short on purpose.
Anything you'd have to defend under scrutiny without being able to say where the number came from. Anything about a specific person — performance, capability, blame. Anything where the failure is discovered by someone other than you, months later.
Prefer to read it on its own, or send it to someone? This session has its own page →
I'm a SAFe Senior Scrum Master, currently contracting at a large healthcare organization. I've spent the last year making Copilot and Rovo genuinely useful in real ceremonies — and finding out where they aren't.
I also built the 21 free courses on this site. They're free, and they'll stay free. This is the first thing I've ever charged for.
I'm not an AI expert. I'm a practitioner who does this job every week and writes down what works.
The free courses are broad — one course per role, aimed at getting anyone started. This one goes deep in a single direction and takes twelve sessions to do it. If the free Scrum Masters course didn't earn your trust, don't buy this one.
You get an email telling you the truth and a refund if you want one. I'd rather tell you it slipped than ship something thin.
Full refund, any time, no questions. Email me. You don't have to explain.
It helps, and the examples use them because that's what I use. The methods work with Claude, ChatGPT, or Gemini — the workflows are the point, not the vendor.
No. SAFe context shows up where it's relevant, but the workflows are Scrum-first and apply to any team running sprints.
Yes, distinct from the free ones.