Example
From Wall of Text to "Whoa" — How AI Avatars Transformed My Payment Integrity Course
Let me paint you a picture.
You've got a course on Payment Integrity. It covers things like predictive case prioritization, Coordination of Benefits, and pre-payment accuracy. Important stuff — genuinely! — but let's be honest: the source content reads like a terms-of-service agreement had a baby with a compliance memo.
My learners deserved better. So I went full AI on it. And I am not mad about the results.
Step 1: Turning Dry Text Into Something People Actually Want to Watch
I had dense, text-heavy content covering three core themes for AI Payment Integrity program:
- Expertise — the depth of knowledge behind the system
- Creating Clarity in the Payment Workflow — how AI cuts through the chaos
- Full Transparency — giving providers and payers a clear view of decisions
I took those blocks of text, rewrote them into short, punchy scripts, and handed them off to Synthesia. If you haven't used it yet — buckle up — because you pick an AI avatar, paste your script, and out comes a polished talking-head video in minutes. No camera. No studio. No "uh, can we do one more take?"
Three scripts. Three avatars. Three videos. Done.
Step 2: Okay But How Do I Display These Things?
Here's where it got fun.
I knew I wanted all three videos on one screen — side by side, no scrolling, no clicking away to a separate page. Rise 360's native video block is great, but it wasn't going to give me the layout control I wanted. So I turned to Claude (hi 👋) and asked for a custom HTML code block.
My requirements were simple:
- All three videos, centered, displayed together
- Each video with its own player controls
- If a learner hits play on Video 2 while Video 1 is already running — Video 1 stops automatically. No audio chaos. No dueling narrators.
- Oh, and make it look good. Like, actually good.
What came back? A fully self-contained HTML file with a dynamic animated background — deep navy blues, drifting light orbs, a subtle moving dot grid — and three video cards with a glowing border that activates when a video is playing. The mutual-exclusion audio logic was handled with a clean JavaScript event listener setup that plays perfectly inside Rise 360's iframe sandbox (a detail that matters more than you'd think, trust me).
I dropped it into a Rise 360 Code Block as a project — which lets you upload the HTML file along with all your assets (hello, MP4s!) as a bundled package. No external hosting needed, no fussing with absolute URLs. Everything travels together, nice and tidy.
The Result
Learners land on a screen that doesn't look like a compliance module. It looks like something they'd actually want to explore. They can choose which video to watch first, control their own pace, and the whole thing just… works. No overlapping audio. No broken layouts. No "why is this so small?!" (Okay, there was one round of "make the videos bigger" but that's what iteration is for.)
What I Learned
- AI avatars remove the "production bottleneck" excuse. No more waiting on SMEs to be camera-ready. Scripts become videos in the time it used to take me to schedule a recording session.
- Claude + Rise 360 Code Blocks = a surprisingly powerful combo. If you can describe what you want clearly, you can get custom interactive HTML that Rise can't produce natively. The key is being specific: layout, behavior, visual style, edge cases (like sandbox iframe restrictions — yep, that's a thing).
- The sum is greater than the parts. Synthesia gave me polished video. Claude gave me a polished container. Together they turned a dry Payment Integrity module into something I'm genuinely proud to publish.
Your Turn
If you've been sitting on text-heavy content and wondering how to make it feel modern — try this combo. Pick your AI video tool, write tight scripts, and don't be afraid to ask for help building something custom to display them.
Your learners will notice the difference. And honestly? So will you.
2 Replies
- Thomas_ShayonCommunity Member
SMcNicol, I'm blown away at how integrated everything in your demo feels, despite using disparate tools. Absolutely superb demo. 👏🏾👏🏾👏🏾
Curious, how many hours would you say it took to get to your final version?
- SMcNicolCommunity Member
Thank you so much — that means a lot! 🙏🏼
Honest answer? The final version took about 2–4 hours of active working time. But here's the thing — a big chunk of that wasn't me coding or writing from scratch. I was prompting, reviewing, redirecting, and making judgment calls while Claude handled the heavy lifting.
The custom video player, the interactive HTML components, the course content synthesized from three source documents — all of it came together in a single session. What would have taken me 3–5 days solo compressed into one afternoon.
That said, I think the "integrated" feeling you noticed isn't the AI's doing — it comes from keeping a consistent design language (staying consistent with branding throughout) and making intentional instructional decisions at every step. The AI is fast. The strategy still has to come from you.
That's the part I find most exciting about this workflow. ⚡
