Most product videos made with AI are boring. They list features, a robot voice reads them out, and people scroll away. Recently I tried something different. I gave my agent (running Claude Opus 5.5 on my computer) one line, and by the next morning it had made four explainer videos, 21 minutes in total, that each tell a story while they teach. I've attached two of them. Below is the exact workflow, the prompts and the mistakes, so you can have your own agent do the same for your product or your clients. OpenClaw, Claude Code, Codex, Hermes: the steps are the same. Quick heads-up so nobody feels tricked: the product in these videos is Vois, a voice app I build. So yes, I used my own tool for the voices. But the workflow works with any voice tool your agent can run by itself, and I'll show you what to look for in step 4. ## The big idea: the video IS the thing it teaches Don't make a video *about* your product. Make a video that *is* the thing your customer wants to create, and show how it was made along the way. My four videos teach people how to make podcasts, training courses and audiobooks. So: - the podcast tutorial is a real podcast episode, and halfway through, the hosts reveal they aren't real people - the training tutorial is a real mini course, with quizzes and a certificate with your name on it - one audiobook tutorial is a quiet story about a novelist whose readers keep asking for the audiobook - the other is a support group for authors who keep putting their audiobook off (there's a grumpy dragon) A setting like this gives you characters, something at stake and a payoff for free. A feature list gives you none of that. ## The 7 steps ### Step 1. Give your agent a setting, not a feature list What I'd send it: ```text Make an explainer video for [product]. Don't list features. Make the video BE the thing our customer wants to create: if it teaches making a podcast, the video is a podcast episode. Give it one main character with one real problem and a deadline. Each step in the product

A small personal win to share with the creators here. I'm mildly dyslexic, and text-to-speech has been part of my life for years. When creating my own content meant paying again for every tiny revision, I started building something for myself. That became Vois Studio: an app that turns written scripts into finished voiceovers for videos, podcasts and courses. Now other creators are using it, and a learning and development team at one of the largest space exploration companies is quietly testing it too. That part still surprises me! I'm launching it on AppSumo with a lifetime deal: https://appsumo.8odi.net/5kDBO9 New AppSumo customers only: 10% off with code "voisstudio10" at checkout. I built Vois. Happy to chat about whether it fits what you're making.