By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
How I AIHow to turn meeting notes into prototypes that your sales team can immediately demo to customers
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
At a glance
WHAT IT’S REALLY ABOUT
Use AI transcripts to build demos, decks, and PRDs faster
- Anjan Panneer Selvam (CPTO at Acolyte Health) explains how he captures stakeholder conversations (sometimes via a wearable recorder) and converts raw transcripts into structured prompts for rapid prototyping.
- He uses tools like ChatGPT plus prototype builders (e.g., Lovable/v0) to create interactive, high-fidelity demos in minutes—reducing long documentation cycles and accelerating stakeholder alignment.
- He then layers in AI market research (Perplexity), presentation creation (Gamma), and requirements validation (ChatPRD) to pressure-test ideas before engineering execution.
- A key theme is cultural: AI doesn’t replace PMs/engineers; it shifts teams toward faster alignment, clearer communication, and broader access to prototypes across sales, CS, and leadership.
IDEAS WORTH REMEMBERING
5 ideasMeeting transcripts can become the new source material for product artifacts.
Instead of relying on memory or manual notes, Anjan records stakeholder discussions (e.g., CEO meetings) and pastes transcripts into ChatGPT to extract structured prompts and next-step outputs.
Interactive prototypes are faster—and often clearer—than traditional documentation.
For complex logic-heavy builders (journey/rules/workflow tools), clicking through a prototype surfaces gaps more naturally than reading multi-page PRDs and enumerating permutations.
Use ChatGPT to normalize “product sense” into structured prompts for builder tools.
Anjan starts with a natural-language brain dump, then asks ChatGPT to produce a Lovable/v0-ready prompt that includes UI patterns and interaction details.
Iterate in layers: start broad, then add specific implementation hints.
He begins with a basic prototype prompt, then progressively injects details (e.g., naming a library like React Flow) to help the prototyping tool implement the right approach.
AI research is most useful when explicitly asked to be skeptical.
Because models tend to be optimistic, he adds follow-ups like “play devil’s advocate” to get pro/cons and reasons to say no—often killing weak ideas quickly.
WORDS WORTH SAVING
5 quotesAt the end of this... I have a fully functional now drag-and-drop canvas builder... and the goal here is not to say something is easy. It's more so to, are we all aligned and can be move fast.
— Anjan Panneer Selvam
Now, we're moving from, 'Oh, let's spend a week aligning,' to, 'Here's the alignment,' in less than 30 minutes to an hour.
— Anjan Panneer Selvam
There are more features that AI has helped me say no to... It's done in an hour, and now you can... more freely say no to things.
— Anjan Panneer Selvam
I think people are so afraid of preserving product energy and engineering energy, that they forget that those are... rich people problems.
— Claire Vo
Nothing to displace good old production-resilient code and processes, but this is all before that.
— Anjan Panneer Selvam
High quality AI-generated summary created from speaker-labeled transcript.
