Epling says writing helps teams reason through customer problems and business impact, while prototypes make the experience easier to judge. At Vanta, PMs and designers use tools such as v0, Figma Make, and Lovable; a shared v0 template helped nontechnical PMs get started. Prototypes let teams discuss customer value and flow before getting lost in implementation details.
Why Prototypes Beat PRDs: How to Ship 10x Faster with AI
Speaker
Jeremy Epling, CPO of Vanta and former VP of Product at GitHub and Microsoft, talks with Peter Yang about prototyping, AI workflows, product careers, and building reliable AI products.
Epling calls these sessions product walkthroughs and asks presenters to clarify whether they want early concept feedback or polish before launch. His advice is to get to the prototype quickly, click through the experience, and set expectations for feedback. Reviews can include detailed attention to wording, especially because Vanta serves customers who may find security compliance intimidating.
Epling uses LLMs to learn unfamiliar compliance topics, synthesize performance feedback, and turn spoken thoughts into structured documents. Vanta also built internal tooling on Gong and Slack to surface customer conversations about competitors, features, and product areas. He values access to the original call so product teams can hear what customers actually said.
Epling sees a strong path for senior individual contributors, with progression measured by autonomy and the ability to take ambiguous problems from questions through customer research and cross-functional decisions. He expects PM roles to involve broader business and customer scope, and says technical expertise will remain valuable. He advises PMs to build relationships across disciplines and understand areas such as sales, marketing, and pricing.
Vanta's agent surfaces policy inconsistencies, shows supporting sources, and proposes edits for customer approval rather than leaving users with a blank chat prompt. Epling says the team uses shared evaluation tools, subject matter experts, and more than 50,000 evaluations to improve answer coverage and accuracy. He also describes testing emerging capabilities over time and choosing chat, cards, or other controls based on the task.
Takeaways
- Pair written product thinking with a prototype so teams can judge the customer experience early.
- Give prototype reviewers a clear feedback goal, then get to the experience quickly.
- Use AI to find and inspect customer evidence, not just to summarize it.
- Senior PM growth depends on taking ownership of ambiguous problems and building cross-functional context.
- Set explicit quality measures and involve domain experts when evaluating AI features.
Mentioned in this talk
Search inside this talk
What was claimed 16
- uses
“with a little Loom explaining how to fork from it”
YouTube Unverified1 source· Talk
- previously atJeremy Epling previously at
MicrosoftProduct role“former VP of Product at ... Microsoft”
YouTube Unverified1 source· Talk
- previously atJeremy Epling previously at
GitHub
VP of Product“former VP of Product at GitHub”
YouTube Unverified1 source· Talk
- role atJeremy Epling is Chief Product Officer at
Vanta“chief product officer at Vanta”
YouTube Unverified1 source· Talk
- uses
“getting v0 for everyone on the PM and design teams”
YouTube Unverified1 source· Talk
- integrates with
“used v0's import feature to import some of our basic assets from Figma”
YouTube Unverified1 source· Talk
- built
“one we built when we thought about the Vanta AI agent”
YouTube Unverified1 source· Talk
- integrates with
“we have a Slack channel that pulls that in by product”
YouTube Unverified1 source· Talk
- uses
“tooling we built internally on top of Gong”
YouTube Unverified1 source· Talk
- uses
“using ChatGPT and Slack”
YouTube Unverified1 source· Talk
- feature
Internal go-to-market assistant: Surfaces compliance inconsistencies, provides source lists and suggested edits, and asks for approval before updates
“We'll show you what they are and provide a list of sources”
YouTube Unverified1 source· Talk
- feature
Internal go-to-market assistant: Can surface and explain 14 SLA inconsistencies with source links and suggested edits
“You need to fix 14 SLA inconsistencies”
YouTube Unverified1 source· Talk
- feature
Internal go-to-market assistant: Can dynamically generate charts and graphs from the agent
“being able to dynamically generate charts and graphs on the fly from our agent”
YouTube Unverified1 source· Talk
- uses
Vanta uses Vector RAG“we have a core RAG pipeline and architecture that we use internally”
YouTube Unverified1 source· Talk
- metric
Vanta: Over 50,000 evaluations“We have over 50,000 evals”
YouTube Unverified1 source· Talk
- metricJeremy Epling: Hired over 50 people across engineering, product, and design last quarter
“Last quarter, I hired over 50 people across engineering, product, and design”
YouTube Unverified1 source· Talk









