How Ramp built an AI operating system for scalable work

Summary

Ramp spent the last year building what operations and AI product leader Ben Levik calls an “AI operating system” for the company, with the goal of becoming more productive. Rather than waiting for tools to mature, Ramp promotes a “Builder” mindset and organizes adoption around Prompt, Knowledge, and Workflow. Employees refine vague requests by having AI ask clarifying questions, while a Notion knowledge base connected to other tools uses feedback loops in which AI drafts corrections and humans approve them. AI agents and connectors then automate tasks such as summarizing project updates from five sources and researching prospects for review-ready sales emails. About 90% of 1,200 employees use Notion AI monthly, and Ramp reports shipping 270 features in the first half of 2025, more than during all of 2024, shifting the bottleneck toward choosing what to automate next.

Takeaways

1. 1

   Ramp’s prompt practice starts with a vague request, asks AI to identify clarifying questions, incorporates the answers, and repeats the rewrite loop until the request is precise.

2. 2

   A feedback database lets employees flag outdated or missing knowledge, a Custom Agent draft corrections, and a knowledge manager review and publish updates instead of leaving them in a ticket queue.

3. 3

   Product teams automatically summarize weekly updates from five sources for Slack, while sales workflows research prospects and prepare emails in an outbox for review.