Why Ramp Replaced Product Spec Documents with AI Agent Glass
Ramp CPO Geoff Charles built Glass, an internal AI agent that connects Snowflake, user research, and codebases to generate production-ready specs.
The limiting factor—how to design an AI software factory for speed | Geoff Charles (Ramp CPO)
With Geoff Charles · Saturday, September 26, 2026
Ramp Chief Product Officer Geoff Charles outlines how product organizations must transition from focusing solely on individual output to engineering an AI-powered software factory. Drawing parallels to Formula 1 racing, he explains how automating one part of the product lifecycle inevitably exposes new bottlenecks in discovery, definition, review, testing, and coordination. Charles details the internal AI agents Ramp built—including Glass, Inspect, Review Buddy, Testo, and Gadget—and outlines the three evolving archetypes for product managers in an AI-native world.
Key takeaways
- Ramp built an internal AI agent called Glass that connects directly to Snowflake data, customer research repositories, design systems, and the production codebase. Read more →
- Dumping raw feedback into large language models fails at scale: a one-million-token context window holds less than 0.5% of Ramp's Gong call transcripts. Read more →
- Ramp treats internal employee inquiries as programmatic API calls rather than manual interruptions for product managers. Read more →
- In Formula 1 racing, the driver accounts for only 15% of the impact on winning; the real gains come from optimizing the interaction between the car, pit crew, and team. Read more →
- Ramp uses an internal tool named Inspect with over one million sessions, allowing non-engineers to submit 1,000 pull requests per month. Read more →
- Ramp built dedicated internal AI agents, including Glass, Inspect, Review Buddy, Testo, and Gadget, to handle routine tasks across triage, testing, and review. Read more →
6 articles from this episode
How Ramp Mines Customer Pain Across Millions of Data Points
Ramp CPO Geoff Charles explains how the company uses ETL, vector search, and AI agents to trace customer pain points across fragmented feedback.
How Ramp Solves 85% of Inbound PM Questions with AI
Ramp CPO Geoff Charles reveals how internal agent Gadget resolves 85% of PM inquiries and fixes 60% of UX bugs in 24 hours.
Why AI Coding Tools Shift Your Bottlenecks, Not Solve Them
Ramp CPO Geoff Charles on why AI coding shifts your bottlenecks from writing code to testing and coordination.
How Ramp Uses AI to Automate 93% of Code Reviews
Geoff Charles explains how Ramp built Inspect, Review Buddy, and Testo to scale engineering throughput and catch 425 bugs in 30 days.
Geoff Charles: The 3 Career Tracks for Product Managers
Ramp CPO Geoff Charles explains how AI shifts PM careers into three distinct tracks: Factory PM, Tastemaker, and General Manager.
More Lenny's Podcast episodes
- Why Google wants to win the frontier conversation | Tulsee Doshi (Head of Product for Gemini)Nov 8 · 3 articles
- 86 minutes of paid-UGC alpha | Hector Serrano (Wispr Flow)Nov 1 · 5 articles
- An 86-minute guide to finding PMF | Rob Snyder (Author, The Power of Pull)Oct 25 · 4 articles
- A mind-expanding conversation on how models actually work | Emmanuel Ameisen (Anthropic)Oct 18 · 6 articles