We Built Every Employee at Ramp Their Own AI Coworker

The Models are Good Enough, The Harness Isn’t At Ramp, we hit 99% adoption of AI tools across the company. And then we noticed something concerning: most people were stuck. It wasn't that the models weren't good enough or that people lacked ambition, they just had no idea how to improve their set up. Terminal windows, npm installs, and MCP configurations were too much for most people to grok, and the few who pushed through had wildly different setups, with no way to share what they'd learned. We'd created urgency without providing enough infrastructure, and it limited the true upside of AI to people who already knew how to configure it. So we decided to build our own AI productivity suite to make every employee an AI power-user without the pain of having to configure their environment. We’ve called it Glass. Everyone Can Be An AI Power User The models are already exceptional, but most people use them like driving a Ferrari with the handbrake on. Not because they aren’t smart, or lack ambition, they’ve just never seen what a well-configured environment looks like or what it can do. To solve this problem we aligned around three core principles for Glass: 1. Don't limit anyone's upside. The default approach for non-technical users is to simplify: put the product on rails, offer fewer options, and make it dummy-proof. We couldn’t disagree more. At Ramp, power users thrive on multi-window workflows, deep integrations, scheduled automations, persistent memory, and reusable skills. The goal isn’t to remove complexity, but to make it invisible while preserving full capability. 2. One person's breakthrough should become everyone's baseline. The biggest failure mode wasn’t that people couldn’t figure things out. It was that everyone had to figure things out alone. A workflow discovered by one person didn’t help anyone else. Glass needed to compound wins into organizational capability: shared skills, propagated best practices, and a floor that rises with every discovery. 3. The product is the enablement. Becoming an effective AI user is a skill. People improve through repetition and experimentation, but the product can accelerate that curve by suggesting the right skill at the right time, and showing what “good” looks like in the moment. No amount of workshops can match a targeted nudge while you’re already doing the work. Everything connects on day one Glass comes auto-configured on install. People sign in once via their Okta SSO, and all Ramp’s tools become available to them with a one-click setup. This also includes home-grown products like Ramp Research, Ramp Inspect, and our newly released Ramp CLI. This is the unsexy foundation that makes everything else possible. When a sales rep asks Glass to pull context from a Gong call, enrich it with Salesforce data, and draft a follow-up — it just works, because everything is already connected. We Distribute Reusable Skills Through Our Dojo The easiest way to share learnings across the organization is through skills. These are markdown files that teaches your agent exactly how to perform a specific task, and we’ve built out a marketplace for them called Dojo. Now, when someone on the sales team figures out the best way to analyze Gong calls, break down competitive mentions, and draft battlecards, they can package it as a skill, and give that superpower to every rep on the team. A CX engineer builds a Zendesk investigation workflow that pulls ticket history, checks account health, and suggests resolution paths, and through Dojo the entire support team levels up overnight. Over 350 skills have been shared company-wide. They're Git-backed, versioned, and reviewed like code. The marketplace is the flywheel: every skill shared raises the floor for everyone. To help people find the right skills, Dojo includes a built-in AI guide we call the Sensei. It looks at which tools you've connected, what role you're in, and what you've been working on, and recommends the skills most likely to be useful to you. A new account manager doesn't need to browse a catalog of 350 skills — the Sensei surfaces the five that matter most on day one. It's another example of the product doing the enablement work: rather than expecting people to know what's available, Glass meets them where they are. It Remembers Who You Are, And What You’re Working On When users first open Glass, we build a full memory system based on the connections they’ve authenticated. This gives every chat session context on the people they work with and their active projects, along with references to relevant Slack channels, Notion documents, Linear tickets, and more. As a result, the agent spends less time searching, entering each conversation with the context the user expects. Under the hood, we also run a synthesis and cleanup pipeline every 24 hours, mining users’ previous sessions and connected tools like Slack, Notion, and Calendar for updates. This means Glass can adapt to their world without them having to re-explain