As an all-in-one financial operations platform combining corporate cards, expense management, bill payments, procurement, travel, and accounting automation, Ramp helps companies save time and money at scale.
Challenges
When Ramp implemented Assembled’s workforce management platform in 2022, they were scaling rapidly and needed better operational control.
Like many forward-thinking companies, Ramp provided access to various LLMs across the organization. But without structure, every agent developed their own approach.
Agents faced constant context switching between Notion, Guru, Slack threads, and internal systems. After juggling multiple sources for a complicated ticket, agents needed mental breaks before diving into the next case.
Patrick Crosswhite, Product Operations, Systems & Ops Platforms said: “When ChatGPT first came out, we were very deliberate about providing every available conversational LLM flow or system to every employee at Ramp. That got a little chaotic in the support world. Every agent was on their own.”
The team tracked solves per hour as their primary productivity metric, alongside average handle time, quality assurance scores, and CSAT. With 310,000+ tickets handled annually across a 100-person team, every inefficiency compounded.
The Solution
The team used Assembled to improve agent autonomy, fundamentally changing how they manage performance.
“Targeted SLA look-backs for live channels and functionality to send alerts directly to agents has helped increase agent autonomy, improving our productive adherence scores by ~10% per team in a 6-month period,” Richard Londer, Manager, Customer Operations (Workforce) said.
Compliance became proactive rather than reactive. Rule flagging helped the team catch non-compliant schedule requests before they resulted in costly penalties, protecting the bottom line while ensuring compliance.
VTO and extra work functionality removed hours of manual approval work while increasing agent engagement during heavy seasons.
This allowed agents to pick up hours to drive down backlogs while freeing WFM to focus on strategy rather than administrative tasks.
In early 2024, Ramp faced a critical decision: should they build their own AI support solution or buy one?
The existing partnership with Assembled influenced their evaluation, but the technical requirements were clear: an AI Copilot had to live inside Zendesk to eliminate context switching.
Assembled’s approach to AI also aligned perfectly with Ramp’s own philosophy, making the choice easy.
Patrick Crosswhite said: “We knew that Assembled understands support operations, and especially around businesses like ours. Our thinking was aligned enough that we chose to work with Assembled as a design partner.”
Ramp took a methodical approach to rolling out an AI Copilot, named Cal, understanding that agent trust could be lost as quickly as it’s gained.
Their team focused heavily on enablement. Rachael, an agent on the fraud risk team, built out best-practice documentation specifically for the CX organization.
They gamified early usage by sharing leaderboards of who was doing the most actions within AI Copilot, making adoption feel like a fun challenge rather than a mandate.
Leadership also addressed anxiety about AI automation: AI Copilot wouldn’t replace agents but would free them to focus on increasingly complex work as simple tasks got automated away.
Rachael Howell, Sr. Customer Experience Specialist, CX Risk, Ramp, said: “The biggest hurdle was to use Cal as a tool to enhance the support experience, not as a replacement for my own brain.
It’s not gonna replace what I know and what I’m able to do, but it frees up my mind so I can spend less energy on all of the busy work.”
Results
The results speak to both the partnership and Ramp’s enablement efforts. Adoption grew from 45% in May 2025 to 75% across 100+ agents in early 2026. Agent satisfaction scores rose to the high fours out of five, and the team consistently saves between 30 to 90 seconds per ticket.
Across 310,000+ annual tickets, these time savings add up to over 5,100 hours saved annually. Junior agents now ramp faster with an AI partner that helps them speak in Ramp’s voice from day one, shifting training focus from memorizing processes to knowing when to trust AI Copilot’s answers.
Patrick Crosswhite said: “Cal has had a huge impact on our team and it’s definitely contributing to faster agent ramping.”
For Rachael on the fraud risk team, AI Copilot transformed how she handles complex cases. Recently, a customer needed help troubleshooting a device-related issue for mileage reimbursements, which typically requires multiple sources and extensive back-and-forth.
Using AI Copilot to summarize information and prompt for missing details, Rachael escalated the issue to the appropriate team with all necessary context in one clean hand-off, resulting in minimal friction for both her and the customer.
Rachael Howell said: “Cal helps me move faster without sacrificing quality. There are fewer missed details and just better customer outcomes overall.”
An unexpected benefit emerged: AI Copilot became a forcing function for documentation quality across the entire company.
Ramp consolidated all their knowledge into Notion to support AI Copilot’s context needs. But the benefit flows both ways. When the AI struggles, it signals that the documentation is confusing – not just for AI, but for human employees too.
Agents can now flag documentation issues directly through AI Copilot, creating a feedback loop that improves support quality and also helps sales, account management, customer success, fraud operations, risk teams, and any roles at Ramp that touch customers.
Patrick Crosswhite said: “We are quicker to understand when our internal knowledge is failing because agents are servicing everything in one place. And if we’re confusing the AI Copilot, then we’re probably confusing the rest of our company that’s reading these documents.”
Beyond efficiency metrics, AI Copilot has shifted agent engagement. The once-quiet Slack feedback channel is now active with agents sharing tips, flagging issues, and suggesting improvements.
The team intentionally avoided requiring agents to become prompt engineering experts. Instead, curious power users optimize their workflows and share best practices.
Patrick Crosswhite said: “Rachael and other agents have really stepped up, becoming the strategic partners of the curious.”
Future
As Ramp crosses the 100-agent milestone, they’re focused on expanding AI Copilot’s capabilities while maintaining their principled approach to AI. On the WFM side, automation continues driving strategic impact and operational efficiency.
They continue to operate as design partners with Assembled, providing feedback that helps shape the product.
Patrick Crosswhite said: “We’re very excited to come into this new year and really start to push Cal and continue to improve our internal processes.”
This blog post has been re-published by kind permission of Assembled – View the Original Article
For more information about Assembled - visit the Assembled Website
About Assembled
Assembled is a Support Operations platform that helps companies maintain exceptional customer experiences, no matter what lies ahead. Leading brands use Assembled's workforce and vendor management capabilities to make optimal staffing decisions, gain visibility into performance and productivity, and unlock new ways to serve evolving customer needs. Find out more about Assembled
Author: Assembled
Reviewed by: Jo Robinson
Published On: 2nd Jun 2026
Read more about - Industry News, Assembled, Case Studies
