How Arena by PTC Built a Partnership AI Agent with the Crossbeam MCP

Partner networks are rarely simple. Reps and Customer Success Managers often need to know which partner fits a specific buyer's need, and getting that answer usually means searching Slack, digging through SharePoint (that bottomless, ever-growing folder tree), or waiting on a reply from the partnerships team.

That was one of the main challenges Heatherly Bucher, Director of Strategic Alliances at Arena, a PTC business, faced. 

She manages a partner network that spans referral partners, marketplace and technology partners, value-added services partners, and platform technology partnerships. Each type carries its own logic, and her team needed a way to get the right partner in front of the right customer without every rep having to learn the full network by heart.

To close that gap, her team built a partnership AI agent in Microsoft Copilot Studio, connected to the Crossbeam MCP, Gong, Crayon, and a set of curated SharePoint folders. Nine months after launch, most of Arena's customer-facing teams use it as their default source for partner questions, and the partnerships team now runs early partnership evaluations through it as well.

"We're super excited about the Crossbeam MCP. We're super excited about Crossbeam." — Heatherly Bucher, Director of Strategic Alliances

The problem: partner knowledge lived in too many places

Arena runs a large, varied partner network, and Heatherly's team supports both the sellers and Customer Success Managers who need partner answers in the moment and the partnerships team that manages the relationships themselves. Before the agent, that meant reps asking in Slack, digging through SharePoint, or waiting on a reply from partnerships. 

Every answer took time, and quality depended on who happened to respond.

The stakes were higher because of how many partnership types Arena runs at once. For example, a rep working a deal with a buyer using a mechanical Computer-Aided Design (CAD) system needed to know which partners covered that integration and how their offerings differed, not just whether a partnership existed. That kind of comparison was hard to do quickly without a single, current source.

Heatherly's team also knew that AI adoption inside Arena varied widely by person. Some of her teammates already used AI daily in their personal lives, while others have not knowingly embraced AI. Any solution had to work for both groups from day one.

"The critical components of AI are how good the data is, the quality of the data for the purposes of the agent, the constraints you build on the agent, and then how well users interact with your agent." — Heatherly Bucher

How they built it: starting narrow and expanding on purpose

Arena's team started small on purpose, treating the agent's scope as the first design decision rather than an afterthought.

01 Define a narrow job for the agent 

The team resisted building an agent that tried to do everything. The first version had access to a handful of public web pages and one SharePoint folder, with no MCP connections at all. The goal was specific: be the authoritative source on Arena partnerships.

02 Restrict general web access 

The agent cannot browse the open web. Heatherly's team made that choice deliberately, so the agent would never pull in blog posts, forum threads, or competitive chatter that could contradict Arena's own partner data.

03 Add the Crossbeam MCP once the foundation held 

As the agent proved useful, the team added the Crossbeam MCP connection, along with Gong and Crayon. That gave the agent access to account mapping data alongside call context and competitive intelligence, all inside the same conversation.

"Our partnership AI agent does have access to Crossbeam through the MCP connection. It allows us to bring that Crossbeam data into a multi-data source analysis for these customer-facing teams and for our partnership team as well." — Heatherly Bucher

04 Teach the team to use it before expecting adoption 

Heatherly watched for questions in Slack channels, ran them through the agent herself, confirmed a good answer, then posted that answer back publicly. The habit shifted slowly, and reinforcing it directly moved people away from asking around and toward asking the agent.

05 Use the agent for partnership evaluation 

More recently, the partnerships team began using the agent to evaluate a potential channel partner, an Enterprise Resource Planning (ERP) vendor adjacent to Arena's own space. The agent combined Crossbeam overlap counts from an early, NDA-only relationship with context on existing partnerships that could strengthen that overlap, plus Arena's own partnership criteria stored in SharePoint. It returned a recommendation, not just a data pull, though Heatherly's team kept the final call with a person.

What happened: a single source teams actually trust

Nine months in, most of Arena's customer-facing teams now default to the partnership agent instead of asking in Slack or searching SharePoint on their own. Heatherly credits that shift to consistency: the agent gives the same answer every time, drawn from the same set of vetted sources, rather than whoever happens to be online.

“One of the things we really appreciated about Crossbeam as we've explored its use is that we've been using Crossbeam more and more in our vetting of new potential partnerships. One of the questions you often need to answer in looking at new partners is: what is our overlap in that ideal customer profile? What's our overlap in customers? What's our overlap in engaged opportunities and prospects, those greenfield opportunities?” — Heatherly Bucher

The partnerships team has started leaning on the agent earlier in its own process, using it to pull together an initial view of a potential partner before running the manual analysis that used to come first. Heatherly noted the agent's read on the ERP channel partner opportunity was faster than running a Crossbeam report and separately checking it against team strategy by hand, even though the final decision still came from her team, not the agent.

A final thought

If you're weighing whether to connect an MCP to your own partnership workflow, start with what you already do every week and look for the parts that repeat. Heatherly's advice is to automate the task you'd be relieved to stop doing by hand, then build outward from there once your team trusts the results.

Treat the rollout as ongoing rather than a single launch. Arena's team still checks in when the agent misses, and they review and maintain the tools themselves.

Ready to give your partnerships team one trusted source for partner answers? See what the Crossbeam MCP can do. Book a demo with our team.

Frequently asked questions

What is the Crossbeam MCP? 

The Crossbeam MCP is a way to connect Crossbeam's partner overlap data directly into AI tools like Microsoft Copilot Studio, so an agent can answer questions using live account mapping data instead of a static export.

Does Arena's agent make partnership decisions on its own? 

No. Heatherly's team uses the agent to speed up research and surface a recommendation, but a person still makes the final call on any partnership decision.

Why did Arena restrict the agent from browsing the open web? 

The team wanted a single authoritative source for partner information. Open web access risked pulling in outdated or contradictory information from outside sources, which would undercut the trust they were trying to build.

How long did it take for teams to adopt the agent? 

About nine months passed between launch and the point where most customer-facing teams at Arena were using the agent as their default source for partner questions, according to Heatherly.

‍