CX just got a seat at the table — TheyDo Agent live reveal recap

The deck lands on Friday at 4pm. The budget meeting is Monday at 9am. Most CX leaders know exactly how this goes

On May 27, TheyDo CEO Jochem van der Veer, Solutions Engineer Rebecca Dickson, and YouSee Journey Management Specialist Louise Kampmann-Kahlen pulled back the curtain on TheyDo Agent live: an AI operational layer designed to reason across structured customer journey context inside real enterprise environments.

The session wasn't really about faster reporting or AI-generated summaries. It was about a shift already underway inside large enterprises: customer context evolving from static research and siloed dashboards into living operational infrastructure that can guide decisions across the business.

Whether you're managing a CX program across multiple product lines, preparing executives for budget season, or trying to keep journey governance consistent as your team scales, this webinar shows what that shift looks like in practice.

Louise's problem, which is probably also yours

Louise works in the CX and Journeys team at YouSee, one of Denmark's largest telcos. Her team supports multiple product areas: internet, TV, mobile, streaming, and enterprise services, with a headcount that cannot absorb the volume of questions coming in from the rest of the business.

A live poll of attendees confirmed this is not unusual. 65% said it takes their team one to two weeks to answer a meaningful CX question, and 26% said it takes longer. "It would be weeks for us. Sometimes months," Louise says.

The issue isn't that enterprises lack information. Most organizations already have BI dashboards, VoC platforms, support data, operational metrics, call transcripts, journey research, and feedback repositories. The problem is that these systems rarely share a common operational structure. The context lives in fragments, and it compounds with every new team, market, or product line you add.

A six-month-old PowerPoint, and what Louise did instead

A colleague requested access to a deck Louise had built half a year earlier, a familiar enterprise pattern where insights live in files and files live in people's inboxes. Instead of scheduling a meeting to reconstruct the analysis, Louise opened Ask TheyDo, typed the exact question her colleague had sent in chat, and got a document back.

The colleague's first response was to ask where the insight came from, which meant she was already acting on it, not reviewing it. The conversation moved directly to the work.

The data sources problem

Jochem asked the audience how many data sources their teams pull from to answer a single CX question. Over two-thirds said four or more, with many landing at seven to 10 or beyond, with manual reconciliation sitting on top of it all.

"That's not a workflow problem," Jochem explains. "That's what happens when there's no shared layer that different data sources can map to, and it compounds with every new team, market, or product line you add."

Not an AI problem

"AI quality is not necessarily an AI problem. It's actually a data management problem," Jochem says. His framing of the AI landscape is worth watching in full, but the thesis is this: AI outputs in customer experience fall short not because the models are weak, but because the underlying data has no shared structure for the model to reason from. Journey management provides that structure: a common layer that business performance data, VoC signals, and individual customer interactions can all flow into. Once it exists, AI has something real to work with.

TheyDo Agent in action: the Friday 4 p.m. demo

Rebecca sets the scenario every enterprise CX leader recognizes: an executive message arriving Friday at 4 p.m. asking for a complete CX update, churn analysis, and funding recommendations ahead of a Monday morning budget meeting. This is where the product reveal begins.

TheyDo Agent reasons across the journey context already curated inside the platform. It reads across journey phases, pulling:

• VoC signals from Medallia and Qualtrics

• Quantitative metrics from Snowflake, Databricks, and Power BI

• Delivery progress from Jira and Azure DevOps

• All connected to the specific phases and steps where customers interact with the business

Three minutes. 

That's how long it takes TheyDo Agent to produce a sourced, structured executive document from the question. Not a draft to refine over the weekend. "This is not just the narrative. This becomes the funding conversation," Rebecca says.

Same context, new audience

After the executive document, Rebecca shows the same underlying evidence reframed for the product team, reshaped into a sprint brief without rebuilding any of the source material. The context exists once. The framing adjusts to who's in the room.

"Instead of CX being a reporting function, you've now been elevated to the most strategic function in the enterprise," Rebecca says.

The governance demo

This one is for practitioners. It shows how TheyDo Agent maintains context, not just surfaces it. A journey practitioner uses an Agent skill to govern an entire workspace with a single instruction, updating tagging, linking opportunities to solutions, flagging duplication, and integrating a post-merger dataset that arrived as unstructured files. The alternative is weeks of manual work. "This is what enables us to scale without adding headcount," Rebecca explains.

In the merger scenario, the agent analyzes incoming files from an acquired organization, extracts quotes and themes, maps insights to the appropriate journey steps, and aligns new data with existing governance standards. The result is not reorganization. It's operational continuity.

How do you know you got it right?

Louise’s answer comes from firsthand experience: prompt carefully, review continuously, and use inline editing to refine rather than redo. She adds that the models achieve between 80% and 90% accuracy, that every output traces back to the source material, and that the activity log shows exactly what the Agent did. Not a black box, but a transparent record.

Q&A highlights

The session wrapped with a Q&A where attendees dug into how TheyDo Agent works in practice. Key questions and highlights:

• How do you monitor reliability? Louise’s advice: treat it like working with a good collaborator. Prompt carefully, review continuously, and use inline editing to refine rather than redo. The quality is improving continuously, and the ability to work on specific sections without having to start over makes a real difference.

• How does the agent learn to speak your organization's language? Governance documents that codify your taxonomy, brand language, and insight standards give the agent the rules it needs to return outputs that sound like your business, not a generic summary.

• Can it analyze across nested journeys? Yes, and it's exactly what the team is building toward. The goal is to surface the tip of the iceberg while preserving the depth, so stakeholders who don't want the full journey can still get the insight they need.

Louise also shared a fresh example from the day before the webinar: a colleague had asked for another PowerPoint. Instead of rebuilding it, Louise used Ask TheyDo to pull insights across multiple journeys she hadn't formally mapped yet, creating a document with a summary at the top and full detail below for anyone who wanted to go deeper.

What's next

These capabilities are now live. If AI is enabled in your workspace, your admin can activate it. If it isn't, your CSM can sort that.

TheyDo Agent runs on the customer context your team has already built — not generic AI applied to CX data. Every output traces to evidence and is structured enough to send to a CXO.

We're also building TheyDo MCP, so teams across the business can access structured customer context through the LLMs they already use, without needing to navigate the journey themselves.

"This is the start of actually activating all the data that's already there," Jochem says. "We're building this context layer so that the rest of the org can self-serve, and so our CX teams can focus on the harder problems that actually bring us closer to the customer."

Talk to an expert to see how TheyDo Agent works in practice.