From Order Taking to Operational Visibility

When Delta's digital content operation shifted from an on-demand, order-taking model to a structured sprint-based workflow, the way the team communicated its work had to change as well.

Previously, content requests were handled largely independently. Work was assigned, completed, and published on individual timelines, with stakeholder communication happening primarily between the content editor and the person who had requested the work.

The new operating model created a different need: stakeholders needed visibility into the work as a system.

What was being worked on? What was coming next? When should a stakeholder submit a request? When could they expect delivery? What had been completed? And how did the team's work contribute to broader business goals?

As the communications lead for the new sprint management team, I took responsibility for answering those questions.

The Challenge

There was no established reporting process to support the new operating model.

The information needed to communicate progress already existed across the team's workflow data, but extracting it, interpreting it, and turning it into useful communication would have required substantial manual effort.

I saw an opportunity to do something different: use the data already being generated by the operation as the foundation for an automated communications and reporting ecosystem.

Rather than simply creating another status report, the goal was to make stakeholder communication more timely, consistent, targeted, and useful.

The Approach

I began experimenting with AI-assisted development using Kiro, working from data exported from Workfront, the platform used to manage the team's content work.

The resulting system evolved into a collection of recurring reports and communications designed for different audiences.

Some communications are targeted directly to stakeholders whose work has just been completed or is entering an upcoming sprint. Others provide broader visibility to leadership, the Digital Experience organization, or the wider team.

The reports don't simply reproduce the underlying data. AI is used to interpret the information, identify relevant metrics and trends, summarize the work, and provide narrative context around what the data means.

I also established a set of parameters and requirements that guide how the reports are generated. These include:

• What information should be extracted
• How the data should be summarized
• How business priorities and enterprise goals should be reflected
• How communications should be structured for different audiences
• Delta standards for visual presentation and email design
• Editorial and language guidelines
• What information should intentionally be excluded

For example, early versions of the reporting included individual employee names associated with completed work. After reviewing the output with teammates, I determined that identifying individuals wasn't necessary for the purpose of the reporting. I incorporated that decision into the reporting requirements so subsequent reports consistently focused on the work rather than individual contributors.

The result was not simply a collection of AI-generated emails. It became a repeatable reporting system with defined rules, editorial judgment, business context, and human oversight built into the process.

Extending the System Beyond Reporting

The same AI-assisted approach led to another useful application: operational dashboards for content and experience components managed through AEM.

Some of the underlying information used to manage these experiences is stored as JSON. While the raw data contains the information needed to understand what is live, it isn't particularly easy for a person to read or compare — especially when examining multiple environments.

I built dashboards that transform that underlying data into visual representations and make it possible to compare environments such as staging and production much more easily.

What previously required manually parsing and comparing JSON could now be understood through a visual dashboard almost immediately.

Impact at a Glance

The Result

The biggest result wasn't simply the time saved.

The new reporting ecosystem gave stakeholders a level of visibility into the content operation that had not previously existed.

Stakeholders can see the status of their requests, understand what was completed in a previous sprint, know what is scheduled for an upcoming sprint, and use that information to communicate with their own leadership.

The communications also created visibility beyond the immediate stakeholder audience. Leadership several levels above my position began noticing the reports, providing feedback, and requesting additional information and capabilities.

That feedback confirmed something important: the reporting was not simply administrative overhead. It was becoming a useful source of organizational visibility.

What This Demonstrates

Operational Excellence

Recognizing that a change in operating model requires a corresponding change in the systems and communications that support it.

AI-Assisted Development

Using AI as a development and problem-solving partner to rapidly build practical tools around real operational data.

Automation

Turning recurring manual data compilation and analysis into repeatable workflows.

Stakeholder Enablement

Giving people the information they need to understand progress, anticipate outcomes, and communicate effectively with their own organizations.

Data Storytelling

Moving beyond raw metrics to create reporting that explains what the data means and why it matters.

Governance & Editorial Judgment

Establishing rules for what information should be included, how it should be presented, and what should intentionally be excluded.

The Bigger Lesson

The most valuable part of this work wasn't the technology itself.

The technology made it possible to build quickly, but the real work was understanding what information people needed, why they needed it, how different audiences would use it, and how to turn operational data into a story that people could act on.

That combination — process thinking, communications, data, automation, and AI-assisted development — is where I see significant potential for improving how modern organizations work.

Tools & Technologies