Case study

How RTL NEWS Is Shaping the Future of Newsrooms With AI-Powered Workflows

Media and Entertainment
rtl-case-study-fullscreen-hero-mobile-1024px-1024px-2

Challenge

Newsrooms receive thousands of stories daily, and sorting through them requires staff to balance accuracy vs. speed. RTL NEWS sought a way to automate these routine tasks and empower their editorial team.

Outcome

By implementing two AI modules with Endava and Google Cloud’s support, the Hot Topic Discoverer and the Consistency Checker, RTL NEWS has paved the way for higher quality content and improved speed-to-market.

In a modern newsroom, thousands of stories flood in daily that require sorting, verification and publication. And even for the most experienced editorial teams, balancing speed and quality can be a challenge. 

 

As they sought a solution to speed up processes and make manual consistency-checking more effective, RTL NEWS, a pioneer in digital news media, asked a bold question: How can we empower our editors with AI-powered tools so they can focus on what truly matters? 

 

With the support of our partner Google Cloud, we helped RTL NEWS further develop their existing prototype – which has additional AI-specific application options – into a solution that not only accelerates existing processes but also provides editors with full visibility and control.  

 

With the right AI tools in place, RTL NEWS can now automate routine tasks such as topic selection and quality control, accelerating time-to-market, relieving resource constraints and paving the path for higher-quality content. 

rtl-case-study-text-blocks-Image-1024px-993px-updatedV2

The solution: AI meets editorial excellence

Manual consistency-checking can be tedious and difficult to scale. Similarly, identifying relevant topics depends heavily on experience and subjective judgment. 

 

One way to solve for this is by leveraging state-of-the-art technology through the practical application of AI. Current advancements make it possible to break down complex challenges into individual tasks, handled by AI modules. Each of these tasks are assigned a clear set of rules to ensure optimal output, and these modules are orchestrated within a structured AI workflow. 

 

This partnership resulted in two groundbreaking modules that seamlessly integrate into a structured AI-powered editorial workflow: the Hot Topic Discoverer (HTD) and the Consistency Checker (CC). Both tools harness the power of Google Cloud, including Vertex AI, Looker and other advanced technologies, to deliver precise, scalable solutions that save the company valuable time and costs. 

AI module 1: Hot Topic Discoverer

Navigating a sea of information can slow down editors when trying to pinpoint relevant topics. Using AI, the Hot Topic Discoverer analyses news articles and evaluates them based on several factors and criteria that determine the news’ value. 

 

While the criteria remained consistent across media outlets, the weightings for these factors varied depending on the editorial priorities of each platform. For instance, some platforms prioritised emotional resonance, while others focused more on geographical proximity or unique topics. These weightings were carefully calibrated using an algorithm and validated by editorial teams to ensure accuracy and usability. 

 

Thanks to Google Cloud’s Vertex AI, the solution analyses large datasets efficiently and provides full transparency by explaining the basis for its evaluations, ensuring editors remain in control of their decisions.  

rtl-case-study-visual-1

 

Workflow overview of the Hot Topic Discoverer from the “RTL Newsroom Efficiency Case Study.”

With the Hot Topic Discoverer, we can focus on important stories and make well-informed decisions.”

Tatjana Anisimov

Head of Content Innovation & AI Products at RTL NEWS 

AI module 2: Consistency Checker

The sentence-based approach, selected after testing three methodologies, ensures high accuracy by splitting text into sentences using Python’s SpaCy library and validating them with Gemini Flash. Compared to ‘claim-based approaches’, which risk hallucinations or misinterpreted claims, the sentence-based method maintains the original message and reduces errors. 

 

Additional tests explored embedding techniques and full-text processing, but these were less accurate than the final method. By focusing on individual sentences, the tool delivers a recall rate of over 99% with an average latency of just four seconds, making it ideal for long-form articles. 

 

rtl-case-study-visual-3

 

Technical architecture of the Consistency Checker from the “RTL Consistency Checker Case Study.”

 

rtl-case-study-visual-2

Example evaluation

 

The close collaboration between the partners was highly appreciated, not just by RTL NEWS but also by Google: 

 

“Working with Endava was excellent,” said Thomas Heigl, Key Account Director Media and Entertainment, Google Cloud. “Their technical expertise and ability to seamlessly integrate solutions into existing workflows were instrumental in successfully delivering this innovative project. The solution provided will automate routine tasks and accelerate time-to-market, which will save valuable time and costs in a fast-paced newsroom environment.” 

rtl-case-study-2-text-blocks-Image-1024px-993px-updatedV2

More time, higher quality, greater success

The introduction of these AI-powered modules is transforming the day-to-day operations of RTL NEWS’ newsroom and is now entering the next phase, where the modules will be tested in practice and validated 

  • For editors: More time for creative research and enriching articles with exclusive content. 
  • For management: Faster time-to-market and higher-quality content, plus increased reach and engagement. 
  • For technical teams: Seamless integration into existing systems, high scalability and minimal latency.  

AI support systems not only relieve resource constraints but also create opportunities to gain competitive advantages through higher-quality, reliable and consistent content. 

 

With the success of these two modules, the path for further innovations is clear. Tools like the Hot Topic Discoverer and the Consistency Checker are just the beginning.  

 

Today, RTL NEWS is poised to shape the future of journalism with AI, equipping their newsrooms with the tools to deliver accurate, timely and engaging news. 

Interesting? We love when people share.

We can help you reach new heights

Let's connect