AWS Only
FootballCo Improves Accuracy and Reduces Article Production Time by 80% with Firemind’s AI Solution
FootballCo partnered with Firemind to automate the creation of its "Where to Watch" articles with generative AI. By implementing a Proof of Concept (POC) using Large Language Models (LLMs), Firemind enabled FootballCo’s GOAL.com platform to streamline the production of match previews, significantly boosting efficiency.
AWS ONLY ·
FootballCo Improves Accuracy and Reduces Article Production Time by 80% with Firemind’s AI Solution
FootballCo partnered with Firemind to automate the creation of its "Where to Watch" articles with generative AI. By implementing a Proof of Concept (POC) using Large Language Models (LLMs), Firemind enabled FootballCo’s GOAL.com platform to streamline the production of match previews, significantly boosting efficiency.
At a glance
FootballCo is a global football media company, designed for the next generation of fans. Their mission is to build football communities that entertain, inform, and inspire, offering everything from news and analysis to live scores, video, and original reporting across digital platforms. With a global reach, FootballCo engages millions of fans worldwide, making it a major force in football media.
Challenge
Automating the creation of structured football content efficiently while maintaining factual accuracy.
Solution
Firemind built a pipeline utilising AWS services to enable the generation of match previews using AI.
Services Used
Amazon Bedrock
AWS Lambda
Amazon S3
AWS Step Functions
Outcomes
80-95% accuracy in generating articles
80% reduction in content generation time
Business challenges
Automating football content creation with high accuracy
FootballCo needed a solution to automate the creation of their “Where to Watch” (W2W) articles, which required consistent formatting and high factual accuracy. These articles, a key part of their content offering on GOAL.com, involved extensive manual effort by editors to ensure detailed match information was presented accurately and in a timely manner. As their platform grew and the demand for content increased, FootballCo faced challenges in scaling their editorial efforts without compromising the quality of their output.
The primary challenge was finding a way to automate the process of generating structured content—such as match details, viewing options, and team news -while maintaining a high standard of factual accuracy. FootballCo needed a solution that could not only speed up content production but also ensure that generated articles aligned with the editorial style that their audience expected. Additionally, ensuring that the AI model could adapt to evolving data inputs, like team rosters and league standings, was critical for preventing inaccuracies in the articles.
"Firemind's PULSE tool was able to quickly and accurately summarise vast datasets of customer surveys, ensuring we could take action against any negative customer experience elements."
Dean Macfadyen, Data Platform Engineer — Generative AI Customer
Solution
AI-driven content pipeline with AWS-powered automation
To solve FootballCo’s challenge of automating content generation, Firemind developed a AI-driven solution using AWS services. The goal was to automate the creation of structured “Where to Watch” (W2W) articles while maintaining high factual accuracy. The solution was built using a combination of AWS Lambda, Amazon Step Functions, and Amazon Bedrock, all integrated to form a seamless pipeline for generating match previews.
The process began with AWS Lambda, which handled serverless compute tasks to scrape relevant match data from FootballCo’s GOAL.com platform. Lambda functions were responsible for invoking custom-built web scrapers that extracted essential information, such as match schedules, team rosters, and historical data, and uploading this information to Amazon S3 for storage.
Next, Amazon Step Functions orchestrated the entire workflow, coordinating each step of the content generation process. Step Functions managed the flow of data between different AWS services and Lambda functions, ensuring that the data was correctly processed, stored, and passed to the next stage of the pipeline. This orchestration was critical for automating tasks such as managing scraped data, triggering model invocations, and handling validation processes.
Once the data was prepared, it was passed to Amazon Bedrock, which powered the core of the AI-driven article generation. Using Large Language Models (LLMs), Amazon Bedrock transformed the raw data into structured W2W articles, following a predefined template. The model generated content based on prompt engineering, ensuring that the articles were formatted with key sections like kick-off times, how to watch the match, team news, and head-to-head comparisons. The prompts were customised to adhere to FootballCo’s editorial guidelines, and specific instructions were included to prevent hallucination and maintain factual accuracy.
The generated content was then processed for validation and review, ensuring it met FootballCo’s standards. By leveraging the combined capabilities of these AWS services, Firemind created a pipeline that automated article creation, maintained high factual accuracy (80-95%), and significantly reduced the time editors spent manually producing content, leading to an 80% reduction in production time.
80% faster production:
The AI-generated content pipeline reduced the time to create articles by 80%.
High accuracy:
The AI solution generated articles with an 80-95% factual accuracy, significantly improving over manual methods.
AWS-powered scalability:
The solution leveraged Amazon Bedrock and AWS Lambda functions for seamless scaling.
Why Firemind
FootballCo chose Firemind as their partner due to Firemind’s expertise in developing AI-driven solutions that seamlessly integrate with existing infrastructures. Firemind’s deep knowledge of AWS services and proven track record of delivering scalable, efficient automation solutions made them the ideal choice for automating FootballCo’s content creation process. Their ability to quickly implement a tailored, high-accuracy solution that met FootballCo’s editorial standards was a key factor in this successful partnership.
1920%
Workflow speed increase
1,000 documents in 12.5 minutes compared to 4 hours by human operator
88%
Keyword accuracy
for leading categories within data modelling & training
Added value
We were also able to take all stakeholders on a journey concerning how Cloud Adoption and Machine Learning would benefit their customers and their business continuity, all in a 12 week timeline from start to finish.
Get in touch
Want to learn more?
Seen a specific case study or insight and want to learn more? Or thinking about your next project? Drop us a message below!