AWS Only
Immedis Leverages Generative AI to Proactively Monitor Payroll Compliance Changes
Immedis, a global payroll provider, partnered with Firemind to develop a solution that leverages Amazon Bedrock's large language models to automatically detect and summarise changes in government websites impacting payroll compliance.
AWS ONLY ·
Immedis Leverages Generative AI to Proactively Monitor Payroll Compliance Changes
Immedis, a global payroll provider, partnered with Firemind to develop a solution that leverages Amazon Bedrock's large language models to automatically detect and summarise changes in government websites impacting payroll compliance.
At a glance
Immedis, now part of UKG is a specialised provider of enterprise technology solutions for global payroll, tax, and HR, simplifying the complexities of managing payroll across multiple countries.
Challenge
Immedis needed to transition from a reactive to a proactive approach in capturing legislative changes affecting their payroll software, so they partnered with Firemind to develop an innovative AI-powered solution.
Solution
Firemind developed a solution leveraging web scraping, Amazon Bedrock's language models, and AWS services to automatically detect and summarise relevant changes in government websites.
Services Used
Amazon Bedrock
AWS Lambda
Amazon S3
Amazon DynamoDB
Outcomes
High accuracy change detection
Compliance integration via timely updates
Business challenges
Transitioning from reactive to proactive compliance monitoring
Immedis’ past processes relied on partner companies to report legislative changes, leading to delays and the risk of missing important updates. The company sought to transition to a more proactive approach, ensuring they are the first to know and respond to changes that impact their payroll software.
This reactive model was inefficient and exposed Immedis to potential compliance risks, prompting the need for a more innovative solution to stay ahead of regulatory updates.
“It was about finding an AWS Partner that understood our ethos and values. It’s been really refreshing talking to Firemind about the the project with clear communication and without the usual jargon and abbreviations.”
Pete Kilbane, Commercial Director — MRC
Solution
Firemind’s AI-powered payroll compliance monitoring solution
Firemind partnered with Immedis to develop a solution that leverages the power of large language models and web scraping to automatically detect and summarise relevant changes in government websites. By integrating this AI-driven system, Immedis can now quickly identify and address compliance updates, improving their service delivery and maintaining a competitive edge in the payroll software market.
The solution offers both an “Augmented Comparison” approach for testing, as well as an “Automatic Comparison” feature to continuously monitor real-world regulatory changes. The Augmented Comparison allows Immedis to manually modify web content and test the system’s change detection capabilities, while the Automatic Comparison continuously scrapes target websites and identifies any differences.
This approach empowers Immedis to proactively stay ahead of evolving payroll regulations, ensuring their software remains compliant and their customers receive the highest level of service.
Highly accurate change detection
The solution's language models demonstrated a remarkable ability to detect even the most subtle changes, such as single-word alterations, ensuring Immedis is alerted to all relevant regulatory updates.
Faster compliance integration
By providing timely updates on legislative changes, the solution enables Immedis to quickly integrate compliance updates into their payroll software, improving service delivery to their partners and customers.
Model Spotlight
Claude v1 + v2
We chose to use versions 1 and 2 of this particular language model due to several key advantages. First, it significantly reduced the need for prompt engineering, making it more user-friendly and efficient. Additionally, the larger context window allowed for the processing of more information in a single interaction, thanks to the increased token capacity.
Finally, the model delivered a noticeable improvement in speed, enabling faster and more responsive performance. These factors combined to make it an ideal choice for our needs.
Why Firemind
“It was really about finding an AWS Partner that understood our ethos and our values, and echoed the same."
Looking to use AI/ML, meant MRC were looking for a partner that could guide them through technological advancements and the cloud. MRC needed to be provided full understanding, confidence and training, across all stakeholders, to embrace the new innovation.
Working with Firemind, the path to automate and optimise MRC’s processes were defined, then validation of challenges in handwritten medical documents, such as doctor’s notes, were provided.
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!