Building an AI HR assistant using Amazon Bedrock with Personio
HR tech company Personio built an AI-powered assistant on Amazon Bedrock to automate requests and improve workflows.
Benefits
Overview
As demand for AI-driven experiences increased, human resources (HR) software provider Personio sought to simplify everyday tasks. The company took its first steps into generative AI by incorporating intelligent capabilities into its product to improve how HR teams access and manage employee data. Working alongside Amazon Web Services (AWS), Personio built an AI-powered assistant that handles 70 percent of routine HR requests.
The solution reduced the time to manage HR reporting by 21 percent and day-to-day processes by 20 percent, freeing HR teams to focus on strategic, meaningful work. To meet data residency and sovereignty requirements, Personio stores data within the European Union, maintaining data protection standards under the AWS Shared Responsibility Model.
About Personio
HR tech company Personio helps organizations across Europe manage employee data, streamline processes, and support day-to-day operations. Its AI-powered platform spans the entire employee life cycle, from core HR to talent and payroll.
Opportunity | Using AWS to build an AI HR assistant for Personio
As generative AI gained momentum, Personio identified an opportunity to transform how HR teams handle day-to-day operational tasks. The software provider wanted to build an AI assistant that could simplify everyday work while meeting enterprise requirements for scale, flexibility, and data privacy. At the same time, the solution needed to support access to multiple foundation models (FMs) and keep pace with rapid changes in AI.
Because the company handles employee records, maintaining control over sensitive data was essential. To guide its approach to AI development while strengthening security, Personio worked closely alongside AWS, building on a long-standing relationship. “AWS had the level of scale, processing, and commitment to security that we needed,” says Alex Bannon, engineering manager at Personio.
Solution | Building intelligent workflows by using Amazon Bedrock
Personio chose Amazon Bedrock, a fully managed service for building generative AI applications and agents at production scale, to accelerate development while maintaining flexibility and strong data governance. Because the service doesn’t store or use customer data to train FMs, data remains within Personio’s control.
The company developed Personio Assistant as an AI-powered capability that is embedded into Personio’s software. Using Personio Assistant, teams can interact with data in natural language to find information and generate insights while exploring AI workflows. Personio Assistant answers common questions, such as those about leave balances or payroll details, and generates summaries, reports, and follow-up insights that are based on user input. To deliver more relevant, accurate, and customized responses, Personio Assistant also connects to additional knowledge sources through Amazon Bedrock Knowledge Bases.
Personio adopted several AWS services to coordinate requests between the solution’s components and support data flow, reliable processing, and system performance at scale. To save and access the data that powers Personio Assistant’s responses, Personio relies on Amazon Simple Storage Service (Amazon S3), an object storage service, and Amazon Relational Database Service (Amazon RDS), an easy-to-manage relational database service. The Personio team can run code without thinking about servers or clusters by using AWS Lambda. To observe and optimize workloads at virtually any scale, the team implemented Amazon CloudWatch.
The software provider also introduced prompt standardization and caching and established consistent communication patterns between AWS services to improve scalability across use cases. Throughout development, AWS provided technical guidance. “Onsite training alongside AWS fast-forwarded our work by months,” says Bannon. Personio used the AWS Countdown program as part of its AWS Enterprise Support plan, which businesses use to accelerate innovation, strengthen security, and streamline cloud operations. As a result, the company sped up the development and launch of its solution.
Outcome | Improving efficiency and establishing an agentic AI future
Handling 70 percent of routine HR requests automatically, Personio Assistant reduced HR support tickets by 15 percent. HR teams cut the time they spent on reporting by 21 percent and on day-to-day processes by 20 percent, and employees get answers more quickly. Now, 95 percent of Personio’s customers use the solution weekly to analyze data, identify trends, and take action more effectively. As a result, customer teams are seeing an 18 percent improvement in overall productivity.
After implementing AI in its development workflows, Personio has increased its own teams’ productivity as well. “Since adopting AWS services for AI development, we’ve improved development velocity and response quality,” says Bannon. “This helps us confidently test new features and deliver results that customers can trust.”
Looking ahead, Personio plans to expand its use of generative AI to develop specialized HR agents that can both provide insights and take action, extending these capabilities across more workflows. “Using AWS, we will build the next generation of our intelligent HR solution to help organizations focus on what matters: their people,” says Bannon.
Using AWS, we will build the next generation of our intelligent HR solution to help organizations focus on what matters: their people.
Alex Bannon
Engineering Manager, PersonioAWS Services Used
Did you find what you were looking for today?
Let us know so we can improve the quality of the content on our pages