Evidence: Medium50/100

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. The assistant is embedded in Personio's product and uses Amazon Bedrock Knowledge Bases to connect to additional knowledge sources.

Organization
Personio
Location
Germany
Published
June 2026

Reported outcomes

+70%

routine HR requests automatedAutomation & deflection

−15%HR support tickets reduced−21%time to manage HR reporting reduced−20%time spent on day-to-day processes reduced+18%customer productivity increased+95%weekly customer usage

Strategic outcomes

New product / capabilityLaunched embedded AI HR assistantNew product / capabilityAutomates routine HR requestsScale & capacityImproved scalability across use casesCost efficiencyReduced HR support workload
Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Routine HR requests automated: 70% increase

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

handles 70 percent of routine HR requests automatically

Normalized claim

HR support tickets reduced: 15% decrease

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

reduced HR support tickets by 15 percent

Normalized claim

Time to manage HR reporting reduced: 21% decrease

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

reduced the time to manage HR reporting by 21 percent

Normalized claim

Time spent on day-to-day processes reduced: 20% decrease

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

on day-to-day processes by 20 percent

Normalized claim

Customer productivity increased: 18% increase

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

overall productivity by 18 percent

Normalized claim

Weekly customer usage: 95% increase

AWS Solutions Case StudyJun 8, 2026Customer storyExplicit claimMedium evidence strength

95 percent of Personio's customers use the solution weekly

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
Personio
Provider
AWS
Maturity
Unknown

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

  • 1HR assistant
  • 2Employee self-service
  • 3Knowledge retrieval
  • Personio wanted to simplify everyday HR tasks as demand for AI-driven experiences increased.
  • The solution needed to support access to multiple foundation models and meet EU data residency and sovereignty requirements.
  • Sensitive employee data required strong control under the AWS Shared Responsibility Model.
  • Personio built Personio Assistant as an AI-powered capability embedded in its software using Amazon Bedrock.
  • The assistant handles natural-language HR questions, generates summaries, reports, and follow-up insights, and automates routine requests.
  • Personio connects the assistant to additional knowledge sources through Amazon Bedrock Knowledge Bases and uses Amazon S3, Amazon RDS, and AWS Lambda to coordinate requests, data flow, and performance.
  • The company also introduced prompt standardization and caching to improve scalability across use cases.
  • Personio Assistant handles 70 percent of routine HR requests automatically.
  • It reduced HR support tickets by 15 percent.
  • HR teams cut the time spent on reporting by 21 percent.
  • HR teams cut time spent on day-to-day processes by 20 percent.
  • 95 percent of Personio's customers use the solution weekly, and customer productivity improved by 18 percent.
Architecture

Personio Assistant is embedded inside Personio's HR software and uses Amazon Bedrock with Amazon Bedrock Knowledge Bases, Amazon S3, Amazon RDS, and AWS Lambda. The article also mentions prompt standardization and caching to improve scalability and consistent response patterns.

Sources & evidence1
Evidence: Medium50/100Evidence strength
  • Customer explicitly identified
  • Primary source available
  • Quantified outcome available
  • Technical implementation details available
Type: Customer StoryPublished: Jun 8, 2026Publisher: AWSEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.