PGGM enhances employee efficiency and search accuracy with Elastic AI-driven search

PGGM is a leading Dutch pension administrator serving 5.8 million participants. Managing over €250 billion in assets with approximately 2,000 employees, the organization is responsible for ensuring the long-term financial security of a significant portion of the Netherlands' population.

To maintain operational excellence, PGGM's innovation department is focused on leveraging new technologies to make the organization's broad workforce more efficient. By putting Elastic at the center of its search strategy, PGGM has transitioned from difficult-to-navigate legacy systems to a modern, AI-enhanced SmartSearch platform.

Before implementing Elastic, PGGM employees struggled to find information within the company's vast documentation. "Our biggest challenge is that the organization is quite broad and with SharePoint, it was hard to find your documentation," says Lauryn Cuffy, innovation manager at PGGM.

The legal team, for example, faced the daunting task of searching through over 350,000 documents to find historical cases, policies, or specific external emails. To solve this, Louic Vermeer, senior data science developer & innovation manager at PGGM, and his team built a centralized search engine powered by Elastic.

The platform ingests diverse data types, including emails, Word documents, and Excel sheets from SharePoint into Elasticsearch. By utilizing Elastic's ingestion pipelines, the team enriched the data with automatic classification and labeling, making it easier for users to filter and find exactly what they need.

The move from traditional keyword search to semantic search was a turning point.

This allowed the team to implement a retrieval augmented generation (RAG) workflow, ensuring the AI is grounded in PGGM's specific data.

The impact on efficiency has been significant:

• Time savings: Different teams reported saving between two and eight hours every week.
• Employee experience: By removing the "boring work" of manual searching, employees can focus on more strategic and interesting tasks.
• Onboarding: New employees, who may not yet know the specific company terminology, find it much easier to discover relevant documents using semantic search.

While the SmartSearch platform is an internal tool, its benefits extend to PGGM's 5.8 million participants. In the customer service center, agents must quickly find answers within a database of 2,000 Q&As to help participants on the phone.

With Elastic, agents can provide responses "as fast as possible" while ensuring the information remains "factual and consistent." This efficiency ensures that participants receive high-quality support during every interaction.

Looking ahead, the PGGM innovation team plans to evolve the platform from a search engine into a "question-answering engine." By further integrating generative AI and expanding the platform's reach, they aim to provide direct answers rather than just lists of documents.

"The relationship with Elastic is great and it feels like a community," says Cuffy. "When we have a question, they connect us to other clients who have similar problems to help us solve problems faster."