Case Study: How Neople delivers agentic customer-service AI with Weaviate
Key results
The challenge
Neople builds GenAI digital co-workers (“Neople Assistants”) that must process large volumes of company-specific knowledge before responding to a customer case. On its original Postgres database it was impossible to provide real-time responses; assistants search multiple times per query, and replies could take minutes — long enough that a human could have completed the same task.
The solution
Neople replaced Postgres with Weaviate as its AI-native vector database, running inside the Neople tenant and deployed via Docker and AWS CloudFormation. Weaviate's out-of-the-box reranking module and hybrid search let Neople remove custom-built components while improving result quality.
“We're really eager to learn from other people and to use services like Weaviate that specialize in vector databases to improve our offering. In the end our main goal isn't to maintain a database, it's to deliver the best results and user experience for our customers.”
JNJob NijenhuisCo-founder and CTO, Neople
The results, in context
Search result time dropped from an average of 10 seconds to less than 1 second — a 90% reduction — and Neople increased the number of data objects stored by a factor of 1000 while improving query response times. Removing a custom re-ranking mechanism in favor of a Weaviate module also reduced developer toil.