80%
“they reduced their operational costs by over 80%”
As published on weaviate.io. Captured by usedby on Oct 8, 2026.
What happened
predori runs a patent intelligence platform whose semantic search and retrieval run on Weaviate Cloud's managed vector database, replacing a previous Lucene-based AWS service. It is also used as the foundation for building agentic RAG systems.
Summary written by usedby from the source page, in English. The figures are those of Weaviate and predori, not ours.
- factor of 10“By moving away from the Lucene-based AWS setup, predori immediately cut their operational costs by a factor of 10.”
By switching to Weaviate's managed vector database, they reduced their operational costs by over 80%, freed their team to innovate, and cleared the path for building advanced agentic RAG systems that will define their future.
We were trying to squeeze a vector database into what is not really a vector database, and it was super expensive and just not good. It was just the wrong technology, a complete overkill for the mathematical problem of approximate nearest neighbor search.
What the story claims, and what we checked
We compared the story with its live page on Oct 8, 2026.
- The figure: 80%CheckedPrinted word for word on the page, near the name of predori.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of predori.
- predori uses WeaviateCheckedConfirmed line. Latest check across sources: Oct 8, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.
More stories
Same company, same tool or same industry.
