back_office_ops · realestate · workflow
CBRE powers unified property management search and digital assistant using Amazon Bedrock
CBRE's property management professionals had to sift through millions of documents and switch between multiple separate systems and databases to locate property data, with no unified way to query structured and unstructured information in natural language.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Property manager submits query
Property managers interact through the PULSE user interface, which serves as the gateway for keyword searches and natural language queries.
Tools used
Amazon BedrockAmazon OpenSearch ServiceAmazon Nova ProClaude HaikuAmazon ElastiCache for RedisAmazon TextractAmazon S3Amazon Titan Text embeddings v2PostgreSQLMS SQLPULSEMicrosoft B2CSQSClaude 3 Haiku
Outcome
CBRE's unified PULSE search system, powered by Amazon Bedrock with RAG and Amazon OpenSearch Service, enables property management professionals to query across structured and unstructured property data in natural language, achieving a 67% reduction in SQL processing time, 80% improvement in query performance, and 95% accuracy for business decisions, while significantly reducing manual effort per user annually.
Results
Time saved67%
Volume80%
Grounding & classification
Source type: platform led case
46 fields verified against source quotes, 2 dropped as unverifiable.
conversational aidata extractiondocument aienterprise searchragsummarizationcontractemailknowledge basemetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedreal estateaccuracy improvementcost reductioncycle time reductionemployee productivityplatform led caseback office opsextract classify routerag answering