quality_assurance · realestate · workflow
Rexera uses LangGraph to reduce QC false positives to 2% in real estate transaction workflows
Rexera's QC application processed thousands of real estate workflows daily, but initial single-prompt LLM checks lacked the context and multi-step reasoning needed to handle complex, multi-dimensional real estate scenarios, producing high rates of incorrect issue flags.
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 · Workflow enters QC application
The QC application receives a real estate transaction workflow for review, processing thousands of such workflows daily.
Tools used
LangChainLangGraphLLMsCrewAI
Outcome
LangGraph's tree-like decision structure reduced false positives from 8% to 2% and false negatives from 5% to 2%, delivering greater consistency and accuracy across real estate transaction workflows.
What failed first
Single-prompt LLMs produced false positive rates of 35% and false negative rates of 10%. A multi-agent CrewAI approach improved both figures but agents still sometimes took incorrect decision paths in complex scenarios, leaving residual false positive and false negative rates.
Results
Volume35%
Grounding & classification
Source type: vendor customer story
31 fields verified against source quotes.
agentic workflowdata extractionmulti agent workflowquality inspectioncontractfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedreal estateaccuracy improvementerror reductionvendor customer storyback office opscompliance monitoringquality assuranceescalation workflowextract classify routehuman review queue