AI-powered insurance data analytics for risk management teams
LineSlip converts static insurance documents into structured, queryable data via LLM fine-tuning and RAG pipelines—a shift from manual Excel-based program management to automated intelligence. The tech stack reveals an LLM-native architecture (GPT, Llama, Falcon, Qwen with LoRA fine-tuning, Langchain, Pinecone, FAISS) layered atop Azure cloud and Microsoft BI tools (Power BI, SQL Server, Azure Cognitive Search). Hiring is heavily data-focused (10 of 15 roles) at senior and manager levels, consistent with active work on document intelligence, schema design, and RAG pipeline development—but elevated churn and Power BI performance bottlenecks suggest scaling challenges in the analytics delivery layer.
Notable leadership hires: Finance Director
LineSlip is a nine-year-old insurance technology company in New York that delivers AI-powered analytics for commercial risk management teams. The product automates the extraction and aggregation of policy data from complex, unstructured insurance documents into interactive dashboards and reports—replacing manual Excel-based workflows. The core use cases span renewal analytics, carrier relationship tracking, coverage gap identification, and strategic reporting. LineSlip operates across multiple geographies, with hiring in the U.S., Argentina, India, Pakistan, Romania, and South Africa.
LineSlip uses Power BI, SQL Server, and Azure cloud for analytics infrastructure; GPT, Llama, and Falcon LLMs with LoRA fine-tuning for document intelligence; and Langchain, Pinecone, and FAISS for RAG pipeline orchestration. Deployment runs on Azure Kubernetes Service and Databricks.
Active projects include fine-tuning LLMs for insurance data extraction, building RAG pipelines for claims processing, designing structured data schemas, containerizing LLM deployments on Azure Kubernetes, and addressing Power BI performance bottlenecks in reporting.
Other companies in the same industry, closest in size