{"slug":"crisis-text-line-fine-tunes-an-llm-powered-conversation-simulator-on-databricks-to-train-crisis-counselors","url":"https://findausecase.com/use-cases/crisis-text-line-fine-tunes-an-llm-powered-conversation-simulator-on-databricks-to-train-crisis-counselors","title":"Crisis Text Line fine-tunes an LLM-powered conversation simulator on Databricks to train crisis counselors","description":"Crisis Text Line, a nonprofit text-based mental health crisis service supporting 1.3 million conversations a year, used Databricks MLflow and fine-tuned versions of Llama 2, trained on synthetic conversation role-plays created by clinical staff, to build an LLM-powered conversation simulator that lets new volunteer crisis counselors practice engagement strategies without real-world repercussions. The simulator has been used by over 50 volunteers and clinicians, and the organization is also developing a conversation-phase classifier to help assess response quality.","company":"Crisis Text Line","industry":"Technology & Software","aiCapabilities":["Large Language Models","Conversational AI"],"technology":["MLflow","Spark Declarative Pipelines","Unity Catalog","Llama 2","Agent Bricks"],"deployment":"Public Cloud","problemStatement":"Crisis Text Line's data landscape was siloed in terms of record reporting, with business rules and context inconsistent or lost in data silos, causing downstream operational teams to struggle making efficient, real-time decisions; legacy systems also suffered simple queries timing out and multiple points of failure from batch-script data transformation.","solutionApproach":"Crisis Text Line centralized its data on the Databricks Data + AI Platform to create a single source of truth with a federated data store, used Unity Catalog for granular table- and column-level access control, MLflow to manage the full model lifecycle, and Spark Declarative Pipelines for its post-processing pipeline, then fine-tuned versions of Llama 2 on synthetic conversation role-plays from clinical staff to build an LLM-powered conversation simulator.","businessValue":"Databricks helped Crisis Text Line dramatically reduce the time required to make critical datasets available to clinical teams, analytics groups and future ML work, increased user adoption of dashboard artifacts, increased program ROI as customers and affiliates learned to trust its operational and analytical expertise, and reduced infrastructure and engineering overhead; the LLM-powered conversation simulator has been used by over 50 real volunteers and clinicians to boost training confidence.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/crisis-text-line","dates":{"publishedAt":"2026-09-16T09:05:16.104Z","publishedAtSource":"pipeline","updatedAt":"2026-09-16T09:05:16.104Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/crisis-text-line-fine-tunes-an-llm-powered-conversation-simulator-on-databricks-to-train-crisis-counselors. Bulk republication requires permission."}