finance_ops · finance · workflow
FactSet standardizes GenAI on Databricks Mosaic AI, cutting latency by over 70%
FactSet lacked a standardized LLM development platform — engineers across teams used disparate tools, cloud-native services, and bespoke solutions with no cohesive governance or data lineage framework.
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 · News data ingested via Delta Live Tables
Delta Live Tables ingests and parses news data in an XML format.
Tools used
DatabricksDatabricks Mosaic AIMLflowDelta Live TablesVector SearchUnity CatalogModel Servingmeta-llama-3-70bDBRXFoundation Model APIsLangchainHuggingFaceLlama 3MistralOpenAIAnthropicMLflow Deployments Server
Outcome
Standardizing on Databricks Mosaic AI reduced code generation latency by over 70% and cut Text-to-Formula end-to-end latency by about 60%, while providing centralized governance and democratizing advanced AI workflows across teams.
What failed first
The initial commercial LLM pipeline for code generation produced over a minute of response time, and the Text-to-Formula RAG approach hit a quality ceiling that prevented scaling to more complex formulas.
Results
Time savedover a minute
Volumeover 70%
Running sincelate 2023
Grounding & classification
Source type: technical build writeup
46 fields verified against source quotes.
code generationragsummarizationknowledge basefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedfinancial servicessoftwareaccuracy improvementcycle time reductionemployee productivitytechnical build writeupback office opsfinance opsrag answering