Receive daily AI-curated summaries of engineering articles from top tech companies worldwide.
Endigest AI Core Summary
This post explains how Addepar, a financial technology platform managing nearly $9 trillion in assets, built a scalable AI agent system called Addison using Databricks on AWS.
•Addepar migrated from legacy systems to a unified Databricks data platform, reducing pipeline costs by 60% and achieving 5x faster pipeline delivery.
•Addison is embedded natively in the platform and supports pull (Q&A), push (proactive alerts), and act (workflow orchestration) interaction modes using live, governed portfolio data.
•Addepar uses Databricks Agent Bricks with a Supervisor Agent coordinating Genie-powered analytics to move from single LLM prompts to multi-step agentic workflows.
•Models are served and hosted within Addepar's environment via Databricks Model Serving, with MLflow providing lifecycle tracking and auditability for compliance.
•Unity Catalog enforces fine-grained access controls across both data and AI systems, ensuring governance for regulated financial services clients.
This summary was automatically generated by AI based on the original article and may not be fully accurate.
Databricks
Google Cloud
Stripe