Loading post…
DatabricksBob PisaniExplainer
How Addepar scales investment workflows with Databricks AI agents
Summary
Addepar, a global technology and data platform, manages nearly $9 trillion in assets and moved from older systems to a unified data intelligence platform on Databricks running on AWS. It ingests hundreds of disparate data feeds, standardizes and enriches them, and delivers results through products, APIs and data sharing. Since adoption, pipeline costs fell 60% versus legacy infrastructure, saving more than $2 million, while new pipelines and integrations became five times faster. Addison, a native AI experience embedded in the platform, combines governed portfolio Q&A, proactive insights and action-oriented workflows, using live data and Addepar’s core calculations engine. Addepar is adopting Databricks Agent Bricks, including Supervisor Agent flows with Genie-powered analytics, while Foundation Model Serving and managed MLflow support governed model serving, traceability, evaluation and iteration for human-supervised agentic workflows.
Context
Addepar serves registered investment advisors, family offices, private banks and global institutions. Its platform unifies portfolio, market and client data across public and private markets, making security, consistency, governance and auditability important requirements for its AI capabilities.
Approach / What changed
Addepar consolidated data engineering, analytics and AI on Databricks running on AWS, using Unity Catalog for permissions and access controls. Addison uses governed live data, Addepar’s calculations engine, Databricks Model Serving, Foundation Model APIs and MLflow. Agent Bricks Supervisor Agent coordinates Genie-powered analytics and supports multi-step workflows with human oversight, evaluation and traceability.
Takeaways
Addepar reports a 60% reduction in pipeline costs versus legacy infrastructure, more than $2 million in savings, and a 5x improvement in delivering new pipelines and integrations.
Addison combines pull-based questions, push notifications and action-oriented workflows, while referencing live governed data and the same portfolio calculations used elsewhere in Addepar’s platform.
Agent Bricks centralizes orchestration for agentic workflows, while Foundation Model Serving and managed MLflow provide governed endpoints, traceability, evaluation and iteration.
FAQ
How does Addison differ from a basic chatbot?
Addison is embedded in Addepar’s platform and integrates with portfolios, workflows and the core calculations engine. It supports questions, proactive insights and actions using live, governed data rather than only conversational responses.
How are security and governance applied to Addison?
Addison inherits Unity Catalog permissions and access controls, while models are served within Addepar’s environment through Databricks Model Serving. MLflow tracks and manages models, supporting lifecycle management, traceability and auditability.
What role does Agent Bricks play in Addison?
Addepar is adopting Agent Bricks Supervisor Agent to coordinate Genie-powered analytics and move beyond isolated prompts. It centralizes prompts, tools and validation logic for multi-step workflows that remain subject to advisor oversight.
Source and freshness
- Source
- databricks.com
- Published
- Added to Yomu
- Last updated
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.