A unified knowledge and AI basis for monetary providers
Addepar is a world know-how and knowledge platform that empowers funding professionals to show advanced monetary info into actionable intelligence. Registered funding advisors, household workplaces, non-public banks and world establishments depend on Addepar to unify portfolio, market and shopper knowledge and ship a complete portfolio view throughout private and non-private markets.
Knowledge and AI are elementary to this mission. Addepar now manages practically $9 trillion in property on its platform, and purchasers depend on safety, high quality and consistency to make knowledgeable, high-stakes choices. To assist this, Addepar moved from a group of older methods and database instruments to a single knowledge intelligence platform on Databricks operating on AWS. That platform ingests lots of of disparate knowledge feeds, standardizes and enriches them after which delivers the outcomes to purchasers by means of merchandise, APIs and knowledge sharing.
Constructing on Databricks for scale, governance, and collaboration
Addepar selected Databricks to unify engineering, analytics and AI on a single, ruled knowledge platform. Collaborative notebooks and SQL let inner groups work in a single place, whereas Unity Catalog offers the fine-grained permissions and entry controls {that a} world monetary providers footprint calls for.
The result’s a single supply of fact that engineers, analysts, and now AI methods can all depend upon.
This choice has produced a transparent enterprise impression. Since adopting Databricks, Addepar has lowered pipeline prices by 60% versus legacy infrastructure—driving greater than $2 million in infrastructure and knowledge processing financial savings—and achieved a 5x enchancment within the velocity of delivering new pipelines and integrations. That acceleration helps onboarding, shopper supply and experimentation, whereas the Databricks and AWS mixture offers Addepar the size and reliability wanted to develop with its purchasers.
Addison: a local AI expertise embedded within the platform
Constructing on its unified knowledge basis, Addepar has launched Addison, a local AI expertise embedded instantly throughout the platform. Addison is designed to offer trusted steerage and actionable insights which are grounded in Addepar’s core knowledge and workflows.
Addison goes past a chat-based interface, to:
- Dwell inside Addepar’s core platform, built-in instantly with portfolios, options and workflows.
- Perceive the “nouns and verbs” of finance within the context of Addepar’s knowledge mannequin.
- Mix Q&A, proactive insights (push) and action-oriented workflows right into a single expertise.
- Floor related market information alongside portfolio knowledge, serving to advisors join shopper holdings to present market occasions.
- Run on Addepar’s core calculations engine, referencing the identical portfolio metrics and efficiency calculations used throughout the platform.
For funding professionals, Addison acts like a digital accomplice:
- Pull: Advisors ask questions like, “Break down this portfolio’s options allocation,” “If charges rise by 50 bps, what’s the projected impression on fastened revenue length?” or “Establish any accounts which have drifted greater than 3% from the goal,” and Addison responds utilizing reside, ruled knowledge.
- Push: Addison surfaces notifications and occasions, comparable to rising dangers, alternatives or anomalies in portfolios, with out requiring express prompting.
- Act: Advisors provoke workflows, comparable to operating a monetary plan,, or exploring various allocations, perceive portfolio developments and behaviors – whereas Addison helps orchestrate the underlying knowledge and steps throughout Addepar instruments and workflows. These capabilities are designed with people within the loop, maintaining funding professionals firmly answerable for choices and actions.
The imaginative and prescient is that pure language, workflows and clever brokers turn out to be the first approach customers work together with Addepar. By offloading tedious knowledge manipulation and orchestration to Addison, funding professionals can focus extra time on relationships and strategic choices.
Secure, scalable GenAI for monetary providers
As a result of Addepar’s purchasers function in extremely regulated domains, Addison’s structure should be secure and scalable in ways in which generic client fashions, comparable to direct calls to public LLMs, can not match. Addepar prioritizes safety, knowledge privateness and governance, and has designed its AI stack accordingly.
By reworking its infrastructure on Databricks, Addepar makes use of Unity Catalog, with permissions and entry controls deeply built-in into its surroundings. Those self same controls floor in Addison. A mixture of cutting-edge frontier fashions are served and hosted inside Addepar’s surroundings through Databricks Mannequin Serving, and are tracked and managed with MLflow, delivering constant lifecycle administration and auditability.
Conserving each knowledge and fashions contained in the Addepar ecosystem is essential for personally identifiable and shopper‑identifiable knowledge throughout Addepar’s world infrastructure footprint. It helps the corporate meet shopper expectations round threat, compliance and authorized or jurisdictional issues.
This strategy means Addison isn’t just an LLM endpoint. It’s an AI system that inherits the identical governance ensures as the remainder of Addepar’s platform, one thing that might be considerably tougher to attain with fragmented instruments or unmanaged exterior APIs.
From LLMs to brokers with Agent Bricks, Basis Mannequin Serving and MLflow
Easy LLM prompts could be highly effective, however making them dependable and repeatable sufficient for manufacturing monetary providers workflows is troublesome. It requires orchestration, validation and iteration to achieve the extent of consistency advisors and traders want.
Addepar is now adopting Databricks Agent Bricks as the subsequent evolution of its AI journey, beginning with Supervisor Agent that coordinates Genie‑powered analytics behind the scenes. Addison makes use of these Supervisor flows to maneuver from “LLM plus immediate” to trusted, agentic workflows, the place the system can execute sequences of actions on behalf of advisors with their oversight. What was beforehand a disjoint, guide strategy of wiring collectively prompts, instruments and validation logic is now centralized and simplified by Agent Bricks, together with early use of multi‑agent Genie workflows to energy inner Slackbots and advisor experiences.
Addison leverages LLMs served from Databricks Basis Mannequin APIs, which offer entry to state-of-the-art fashions from a wide range of mannequin suppliers by means of ruled serving endpoints. Manufacturing monetary providers workflows demand transparency, audibility, and fine-grained analysis of AI accuracy. Addepar leverages Databricks Managed MLFlow to energy traceability and granular insights into particular person agent workflows. Addepar additionally now makes use of MLFlow to develop, consider, and iterate on Addison’s efficiency and conduct.
For Addepar, all of this implies it will possibly outline agent workflows, comparable to multi-step portfolio analyses, planning flows or automated perception technology, check them rigorously, and deploy them with governance, all on the identical platform that powers its core knowledge. It is a uniquely Databricks worth proposition: unified knowledge, governance and agent orchestration in a single place.
Collaboration and knowledge sharing as a pressure multiplier
Databricks has additionally modified how Addepar collaborates internally and with purchasers. Beforehand, several types of customers inside Addepar and at shopper organizations usually labored in a transactional approach utilizing spreadsheets, extracts and one-off API exchanges. Collaboration was restricted and disjointed.
With Databricks Notebooks and Unity Catalog, Addepar can now share knowledge, code and SQL in a single surroundings with the precise entry controls. Groups can work on knowledge and fashions in the identical place, and that collaboration extends to AI. They will share fashions, configurations and prompts with constant context. For purchasers, with the ability to view the identical knowledge concurrently builds belief, reduces miscommunication throughout onboarding and ongoing operations, and helps a extra correct and clear view of portfolios.
A partnership targeted on outcomes
Addepar offers the foundational knowledge platform for the funding ecosystem, bringing collectively advanced portfolio, market and shopper knowledge to energy the workflows funding professionals depend on on daily basis. To assist the size, safety and innovation the platform requires, Addepar works carefully with know-how companions like Databricks and AWS, whose capabilities assist energy key parts of its knowledge infrastructure. These partnerships are constructed round open change and shared success relatively than a easy vendor transaction.
As Databricks continues to advance its knowledge and AI capabilities, Addepar expects Addison to turn out to be the first approach many customers expertise the platform. By combining a unified, ruled knowledge basis with GenAI and brokers, Addepar helps funding professionals reduce by means of complexity throughout portfolios, knowledge and workflows to make extra knowledgeable choices and ship higher outcomes for the purchasers they serve.
Attend Databricks AI Days in a metropolis close to you to discover ways to take management of your knowledge and construct AI brokers that drive enterprise impression.