Friedman Real Estate and Leni Come Together to Build Reporting Workflows using Leni's AI Infrastructure.

Friedman used Leni's infrastructure to build its own agents and workflows to produce reports its investment and asset management teams rely on.

NEW YORK and FARMINGTON HILLS, Mich., Sept. 22, 2026 /PRNewswire/ -- Friedman Real Estate and Leni today announced that Friedman is building automated reporting agents and workflows on Leni's infrastructure for commercial real estate. Rather than buying a finished reporting product, Friedman's teams used Leni's

platform to assemble the workflows they actually needed, using their own data, their own definitions, and their own review steps. Those workflows now run on their own and produce reports Friedman can trace back to the source.

The two firms share a view that a real estate company should be able to build its own automation instead of waiting on a vendor roadmap or a custom development cycle. As Friedman scaled its portfolio and took on new properties, its operations teams absorbed a growing volume of custom reporting requests, each one slightly different from the last. Leni's infrastructure gave them a way to turn each of those requests into a repeatable agent, so the work runs without manual assembly and the accuracy and auditability Friedman's stakeholders expect stays intact.

What Friedman built

Friedman's first set of workflows covers custom reporting and the context around it. The data is pulled from Friedman's ERP and accounting systems, apply Friedman's own context and definitions, produce reports and dashboards in Friedman's format, export them to PDF, and route them for review. Work that used to be assembled by hand across several people and systems now runs as a workflow that Friedman controls and can change whenever a lender, owner, or internal team asks for something new.

Because Leni supplies the layer underneath, Friedman did not have to fund a bespoke engineering build to get there. The connectors, the data model, the specialized models, and the checks were already in place. Friedman's contribution was the part only Friedman knows: which numbers matter, how they are defined, what a finished report looks like, and who signs off.

The infrastructure underneath

Leni turns what is normally a long systems project into three steps a team can work through on its own.

Connect the ERP data. Leni's patent-pending Universal Data Model already speaks to seven major ERP and accounting systems, roughly 85 percent of the market, so teams connect their systems instead of specifying pipelines, mapping fields, or standing up a warehouse. Nothing in the source systems has to change.

Gather the context. Leni's patent-pending organizational memory captures the part no system of record holds: how the firm defines its metrics, what a finished report looks like, and who approves it. It builds as people work, so a team is not documenting its own processes up front.

Build on top. With the data connected and the context in place, teams assemble their own agents, customizations, and workflows without designing the architecture underneath. Accuracy is handled by the platform: specialized models and verification loops check every step against the source before an output reaches a person.

Those checks are why teams can build without trading away reliability. In Leni's published research, the architecture improved the accuracy and reliability of the underlying models by 7 to 15 percentage points and cut the cost of reaching the result by roughly 65 percent. In production it delivers task accuracy above 99.6 percent at about one-third the cost of frontier models, and every output carries a record of what was checked, against what, and when.

Why building beats buying here

A packaged reporting tool is fixed on the day it ships. The way a firm reports is not. Definitions change, owners ask new questions, portfolios take on new assets, and each change means another request routed back to a vendor. Infrastructure removes that dependency. Friedman can stand up the next agent itself, and the context it has already captured makes each one faster to build than the last.

That context stays with Friedman. Every connected system, corrected number, and approved deliverable becomes part of the firm's own operating knowledge. Reporting was the starting point, and the same foundation supports budgeting and variance analysis, investor and board packages, document review, and broader operational work as Friedman extends it.

For the wider industry, the takeaway is that firms no longer need to construct this infrastructure in-house to build with AI. Leni supplies the data architecture, the context layer, the specialized models, and the guardrails. The firm supplies its own conventions and builds on top.

Executive perspectives

"We did not want another reporting product that we would immediately need to change. We wanted to build our own workflows, and Leni's infrastructure is what made that possible. Our team defined the metrics and the review steps, and the agents now produce the reports and dashboards on their own, in our format, traceable back to the source. When a lender or an owner asks for something new, we build it ourselves instead of filing a request and waiting."

Jared Friedman, Co-CEO, Friedman Real Estate

"We provide the right infrastructure so that firms can experience the true promise of AI. Friedman's data was locked in closed systems, and the knowledge of how Friedman reads that data lived with its people. We connect the systems and capture that context, then give teams specialized models and verification they can assemble into their own agents. Friedman built reporting agents first because reporting hurt the most. The point is that the context layer belongs to Friedman, and every workflow it builds next runs faster and cheaper on it."

Arunabh Dastidar, Co-founder and Chief Executive Officer, Leni

About Leni

Leni is context-aware AI infrastructure that lets enterprises build their own agents and workflows for back and middle office work, starting with commercial real estate. Its platform connects closed ERP systems, captures how a firm defines and produces its work, and orchestrates verification on every step. Leni supports more than $80 billion in assets in North America. The company came out of Vector Institute Labs, co-founded by Nobel laureate Geoffrey Hinton, is SOC 2 Type II compliant, and is headquartered in New York. Learn more at https://leni.co.

About Friedman Real Estate

Friedman Real Estate is one of the nation's largest privately held, full-service commercial real estate organizations, delivering integrated solutions across advisory, brokerage, property management, financing, and construction services. Through a single point of contact, Friedman provides clients with the expertise and resources needed to maximize value across every stage of the real estate lifecycle.

With more than 20 million square feet of commercial property and over 19,000 multifamily units under management nationwide, Friedman combines institutional capabilities with entrepreneurial agility. The company's brokerage team oversees more than 600 active listings and has completed over $25 billion in transactions, while also serving as a trusted leader in receivership and distressed asset management. Backed by nearly four decades of ownership and operational experience, Friedman delivers strategic insights and results-driven solutions that help clients achieve their investment and business objectives.

Learn more at https://friedmanrealestate.com/

View original content to download multimedia:https://www.prnewswire.com/news-releases/friedman-real-estate-and-leni-come-together-to-build-reporting-workflows-using-lenis-ai-infrastructure-302885132.html

SOURCE Leni