Build custom CRE investment reporting agents on your ERP data with Leni
Friedman Real Estate (about 23 million square feet of commercial property and more than 21,000 multifamily units) is assembling AI agents on Leni's infrastructure that pull from the firm's ERP and accounting systems, apply Friedman's own reporting rules and metric definitions, produce reports and dashboards, export to PDF, and route finished work through the firm's normal review process—rather than buying a fixed reporting product they would have to customize.
At a glance
- Tools used
- Leni
- Category
- Brokerage ops
- Audience
- investor, broker
- Difficulty
- Builder
- Source
- Friedman Builds AI Agents Across Its CRE Platform
PLOT Daily (AI for CRE Collective) · Article · Sep 23, 2026 - First step
- Pick one recurring owner or lender report your team already builds by hand, write down the exact metric definitions and who must approve the PDF, then map which ERP fields feed each number before connecting any AI layer.
Compliance note: Keep material numbers traceable to source ERP records. Investment decisions and external commitments stay with qualified humans; treat AI output as a draft until reviewed.
Suggested prompt
Written by this directory, inspired by the source. Replace the [bracketed] parts.
We need a repeatable CRE investment/asset-management report agent. Report audience: [owner | lender | internal IC] Required sections: [list] Metric definitions we already use: [paste glossary] Source systems: [ERP/accounting names and which tables] Approval path: [who reviews before send] 1. Draft the agent job description: inputs allowed, outputs (PDF + dashboard), and verification steps that check figures against source records. 2. List every field the agent may read and every field it must never invent. 3. Write the human-review checklist the approver uses before the PDF goes out. Do not invent financial figures; leave placeholders for live ERP pulls.