The carry trade is dead, and capital is moving to whoever can manufacture cash flow. Takeaways from a day with more than 250 investors and operators in emerging real estate.
Private wealth has passed the institutional market, and most sponsors have no idea how to reach it. A workshop on raising from family offices and RIAs.
Most operators source deals the same way: broker blasts, relationship networks, listing platforms, referrals, and a steady stream of offering memoranda arriving in the inbox. From there comes the familiar sequence: read the OM, screen the opportunity, pull market data, run a back-of-the-envelope underwrite, decide whether it’s worth pursuing, and, if it is, prepare materials for investment committee.
The greatest opportunity lies in compressing those workflows into AI agents that run autonomously with human oversight at critical decision points.
We've begun doing this internally with a handful of operating partners. But since we don't have the capacity to work with every operator, we're opening the hood on what we're doing in a workshop next week.
The latest generation of AI tools—led by Claude and an expanding ecosystem of real estate data platforms—is making it possible for small acquisitions teams to operate with the throughput of organizations several times their size. Instead of spending hours deciding whether to pursue a deal, firms can compress much of that work into minutes, reserving human judgment for the opportunities that truly deserve it.
The agents we’re building with operators today perform tasks that would have required a full acquisitions team just 18 months ago:
Reading and abstracting offering memoranda in seconds
Screening opportunities against a firm’s buy box
Pulling parcel, ownership, demographic, zoning, and permitting data
Preparing first-pass deal summaries and underwriting assumptions
Drafting investment committee memoranda
Monitoring multiple deal sources simultaneously for new opportunities
The workshop provides a practical introduction to building exactly that system.
About the Workshop
Next Thursday, August 13 at noon ET, I’ll lead a live two-hour workshop on building and deploying an AI acquisitions agent from scratch using Claude alongside leading real estate data platforms.
The session is split into two halves.
First, you’ll learn how to build an AI acquisitions agent from scratch using Claude—giving it a brain, memory, reusable skills, access to external data sources, and workflows tailored to your acquisition process.
Then, you’ll watch that agent execute a complete acquisitions workflow through a live case study, from sourcing and screening a deal to preparing investment committee materials.
Thursday, August 13 | 12:00–2:00 PM ET | Zoom | $299
The session is designed for principals, acquisitions professionals, analysts, underwriters, asset managers, and capital markets professionals who want to stop hearing about AI in acquisitions and start using it. No programming background is required.
What the Session Covers
Part One: How to Build the Agent (Approx. 60 Minutes)
We’ll build a fully functional acquisitions agent live, layer by layer, explaining what each component does and why it matters.
The Brain: System Instructions & Custom Prompts: We’ll write the core system prompt that teaches the agent how to think like an acquisitions professional—how to evaluate buy-box fit, recognize key deal characteristics, identify risks, and communicate findings consistently.
The Memory: Buy Boxes, Investment Criteria & Historical Deals: We’ll load the agent with your acquisition criteria, investment strategy, prior deals, underwriting assumptions, and market knowledge so it operates with the context of your business rather than as a generic chatbot.
The Skills: Reusable Acquisition Workflows: We’ll create reusable prompt libraries for common acquisitions tasks: OM abstraction, market research, rent and sales comp analysis, investment committee memo drafting, risk identification, and broker response preparation.
Connecting External Data: You’ll learn how to connect Claude with publicly available property and market data, including parcel information, ownership records, demographics, permitting activity, and other acquisition inputs.
Putting It All Together: Finally, we’ll assemble the complete acquisitions agent and show how each layer works together as a repeatable operating system for sourcing and evaluating opportunities.
Part Two: Deploying the Agent (Approx. 60 Minutes)
In the second half, we’ll put the agent to work against a realistic acquisition opportunity.
Live Demo 1: Deal Intake - We’ll feed the agent a new offering memorandum and watch it extract the critical information, normalize the data, and summarize the opportunity.
Live Demo 2: Opportunity Screening - The agent will compare the opportunity against a defined buy box, identify strengths and weaknesses, and determine whether the deal merits deeper underwriting.
Live Demo 3: Market Intelligence - We’ll connect publicly available data—including parcel records, demographics, ownership information, and permitting activity—to enrich the analysis with real market intelligence.
Live Demo 4: Investment Committee Preparation - Watch the agent prepare a professional deal summary, draft an investment committee memorandum, and organize supporting materials for internal review.
Live Demo 5: Build vs. Buy - We’ll finish by discussing where purpose-built AI real estate platforms create value, where Claude alone is sufficient, and how to think about assembling your firm’s AI acquisitions stack.
Format & Access
One Live Session - Two hours on Zoom with live demonstrations and time for questions throughout.
Hands-On Demonstration - Participants are encouraged to build alongside us inside Claude as we create and deploy the acquisitions agent live.
A Recording for Everyone - Recordings are sent to every registered attendee, whether or not you can join live.
Slides & Materials - Participants receive the workshop slides, prompt libraries, agent templates, and implementation resources.
Ongoing Access - Your recording and workshop materials remain available in your Thesis Driven account so you can revisit them whenever needed.
Paul Stanton is a Partner at PTB, a boutique investment bank focused on joint ventures, capital raising, and M&A transactions. Paul is a Teacher and Writer at Thesis Driven, developing and growing next-gen real estate & proptech concepts.
Private wealth has passed the institutional market, and most sponsors have no idea how to reach it. A workshop on raising from family offices and RIAs.
