How acquisitions teams are using AI to catch what brokers bury — before they're under contract.
An interactive workshop for acquisitions professionals, analysts, and asset managers at small to mid-size shops — the people underwriting deals without a full team behind them, who've learned the hard way that broker OMs don't always tell the whole story.
Thursday, September 10, 2026 — 12:00–1:00pm ET
The session will be recorded and shared with all participants via Circle.
This session is part of the Claude 100 — Foundations track. No prior AI experience required.
A hands-on workshop for acquisitions professionals who are tired of getting deep into a deal before realizing the OM numbers don't match the rent roll. You'll build a two-part Claude workflow that abstracts every broker assumption from any OM, populates your underwriting model automatically, then audits the actual lease data against it — flagging every discrepancy before you spend real time or real money.
This session is part of the Claude 100 — Foundations track, designed for new users with no prior AI experience required.
Acquisitions professionals and analysts at small to mid-size shops who are catching broker discrepancies too late — and who need a repeatable system to audit every deal at the front of the funnel, not after they're under contract.
Meet Marcus, a principal at a three-person value-add multifamily shop in Dallas, TX. He's been burned twice by deals where the broker's OM didn't match the actual leases — occupancy overstated, concessions buried in the fine print. This workflow finds it before he's under contract.
In this session, you'll build a two-part Deal Underwriter Claude Project: first, drop in any OM and Claude abstracts every broker assumption — rents, occupancy, expenses, cap rate, debt terms — and populates the inputs tab of a pre-built underwriting model. Second, upload the actual rent roll and Claude audits it against the OM data, flags every discrepancy, and tells you exactly what to change before you go under contract.
Everything runs through a Deal Underwriter Claude Project configured to your model structure and packaged as a .skill file — so the full setup installs in one click.
You'll leave with:
Oscar Hajduk, GM of CapitalStack at Thesis Driven. He builds AI tooling for real estate investors, including deal-signal pipelines, LP screening, and underwriting workflows, and runs these systems in production, not just on slides.
Will participants receive a copy of the materials? Yes. All registered participants will receive an invitation to join our private Circle community. Recordings, slides, agent templates, skills files, and setup guides will be uploaded within one week of the workshop ending.
I can't make this time—will a recording be available? Yes. All registered participants receive access to the recording and materials via Circle, even if they cannot attend live.
Do I need a Claude account to participate? A Claude Pro or Team account is recommended to follow along in real time, but not required. All system instructions, skills files, and setup documentation will be shared via Circle so you can build the agent at your own pace after the workshop.
