You just got a broker blast with a self-storage facility in a market you’ve been watching. The unit mix looks solid, the occupancy is strong, and the asking price is in your range. Now you need to figure out whether this deal actually fits your buy box.
So you open the OM, start pulling out NRSF and unit counts, cross-reference your criteria on climate-controlled mix, dig into the trade area demographics, and check the competitive supply per capita. Before you know it, 30 minutes have disappeared on a deal that might not even pass the first filter. It’s not that you don’t know what to look for. It’s that screening every deal properly takes time you don’t have when three more OMs land in your inbox tomorrow.
That’s exactly what this task is built to fix.
What This Task Does
You upload the offering memorandum (or broker one-liner) for a self-storage facility and fill in your investment criteria across four dimensions: facility type and size, market and trade area, occupancy and rate performance, and investment strategy and pricing. Each input has example formatting built in, so you know exactly how specific to get.
From there, the Real Estate Analyst (with Memory) takes over. It reads the OM, extracts every relevant data point (NRSF, unit count, climate-controlled mix, occupancy, street rates, cap rate, asking price, expansion potential, and more), runs a deep location analysis on the property address using a 3-mile trade area, and maps what it found against each of your four criteria. If the OM is missing something the AI needs to make a call (trade area demographics, parcel data, competitive supply, or proximity to demand generators), it pulls only the specific data needed to fill the gap.
The whole process takes roughly 10 minutes of your time. The AI does the rest.
Who This Task Is For
If you’re actively acquiring self-storage facilities, you already know the bottleneck isn’t finding deals. It’s deciding which ones deserve your attention. Every OM that hits your inbox needs to be screened, and doing that well means pulling data from the document, cross-referencing your criteria, and sometimes running your own market research just to make a basic go/no-go call.
This task is built for:
- Self-storage acquisition teams who receive a high volume of OMs and need to triage quickly without sacrificing screening quality
- Independent investors building a self-storage portfolio who want a consistent, repeatable screening framework for every deal in their pipeline
- Brokers and advisors who want to pre-qualify a listing against a specific buyer’s criteria before making the introduction
- Asset managers exploring expansion opportunities who need to screen adjacent markets and new facilities efficiently against their existing portfolio standards
In short: if you already have a buy box and a stack of self-storage OMs, this task gives you a structured pass/fail answer in minutes instead of hours.
Why It Matters
The whole point of a buy box is to screen fast: does this deal fit, or does it not? But actually running that screen against a real OM takes more than a gut check. You need to pull specific data points, verify them against your criteria, and fill in the gaps the OM doesn’t cover.
You already know this. You’ve done it dozens of times. The issue isn’t that you don’t know how to screen a self-storage deal.
The issue is that screening a deal properly takes 30 minutes, and you’ve got a pipeline full of opportunities that all need the same treatment. When the volume picks up, either you rush the screen and miss something, or you slow down and miss the deal.
This task compresses that 30-minute process into 10 minutes of your time. You provide the OM and your criteria. The AI does the extraction, the location research, the gap-filling, and the comparison. You get a structured pass/fail report you can act on immediately.
That’s the multiplier.
What the Output Looks Like
The screening report generated by this task includes:
- A 2-3 sentence summary of the opportunity (facility name, location, NRSF, unit count, climate-controlled mix, and investment thesis)
- A four-column criteria comparison table (Criteria Name, Target, Actual, Pass/Fail) with one row per investment criterion
- A written rationale explaining the reasoning behind each pass, fail, or inconclusive determination
- A hyperlinked Deep Location Analysis for the property address
- A final recommendation: Investment Passes, Investment Fails, or Investment Needs Further Review
The output is not a vague summary with a “looks promising” conclusion. It’s a structured, data-backed screening report, the kind you’d expect from an analyst who actually read the OM and did the research.
Frequently Asked Questions About Screening Self-Storage Acquisitions With AI
Yes, and the task is designed with that expectation. The output gives you a structured first-pass screening, not a replacement for full underwriting. Every pass/fail determination is backed by specific data points from the OM, location analysis, or verified external sources. If a criterion comes back as “Inconclusive,” the task tells you exactly what data was missing so you know where to dig deeper. Think of it as your analyst’s recommendation: you review the reasoning, verify anything that matters most to you, and then decide whether to move to full diligence. The goal is to get you to that decision point in 10 minutes instead of 30.
The report is built to be presentation-ready. It includes a structured criteria table with specific data points, a written rationale for each determination, and a linked Deep Location Analysis for the property address. Partners and committee members can see exactly what was evaluated and why. That said, it’s a first-pass screen, not a full investment memo. It gives you the foundation to present a clear go/no-go recommendation backed by data rather than gut feel.
That’s exactly what it’s built for. Each run takes about 10 minutes and produces a consistent, structured output regardless of how the OM is formatted. Whether you’re screening 5 deals a week or 20, the task applies the same criteria framework every time. You define your buy box once, and the AI applies it to every deal you feed it. The consistency alone saves time, because you’re not reinventing the screening process with every new OM.