AI has gotten really smart.
The latest models from OpenAI, Anthropic, Google, xAI, and others can reason through complex problems, analyze enormous amounts of information, write code, create documents, manipulate spreadsheets, search the web, and increasingly operate software on our behalf.
And the models keep getting better.
Yet ask one of those same models to perform real work inside a commercial real estate firm and you quickly run into a problem.
The AI is smart. It just doesn't know commercial real estate.
It doesn't know your underwriting methodology. It doesn't know how an experienced acquisitions professional approaches a T12. It doesn't know which fields matter when abstracting a lease. It doesn't necessarily know the difference between how you analyze a multifamily rent roll and an industrial NNN rent roll.
And even when it understands the terminology, it usually doesn't have access to the specialized data required to actually do the work.
That gap between general intelligence and domain expertise is increasingly becoming a context problem.
And one emerging solution to that problem is Context as a Service, or CaaS.
The Problem Isn't That AI Isn't Smart Enough
For the past several years, much of the conversation around AI adoption has focused on the models themselves.
Which model is smartest?
Should I use Claude or ChatGPT?
Which model has the largest context window?
Who scored highest on the latest benchmark?
Those questions matter. But increasingly, I think they're becoming less important.
The frontier AI labs are engaged in a massive arms race. Models are improving quickly, and the differences between them will continue to change. The model that is "best" at a given task today may not be the best six months from now.
Meanwhile, a different problem remains.
A general-purpose AI model has been trained on an enormous amount of information about the world. But it hasn't spent 20 years working in acquisitions. It hasn't built hundreds of institutional real estate models. It doesn't have your firm's investment committee process memorized. And it doesn't automatically have access to the property, market, demographic, ownership, zoning, rent, or transaction data that CRE professionals use every day.
In other words, intelligence isn't the same thing as expertise.
This is becoming an important distinction across enterprise AI.
Anthropic describes "context engineering" as the natural progression beyond prompt engineering. Rather than focusing simply on how a prompt is worded, context engineering asks a broader question: what information, instructions, tools, data, and history should the model have available when completing a task?
That is a much more useful way to think about AI in commercial real estate.
What Is Context in AI?
When we talk about context, we're talking about the information an AI has available when it reasons through a problem.
That context can include things such as:
- Instructions describing how a task should be performed
- Methodologies developed by experienced practitioners
- Reference documents
- Company-specific standards and preferences
- Market and property data
- Previous conversations or decisions
- Software tools the AI can use
- Examples of what a good finished deliverable looks like
Think about how we train a new analyst.
We don't just hire a smart person, hand them Excel, and say, "Good luck."
We teach them how we underwrite.
We give them templates.
We explain what goes into an IC memo.
We show them previous deals.
We give them access to CoStar, RealPage, public records, internal databases, or whatever other information they need.
We teach them which assumptions matter, which numbers need to reconcile, and where mistakes tend to hide.
Over time, that analyst combines their underlying intelligence with institutional knowledge, data, processes, and experience.
AI needs the digital equivalent.
From Prompt Engineering to Context Engineering
The first generation of generative AI adoption placed a lot of responsibility on the user.
If you wanted a strong result, you had to become good at prompt engineering.
Instead of:
"Underwrite this deal."
You learned to write something more like:
"You are a senior acquisitions professional with 15 years of experience underwriting institutional multifamily..."
Then you'd explain the methodology, specify the inputs, define the output format, attach supporting documents, tell the model what assumptions to use, and perhaps provide examples.
With enough effort, you could get a pretty impressive result.
But there's an obvious problem with that approach.
Most commercial real estate professionals don't want to become AI engineers.
And they shouldn't have to.
The acquisitions professional should be focused on finding and evaluating investments. The broker should be focused on winning assignments and closing deals. The asset manager should be focused on maximizing asset value.
Those professionals possess incredibly valuable domain expertise. Asking each of them to independently translate that expertise into elaborate prompts every time they use AI doesn't scale.
Context as a Service flips that model.
Instead of requiring the individual professional to package the right expertise and information into every prompt, a context layer makes that expertise available to the AI when it needs it.
What Is Context as a Service?
Context as a Service is an emerging category, so you'll find slightly different definitions depending on who you ask.
But the basic idea is straightforward:
Context as a Service provides an AI with the specialized knowledge, methodologies, data, tools, and other information it needs to perform domain-specific work.
Gartner has begun using the term "Context as a Service" in discussing how MCP servers can gather, aggregate, interpret, and make enterprise context actionable for AI agents.
Similarly, an emerging group of technology companies are describing a "context layer" that sits between general-purpose AI models and an organization's underlying knowledge and data. The goal is to give AI not simply more information, but the right information and business meaning at the time it needs it.
I think of it like this:
The AI model provides the intelligence. The context layer provides the expertise.
And that distinction has important implications for how we adopt AI in commercial real estate.
CRE Agents Is Context as a Service for Commercial Real Estate
This is increasingly how I think about what we're building at CRE Agents.
We're not trying to build a better foundational AI model than OpenAI, Anthropic, Google, or xAI.
That would be a fool's errand.
Billions of dollars are being invested in making those models smarter. We want CRE professionals to benefit from that innovation, regardless of which model happens to be best at any given moment.
Instead, CRE Agents provides the piece those general-purpose models are missing:
commercial real estate context.
Connect CRE Agents to the AI you already use and Vic equips that AI with CRE-specific tasks, methodologies, skills, and live real estate data.
The AI remains Claude, ChatGPT, Grok, or virtually any other AI.
Vic gives that AI the CRE knowledge it doesn't have on its own.
Today, that context includes hundreds of ready-to-run CRE tasks and methodologies, together with a growing stack of live datasets covering areas such as rents and concessions, parcels and ownership, zoning, demographics, employment, migration, retail spending, traffic counts, interest-rate benchmarks, and other information commonly needed in real estate work.
Rather than replacing the AI you already use, CRE Agents makes it better at commercial real estate.
Methodology Is Context
Consider a simple example.
You upload a T12 and ask a general-purpose AI:
"Analyze this T12."
The model may understand what a trailing twelve-month operating statement is. It can probably read the numbers. And it may produce a reasonable summary.
But what should it normalize?
How should it classify expenses?
Which items warrant follow-up?
How should utilities, payroll, concessions, repairs and maintenance, taxes, management fees, or replacement reserves be treated?
What does an acquisitions professional actually need from the analysis?
Those aren't primarily intelligence problems.
They're methodology problems.
A good CRE professional has a mental framework for approaching the task. CRE Agents turns those frameworks into context an AI can use.
And property type matters.
A multifamily T12 isn't analyzed exactly like an industrial operating statement. A hotel isn't underwritten like a self-storage facility. A retail rent roll requires a different approach than an apartment rent roll.
CRE Agents knows exactly how to handle the 12 most common commercial real estate property types, with more being added regularly. The methodology and workflow can therefore adapt to the property type rather than forcing every CRE assignment through the same generic process.
The same is true when reconciling an estoppel against a lease, abstracting loan documents, reviewing a rent roll, building a development pro forma, drafting an investment committee memo, evaluating a broker opinion of value, or preparing a quarterly investor report.
The model can reason.
The methodology teaches it how a CRE professional approaches the work.
Data Is Context
Then there's data.
Suppose you ask your AI:
"What apartment rents are achievable for this site?"
That's an impossible question to answer well from general training data alone.
The AI needs to know where the property is. It needs current rent information. It may need demographics, nearby properties, unit-level comps, concessions, population growth, employment trends, supply, and other market information.
Without access to the right data, even a very capable model is limited to the information already in its context, information it can retrieve elsewhere, or assumptions it makes from what you provide.
CRE Agents connects that AI to real estate-specific data sources it otherwise may not have access to.
That means the same general-purpose AI goes from simply knowing about commercial real estate to being better equipped to actually work in commercial real estate.
The AI Model Becomes Interchangeable
This is perhaps the piece I find most interesting.
If context is where much of the domain-specific value lives, the underlying model becomes increasingly interchangeable.
Maybe your team prefers Claude.
Maybe you live in ChatGPT.
Maybe Grok becomes your model of choice.
Maybe six months from now a model that barely exists today becomes the best model for your particular workflow.
That's fine.
Your commercial real estate expertise shouldn't be trapped inside one AI platform.
CRE Agents is designed around the opposite idea.
Keep using the AI you already like. Connect the CRE context layer to it. When models improve, you benefit from those improvements without rebuilding all of your real estate knowledge from scratch.
This is part of why open standards such as Model Context Protocol, or MCP, are so important. They create a common way for AI applications to connect with external tools and context, allowing specialized capabilities to travel with the user rather than remaining trapped inside a single AI product.
CRE Agents uses this model to deliver CRE-specific tasks, skills, methodologies, and data into the AI tools CRE professionals already use.
From "Teach Your AI Real Estate" to "Use Vic"
The practical result is that using AI becomes much simpler.
Without a context layer, the burden is on you:
Explain the role.
Explain the methodology.
Find the data.
Write the prompt.
Define the output.
Check whether the AI followed the methodology.
Start over the next time someone on the team needs to perform the same task.
With CRE Agents, the goal is much simpler:
"Use Vic to..."
Use Vic to abstract this lease.
Use Vic to map this T12 to our chart of accounts.
Use Vic to screen this opportunity against our buy box.
Use Vic to draft an IC memo.
Use Vic to research the property and ownership.
Use Vic to build a development pro forma.
Behind those two words sits CRE-specific context that helps the AI approach the task using the methodologies and data a CRE professional would expect.
The CRE professional remains responsible for reviewing the work, applying judgment, and making the decision.
Vic provides the context.
The AI provides the intelligence.
You provide the judgment.
Intelligence Is Becoming a Commodity. Context Is the Differentiator.
The underlying AI models are going to keep getting better.
That is great news.
But smarter models alone don't solve the enterprise AI problem.
A newly hired Harvard MBA may be incredibly smart. That doesn't mean on Day 1 they know your firm's underwriting methodology, where your data lives, how your investment committee thinks, or exactly how you want an analysis presented.
You still have to give them context.
AI is no different.
The winners in this next phase of AI adoption won't simply be the firms with access to the smartest model. Eventually, nearly everyone will have access to extraordinary intelligence.
The differentiator will be who can give that intelligence the best context.
For commercial real estate, that's what we're building at CRE Agents.
Claude, ChatGPT, Grok, and virtually any AI bring the intelligence. CRE Agents brings the commercial real estate context. You bring the judgment.
That's Context as a Service for CRE.
Learn more at creagents.com.

