
Claude Code for Commercial Real Estate Teams
Claude Code is an agentic coding tool: you describe what you need in plain English and it writes, tests, and runs real software in your own environment. For a CRE firm, that means custom underwriting tools, data pipelines, and internal systems built to your workflow, not a vendor's roadmap, and owned by you when it ships.
Claude Code for Commercial Real Estate Teams
The short answer
Claude Code is an agentic coding tool from Anthropic. You give it a task in natural language, and it reads your files, writes code, runs it, checks the output, and iterates, inside your own environment, on your own machine or cloud account. It is not a chatbot that talks about code. It is a tool that builds and runs it.
For a commercial real estate firm, that is the difference between waiting on a proptech vendor to maybe add the field you need next quarter, and having someone on your team describe the field to Claude Code this afternoon and watch it get added. It is a general-purpose builder, not a CRE product. That is exactly what makes it useful for firms whose workflows do not match any off-the-shelf tool cleanly, which in our experience is most of them. See our pillar guide to Claude for commercial real estate for how this fits the broader Claude product line.
What CRE teams actually build with it
In practice, the projects that make sense for Claude Code cluster into a few categories:
- Custom underwriting tools. A model that encodes your firm's specific assumptions, sensitivities, and output format, instead of a generic template everyone reshapes by hand each deal.
- Data pipelines from your export files. Scripts that take a Crexi, CoStar, or Reonomy export and turn it into a clean, deduped, firm-formatted spreadsheet or database table, without a junior analyst doing it by hand every week.
- MCP servers that connect Claude to your systems. A small server that lets Claude (or any AI assistant) query your CRM, your data room, or your deal tracker directly, so an analyst can ask a question in plain English instead of hunting through folders. See MCP for real estate firms and whether your firm should build a custom MCP server for the buy-versus-build case on that layer.
- Report generators. Turning a folder of deal documents into a consistent investment memo, rent-roll summary, or LP update, in your firm's format, every time.
None of these are exotic. They are the internal tools most firms have wanted for years and never had the engineering budget to justify. Claude Code lowers the cost of building them enough that a single motivated person can ship one in days, not a multi-month vendor engagement.
Who this is actually for
We will be direct about this: Claude Code is a builder's tool. It rewards someone who understands the problem well enough to describe it precisely, and who is comfortable reviewing what gets produced before it touches real data. That tends to be one of three people:
- A technically-inclined principal or partner who already tinkers with spreadsheets, Zapier, or SQL and wants more control.
- An in-house analyst-engineer, a role we are seeing more CRE firms create specifically because tools like this make one hire more leveraged than a small dev team used to be.
- An implementation partner who builds the system with you, hands over the code, and trains your team to maintain it.
If none of those describe your firm today, that is a legitimate reason to bring in outside help for the build phase. It is not a reason to skip the capability. The tool itself is not the hard part. Knowing what to ask for, and reviewing what comes back, is.
Own it versus outsource it
The most important property of this approach is who ends up holding the keys. When a partner builds you a system with Claude Code and MCP, the output is your code, in your repository, running on your infrastructure. There is no monthly per-seat fee to a vendor for software that does one specific thing for your firm. If you want to change it, extend it, or hand it to a different partner later, you can, because you own it.
That is a different relationship than most proptech contracts, where you are renting access to someone else's roadmap. It is also why we publish our own skills library in the open rather than locking it behind a subscription: claude-skills-cre on GitHub is a set of Claude skills built for CRE workflows that any firm can use, fork, or extend, whether or not we build it for you. We think the market for CRE software is moving toward firms owning more of their own stack, and we would rather be early and useful there than defend a walled garden. For examples of what this has looked like in practice for other firms, see our case studies.
Where this fits alongside skills and MCP
Claude Code is the construction tool. Skills and MCP are what you build with it. A skill is a packaged instruction set that teaches Claude how your firm wants a specific task done, like formatting a memo or scoring a deal. An MCP server is the connection layer that lets Claude reach into your actual data, your CRM, your data room, your deal tracker, safely and repeatably. Claude Code is how you write and maintain both of those, and how you build the one-off tools that do not fit either pattern, like a custom underwriting calculator or a one-time data migration script.
Picking the right model matters too, since not every task needs the same horsepower or cost profile. Our guide on which Claude model to use for commercial real estate covers that trade-off in more detail. And if you are earlier in deciding whether to build this yourselves or bring in a partner, our build solutions page walks through how we approach that engagement, with you owning the result either way.
Related Articles
AI for Commercial Real Estate by Asset Class
The AI playbook for commercial real estate is not one playbook. It changes by asset class because the data sources, the buy signals, and the underwriting math are different for multifamily than they are for self-storage or hotels. This is the map: what is specific to each asset class, and what stays constant no matter what you invest in.
AI for Hotel and Hospitality Real Estate Investing
Hotels are the one commercial real estate asset class where you are underwriting an operating business, not just a building. AI earns its keep here parsing STR reports and monthly operating statements, benchmarking RevPAR and ADR against a comp set automatically, and flagging brand and franchise terms buried in management agreements, work that used to take an analyst days per property.
AI for Industrial Commercial Real Estate (Warehouse, Logistics, IOS)
AI helps industrial CRE investors find off-market warehouse, distribution, and industrial outdoor storage (IOS) deals faster, and underwrite them with clear-height, dock-door, tenant-credit, and rollover data pulled automatically instead of assembled by hand.
