
Claude Projects for Real Estate: Persistent Workspaces, Prompts Included
Claude Projects for real estate: build persistent workspaces per client, listing, or farm area, with standing instructions, brand voice, and copy-paste prompts.
Learning how to use Gemini for real estate is less about chatting in a separate window and more about putting Google's AI to work inside the tools you already run your business in: Gmail, Google Docs, Sheets, and Slides. This guide shows how to use Gemini across Google Workspace to draft email, write listings, analyze deals, and build client presentations.

Most agents open the Gemini app, ask one question, and never touch it again. The real payoff comes when Gemini for real estate works right inside your inbox, documents, and spreadsheets, handling the writing and busywork where it already lives.
Here's what we'll cover:
One caveat before we start: Gemini can run your back office, but it can't capture the buyers already on your website. A real estate chatbot does that, qualifying visitors around the clock so no lead slips away.
Let's get started.
Gemini's real advantage for agents is that it lives inside the apps where your work already happens. Open the Gemini side panel in any Workspace app and it can read the email, document, or sheet in front of you.
In Gmail, use "Help me write" to draft first-touch replies, follow-ups, and negotiation notes without leaving your inbox. Gemini can also summarize a long thread into the key points and next steps before you respond.

Open a message, ask the side panel to draft a reply in your tone, then edit and send.

Prompt to try in the Gmail side panel:
Plain text
Draft a reply to this buyer's email. Confirm the Saturday 2pm showing at 14 Oak St, ask whether they're pre-approved and their target price range, and keep it warm and under 120 words. Sign off as [Your Name], [Brokerage].To clear your inbox faster:
Plain text
Summarize this email thread into the key points, any dates or deadlines, and the three actions I need to take next.Docs is where most agents write. Ask Gemini to draft an MLS description, a pre-listing letter, or a neighborhood guide, then refine it right on the page.

Because it reads the document you're in, you can highlight a rough paragraph and ask it to tighten the copy or match your brand voice.
Prompt to try in the Docs side panel:
Plain text
Using the details in this doc, write a 150-word MLS listing description for a 3-bed, 2-bath bungalow with a renovated kitchen, large backyard, and top-rated schools nearby. Target first-time buyers, keep it warm and Fair Housing compliant, and end with a call to book a showing.Prompt to try in the Slides side panel:
Plain text
Create a 6-slide listing presentation for 14 Oak St: cover, property highlights, three recent comparable sales, pricing strategy, marketing plan, and next steps. Pull the details from my linked doc and add a hero image on the cover slide.For buyers:
Plain text
Build a 5-slide buyer consultation deck covering the buying process, current market conditions, financing steps, my services, and what to expect next. Keep the tone reassuring for first-time buyers.In Drive, ask Gemini about a file without opening it, like pulling the key dates out of a contract. In the Gemini app itself, lean on it for market research grounded in Google Search, disclosure review, and generating marketing images.

Treat document review as a fast first read, never as legal advice or a replacement for your broker.
Prompt to try on a file in Drive or the Gemini app:
Plain text
Review this disclosure packet and list every key date, deadline, and any unusual clause I should flag for my client. Note anything that needs a professional's review. Do not provide legal advice.For market research in the Gemini app:
Plain text
Summarize the last 30 days of housing activity in [City or ZIP]: median sale price, active inventory, and average days on market, with three takeaways a buyer would care about. Cite your sources and note today's date.For a pre-listing packet:
Plain text
Draft a one-page pre-listing letter to a homeowner at [address] introducing me, my recent sales in the area, and my marketing plan. Confident and friendly, under 250 words.In Sheets, Gemini helps you make sense of the numbers. Point it at a range of comps for the average price per square foot, or have it summarize a column of leads into a quick status overview.

It can also suggest formulas and build simple tables, so you spend less time fighting spreadsheets.
Prompt to try in the Sheets side panel:
Plain text
From this table of comparable sales, calculate the average price per square foot for homes sold in the last 90 days, then list the three comps closest to 1,800 sq ft with their sale price, price per sq ft, and days on market.To triage your pipeline:
Plain text
Summarize this lead sheet: how many leads are in each status, which five are marked hot, and which have had no contact in over 14 days.Slides turns your content into client-ready decks. Ask Gemini to outline a listing presentation or a buyer consultation, then generate supporting images to fill the slides.

It's a fast way to build a CMA or pitch deck that looks polished without starting from a blank slide.
Whether you're typing in the Gemini side panel or the app, vague prompts get vague output. A strong real estate prompt has four parts.
A copy-ready example:
Plain text
You are a real estate listing copywriter. Write a 150-word MLS description for a 3-bed, 2-bath bungalow in Riverside with a renovated kitchen, large backyard, and top-rated schools nearby. Target first-time buyers. Keep it warm and concrete, Fair Housing compliant, and end with a call to book a showing.The more specific and local you are, the less editing you'll do. For a running start, our library of ChatGPT prompts for real estate agents gives you templates that adapt cleanly to Gemini.
Getting started takes a few minutes.
If you use Google Workspace to run your business, the paid tier usually pays for itself in time saved.
In the Gemini app and Workspace, type @ to reference a specific Drive file, like last month's market report or a listing sheet. Gemini answers from that document instead of guessing.
A Gem is a custom version of Gemini with saved instructions, similar to a reusable assistant. Build a "Listing Writer" Gem with your voice and format once, and every future description comes out consistent without re-explaining yourself.
Gemini can pull current information from Google, which makes it useful for market trends and neighborhood research. Always confirm the numbers against your MLS, since AI can still get specifics wrong.
Gemini can create and edit images right where you need them, marketing graphics for a flyer or concept visuals for a deck. Disclose any AI-edited photos and never alter the actual condition of a property.
Gemini is powerful, but it has limits worth knowing.
For the one job Gemini can't do, engaging and qualifying site visitors, you need a tool built for it, which we'll come back to at the end.
All three write well; the right pick depends on your stack. If you want the full breakdown of the alternative, our guide on how to use ChatGPT for real estate covers that tool in depth.
| Tool | Best for | Edge |
|---|---|---|
| Gemini | Agents in Google Workspace | Built into Gmail, Docs, Drive, and Google Search |
| ChatGPT | All-purpose content and prompts | Huge prompt ecosystem and plugins |
| Claude | Long documents and careful writing | Strong reasoning and file handling |
Prefer Anthropic's model instead? Our guide on how to use Claude for real estate does the same for Claude's document handling and workflows.
There's no single best; it depends on the job. Gemini is ideal if you run on Google Workspace, ChatGPT suits all-purpose content, and a dedicated chatbot is best for capturing website leads.
For a wider comparison, see our roundup of the best AI tools for real estate agents, and match the tool to the task instead of forcing one to do everything.
Yes. Gemini lets you create Gems, custom assistants with saved instructions and knowledge, which is the easy way to build a repeatable helper like a listing writer or a market-summary assistant. For fully automated, code-based agents, Google also offers the Gemini API.
The free tier covers most writing and research tasks. A paid Google AI plan adds the newest models, larger uploads, and deeper Google Workspace integration, which is worth it if you use Google tools daily.
Gemini's advantage is living inside Gmail, Docs, and Google Search, so it fits agents already in that ecosystem. ChatGPT has a larger prompt and plugin ecosystem, and many agents keep both and use whichever fits the task.
If you're weighing the two non-Google options against each other, our ChatGPT vs Claude for real estate agents comparison breaks them down side by side.
Gemini is a genuine time-saver for real estate: it drafts your content, summarizes your data, and works right inside the Google tools you already run. Learn the prompt formula, build a Gem or two, and it quietly handles the busywork.
The one thing it can't do is capture the buyers already on your site. Book a demo to see how Realty AI qualifies website visitors around the clock, so the leads Gemini helps you nurture actually make it to your inbox.
Related articles
Keep reading in the same category to go deeper on the topics that matter to your team.

Claude Projects for real estate: build persistent workspaces per client, listing, or farm area, with standing instructions, brand voice, and copy-paste prompts.

Claude Code for real estate: what it is, how it differs from Claude chat and Cowork, what agents can build, how to get started, and copy-ready build prompts.

Claude Skills for real estate agents: what they are, how they compare to projects and subagents, how to create one, and 10 copy-ready Skills to use today.
About Madison
Madison is Realty AI's conversational assistant for real estate websites. It engages visitors instantly, qualifies buyers, sellers, and renters through natural dialogue, routes summaries to your CRM, and keeps your team focused on closing.
5.0 average from 2,500 customer reviews

Sarah Logue
Broker & Owner, Top 0.1%

Mark Jensen
Owner & Broker of Record

Michelle Makos
Broker & Owner
See it in action
See how Madison qualifies, books, and routes leads in 2 seconds, across every page on your site.