Every week, real estate agents spend hours on the same repetitive tasks: writing blog posts from scratch, reviewing contracts under pressure, drafting social media captions, and trying to remember how they framed that listing description last month. These tasks are not high-value work. They are the administrative drag that eats into time agents should spend building relationships and closing transactions.
Tony Ray Baker has been a REMAX Realtor in Tucson, Arizona for 32 years. He found a way around this problem. Inside Google Gemini, he built a full AI team using a feature called Gemini Gems: a blog writer, a legal reviewer, a social media manager, and a listing marketer. Each one is trained in his voice, knows his specific market and compliance requirements, and is ready the moment he opens his laptop. The entire setup costs him $20 a month.
On episode 10 of AI Agent Advantage, Tony Ray walks through exactly how he built each gem, what he put inside the legal reviewer, and the one technique that made all of his gems dramatically more accurate than his first attempts. Here is the breakdown.
What a Google Gemini Gem Actually Is
A Gemini Gem is a specialized AI assistant you build and train once inside Google’s Gemini platform. Unlike a standard AI chat session where you re-enter your preferences and context every time you open a new conversation, a gem retains your instructions permanently. You set your writing style, your target audience, your formatting rules, and any language it should always apply or always avoid. From that point forward, every session with that gem starts exactly where you left it.
The practical result for a real estate agent is significant. Opening your blog writer gem means going straight to content without re-explaining your brand. Opening your legal reviewer gem means getting a contract answer in seconds without re-uploading your references. You train the gem once, and it works that way indefinitely.
Google Gemini is not the only platform that offers this kind of persistent assistant. ChatGPT calls them GPTs. Claude calls them Projects. The underlying principle is the same across all three: one setup, then specialized output on demand every time you return.
The Meta-Prompting Method That Makes Gems Work From Day One
Most agents who try to build a gem run into the same problem: they are unsure what to put in the training prompt, so they guess, and the output disappoints them. Tony Ray’s solution is to stop guessing entirely.
His approach, which he calls meta-prompting, works like this. Instead of writing the training prompt yourself, you describe your goal to Gemini in plain language and ask it to generate the optimal training prompt for you. Tell it what the gem will focus on, who your clients are, what standards you expect it to follow, and what you want it to always or never do. Then ask: now write the prompt that will make this gem perform at its best.
Gemini builds the technical instruction set. You copy that into your gem configuration, and you are done. The result is a gem that is calibrated to your actual business from the very first session, without requiring any background in prompt engineering.
The Real AI Team Tony Ray Baker Built Inside Google Gemini
Tony Ray has five active gems that cover the recurring work across his real estate business.
His blog writer gem is configured to produce posts at a minimum of 500 words, structured with NLP principles, optimized for both traditional search and AI-powered search engines, and written in his voice. It cites any research sources it references, excludes the specific filler language he has banned, and delivers a finished draft each time without requiring any setup from him.
His legal reviewer gem is the one that gets the most attention when he describes it. He uploaded Arizona’s real estate contract forms, fair housing law documentation, and the NAR code of ethics directly into the gem, and instructed it to only draw on those sources. When a contract question comes up mid-transaction, he pastes the clause in question and receives a response that cites the exact lines and documents that apply. During one negotiation, an agent on the other side of a transaction was not performing to the contract timeline. Tony Ray asked his legal gem to help him draft a professional note to the other agent, one that was firm about the timeline without escalating the conflict. The communication worked. The documents came through the same day.
“I love my lawyer. Have you ever heard that before? You have an advisor that is never going to talk to anybody else. So you can really be honest.”
Tony Ray Baker
He also built a social media gem, a website analyzer, and a listing marketer. Separately, on ChatGPT, he created a publicly available free tool called Tony Ray’s Little Marketing Helper. You load an address, add property photos, a floor plan, and a handwritten upgrades list, and it generates MLS descriptions, social captions, fliers, geo-tag information, and lifestyle paragraphs in seconds. The tool is available for any agent to use at no cost.
Why Each Gem Should Have One Job and One Job Only
The instinct when building AI tools is to create one assistant that covers everything. Tony Ray tried this approach and found it consistently produced lower-quality output across every task. When you give a gem multiple jobs, it loses focus, and so do you. The instructions start working against each other, and the results become muddled.
A gem trained to write blogs and review legal documents and create social posts ends up doing none of those things particularly well. Keeping each gem focused on a single recurring task produces better output and makes each gem easier to improve over time. When the blog writer gem produces something you want to adjust, you know exactly where to go and exactly what to change. There is no guessing about which instruction is causing the issue.
Tony Ray recommends starting by writing down the ten tasks in your business that cost you the most time each week. Prioritize that list. Take the top item and build your first gem around solving it. Once that gem is running well, build the next one.
“It’s the first time in history where the tool teaches you how to use it. AI teaches you how to use AI.”
Tony Ray Baker
Key Takeaways
- A Gemini Gem is a specialized AI assistant trained once with your preferences, voice, and rules. It retains everything permanently, so you skip the setup on every future session.
- Use meta-prompting to build better gems: describe your goal to Gemini in plain language and ask it to generate the optimal training prompt for you.
- Build single-purpose gems for each recurring task. One gem, one job. Focus produces consistently better output than trying to make one tool do everything.
- You can load documents directly into a gem’s knowledge base. Tony Ray’s legal reviewer contains Arizona real estate contract forms, fair housing documentation, and the NAR code of ethics.
- Keep only one AI tab open per session. Opening multiple tabs from the same account causes inconsistent results and hallucination errors.
- Tony Ray’s free listing marketing GPT, Tony Ray’s Little Marketing Helper, is available on ChatGPT at no cost. Load a property address plus photos and it generates MLS descriptions, social posts, and more.
About Tony Ray Baker
Tony Ray Baker is a REMAX Realtor based in Tucson, Arizona with 32 years of experience in residential real estate. A social entrepreneur and committed AI practitioner, he owns five companies and studied prompt engineering under educator Devin McFaul. He created Tony Ray’s Little Marketing Helper, a free GPT tool for real estate listing content, and runs a nonprofit art gallery in Tucson supporting children and local artists. You can find him on Facebook at Tony Ray Baker or reach him at (520) 631-8669.
Hear the Full Episode
Tony Ray covers all of this and more on AI Agent Advantage, Episode 10. He walks through his exact training process, the legal gem workflow, his free listing tool, and the meta-prompting technique with enough detail that you can replicate it in a single afternoon.
Follow the show and catch every new episode: https://www.buzzsprout.com/2606314/follow
Listen on Spotify: open.spotify.com/show/033dewJbF5qdw4Cjn0m6tq
Listen on Apple Podcasts: podcasts.apple.com/podcast/id1896492768
Watch on YouTube: youtube.com/playlist
New episode every Friday. One expert, one tool, one thing you can implement before your next client call.
Want This Working in Your Business?
Reading about AI and actually using it are two different sports. If you want this running in your real estate business, that is exactly what I do.
Done for you: I build custom AI chatbots for agents at Big Brain Chatbots. https://bigbrainchatbots.com/realestate
Learn it yourself: come into AI-Cademy, where we work through this live every week. https://jmanai.com/ai-cademy/
Ready to go all in? The 6-week AI-Cademy Bootcamp: https://jmanai.com/bootcamp/
Not ready yet? Start with my free guide: https://guide.bigbrainchatbots.com
