Searcher
Treats AI like a search engine. Asks a question, takes the answer, gives up when it's generic.
Free class · Foundations
AI 101 for real estate agents.
Most agents use AI like Google: ask a question, take the answer, move on. This class shows you how to use it like a new hire instead. Define the win, brief it properly, give it a reusable memory of your business, and check every claim before it reaches a client.
Ryan Wanner, founder of AI AccelerationWilliamson County Association of REALTORSEvery class on this page is free to read and watch. No account needed.
What you'll learn.
- 01The difference between using AI like a search box and using it like a new hire you brief, delegate to, and review.
- 02Six mental models that decide your results before you type a word.
- 03The five questions to answer before you ask AI for anything.
- 04How to brief AI so the first draft is usable, then iterate instead of starting over.
- 05How to build a Context Card and a Style Match so AI sounds like you, not a template.
- 06Why AI predicts instead of knows, and which claims always need a human fact-check.
Part 1
Think about AI the right way first.
Delegator
Treats AI like a new employee. Gives context, delegates the task, reviews the work, iterates.
The gap between people who struggle with AI and people who get real work out of it isn't technical skill. It's approach. And the approach comes from a handful of thinking tools that work in any AI product, which is what keeps you free to switch when a better one ships.
- 01
First principles
Define the outcome, not the process. "Help me with social media" becomes "I need 3 posts this week that each start a real conversation. Here's what worked last month."
- 02
OODA loop
Observe, orient, decide, act, then run it again. AI generates, you validate, repeat. The first output is a draft, never the final answer.
- 03
Skill gap
AI accelerates competence. It doesn't create it. An agent who can't price plus AI gets wrong answers faster. Outsource the grunt work, never the thinking.
- 04
Circle of competence
Know where you create the most value. Start with a workflow you already know from A to Z, then put AI into it.
- 05
80/20
AI gets you most of the way from a blank page. Your local knowledge, relationships, and judgment are the part it can never supply.
- 06
Context over cleverness
There are no magic tricks, just good briefings. Specific details and real examples beat clever wording every time.
Five questions before you ask AI anything.
Examples almost always beat descriptions. If you have an email clients love, paste it in and say so. Give AI everything it needs to win.
Part 2
Brief it like a consultant you're paying.
Picture a consultant billing by the hour who has never met you, never seen your market, and never heard of your client. You wouldn't say “help me with this listing.” You'd brief them. AI is that consultant, and it has amnesia. Every new chat starts from zero.
Property details, the client's situation, the market, and your past examples. Everything relevant, nothing just in case.
A listing copywriter, a buyer's agent prepping a consult, a negotiation coach. Say whose shoes it's in.
A first-time buyer's email and an agent-facing MLS remark need different words and a different format.
Length, tone, structure, and exclusions. “5 bullets, each under 15 words” beats “be concise.”
An action verb and a deliverable. “Draft a follow-up to a buyer who saw 3 homes and went quiet,” not “what should I say?”
Don't start over. “Shorter.” “Rewrite the opening.” “Focus on the kitchen.” Build on what you have.
Two shortcuts do most of the work. Ask AI to ask you three clarifying questions before it writes, the way a good employee would. And when you finally get the output you wanted, ask it how you got there from the first try. Save that as your starting point next time.
Give it a memory: the Context Card.
Briefing from scratch every time is slow. A Context Card is a reusable briefing document you load once, so your name, your voice, your market, and your rules are already there when you type the task. Most people only ever type the task. Set up the card once and the task becomes the easy part.
Who you are, your role, your specialty, your experience.
How you sound. Sentence length, phrases you use, phrases you never use.
Your neighborhoods, price ranges, clients, and the local detail nobody else has.
Fair Housing, your Do Not Say list, length limits, and format rules.
Don't describe your voice. Show it. “Professional but friendly” tells AI nothing. Three things you actually wrote tell it everything. Run a Style Match and paste the result into the voice section of your card.
Style Match
Analyze the writing style of these examples. Describe: 1. Typical sentence length and structure 2. Tone and personality that comes through 3. Vocabulary patterns (words used frequently) 4. What makes this distinctive Be specific. I'll use this to have you write like me. --- [Paste example 1: an email or post you actually wrote] --- [Paste example 2] --- [Paste example 3]
Keep the card lean. Context is a limited resource, and a long chat drifts as it fills up. When outputs go generic or forget your rules, ask AI to summarize the constraints and decisions so far, then start a fresh chat with that summary and your card.
Part 3
Check it before it costs you.
AI generates what statistically sounds right. That makes it great at turning facts you gave it into polished copy, and dangerous when it fills a gap on its own. Train your eye for the difference.
Usually safe to let AI write.
- Descriptive language about a feature you told it about, like an open floor plan you confirmed
- A call to action built on the property style you supplied
- Structure, first drafts, options, and rewrites
Always needs a human fact-check.
- Any specific statistic, like a year-over-year price change
- Anything about a seller's motivation, which AI can't know and shouldn't be told
- Zoning, tax programs, and other legal specifics
- Anything that touches Fair Housing, even when you told it to comply
Your part of the work is the part AI can never do. You know the sellers are going through a hard time. You can tell a buyer is nervous, not cheap. You know that comp doesn't count because it was a distressed sale. That knowledge is the value. AI can speed up everything you do, but you're the human in the loop, and you're the one accountable for what goes out.
Write down 3 areas you know cold. That's your circle of competence, and your first place to use AI.
Take one real task and iterate 3 times before you accept the output. Run Style Match on 3 things you wrote.
Build your first Context Card, then 3 reusable briefs for tasks you do every week.
Free with a student account
Get the workbook and prompts, free.
Create a free student portal account to get the workbook, prompts, templates, and downloads for every class.
Create my free account →Already a student? The same link signs you in.
- The AI 101 workbook
- Your AI starting point worksheet
- The OODA check for any AI output
- Prediction vs. truth: the fact-check quiz
- Build-a-brief exercise and a mini Context Card
- AI 101 skill card
Questions agents ask.
What is the best AI for real estate agents?
Pick one of the major assistants, such as ChatGPT, Claude, or Gemini, and learn it well. The mental models in this class matter more than the brand, because they let you switch the day a better model ships. Keep your context in a document you own so you can move it with you.
Why does AI make things up?
A language model predicts what text sounds right. It doesn't look up what is right. So it can invent a specific statistic, a zoning code, or a seller's motivation and say it with total confidence. Anything factual it didn't get from you or from a source you can open needs checking before it goes anywhere.
Do I need to learn prompt engineering?
No. You need to brief AI the way you'd brief a new assistant on their first day: the outcome, the facts, who it's for, and the limits. Better yet, hand it your Context Card and ask it to ask you a few questions before it writes. The skill is knowing what you want and checking what comes back.
What is a Context Card?
A reusable briefing document you give AI at the start of any session. It has four parts: identity, voice, knowledge, and guardrails. Save it in ChatGPT's custom instructions or a Project, a Claude Project, or a Gemini Gem, so you stop re-explaining yourself every time.
What should I never let AI do on its own?
Price a home, read a client, negotiate, or make the final call on Fair Housing and compliance. AI can draft, research, and give you options. If something goes wrong, you're the one responsible, not the chatbot. Read every output as the final decision maker, even when you told it to follow the rules.
Keep going.
Foundations
How to Use Claude in Real Estate
Hand a desktop AI agent one bounded job: set up a Claude Cowork project, check its permissions, have it interview you, then inspect, correct, and rerun.
Foundations
How to Use AI to Solve Real Estate Business Problems
Run any stuck business problem through OODA with AI: define it, find what's missing, audit the answer, pick an option, and act on the smallest step.
Get found
How to Get Recommended by AI for Real Estate
Check what answer engines say about you, verify every source they cite, and publish one sourced answer worth citing.
Library
Every free class
The whole library of recorded classes, by topic.
Research sources
Check the current rules, capabilities, and source basis.
- 01OpenAI: Prompt engineering best practices for ChatGPT ↗
First-party guidance on clear instructions, relevant context, explicit output structure, and iterative refinement.
- 02Anthropic: Effective context engineering for AI agents ↗
Why context is a finite resource, and how to choose high-signal context instead of pasting everything.
- 03OpenAI: Why language models hallucinate ↗
Why plausible output is not evidence, and why uncertainty and verification matter.
- 04NIST: AI Risk Management Framework ↗
The government framework for governing, mapping, measuring, and managing AI risk, including human oversight.
- 05NAR: Artificial Intelligence in Real Estate ↗
NAR's current overview of AI use in real estate and policy priorities around privacy, Fair Housing, and copyrighted listing content.
Product access, limits, local listing rules, platform policies, and laws can change. Re-check the linked authority before important or public work.
Keep building
Put AI to work in your real estate business.
AI Acceleration: Real Estate is a private, self-directed curriculum for practical AI work across content, communication, lead follow-up, CRM, client research, operations, and relationship management. Build it. Review it. Keep what works.
Explore the Skool community ↗Follow Ryan + AI Acceleration
No ranking, revenue, closing, or time-saving promise. The classes teach the work and the review systems around it.
Record: innovation-lab-public-classes. Approved record hash: add45e5ab0ee95b80ad70a4ecb50c8b8317c6997119c13fd8a727225815aff73. Claims: public-classes-free-to-watch, public-classes-portal-unlock, public-classes-taught-live.