58AI Bootcamp
58AI Bootcamp · Real estate agent track · Taught by Arthur Zhao

AI training for Toronto real estate agents
Taught by a working broker, in Mandarin

No theory tour and no tool sales. We start from the work you already do — prospecting, follow-up, showings, deal deadlines, client care — and build your own AI assistant one piece at a time. In person, small groups, with a helper in the room. Classes are taught in Mandarin.

  • In person, Greater Toronto
  • Taught in Mandarin
  • Small groups
  • Hands-on help in class
  • No coding
WHY AN AGENT

Why learn AI from someone still doing deals?

1

12 years full-time, 9 years training agents

You get the details that only come from closing deals and coaching new agents: where files go wrong, what clients actually care about, and what you should never hand to a machine.

2

Everything taught is in daily use

Follow-up, listing copy, market data, showing schedules — each workflow ran in my own business before it reached a classroom. The projects are public in the project library.

Open the project library →
3

Boundaries first, speed second

AI sorts, reminds and drafts. Judgment, terms and signatures stay with the agent. Every class comes back to that line.

AI × AGENT

Which half of the day can AI take?

Not "fully automated". Each part of the job splits in two: what a machine does well, and what needs you in person.

Marketing and content

AI handles
Turns your market views into first drafts of posts, articles and video scripts for each platform
You handle
Your opinion, the facts, and the final check before anything goes out

Lead follow-up

AI handles
Sorts new leads, reminds you on schedule, drafts the first reply
You handle
The real conversation, and the call on when to pick up the phone

Showings and open houses

AI handles
Prepares listing packets and routes, files sign-in details into your client list
You handle
Greeting people, answering professional questions, reading what clients leave unsaid

Deal deadlines

AI handles
Lists documents and dates, flags what is coming due
You handle
Terms, negotiation, advice to your client, signing

Client experience

AI handles
Shows clients where things stand in plain views, compiles regular market updates
You handle
The extra call and the extra visit — where the saved time should go

Your knowledge base

AI handles
Organizes scripts, FAQs and deal reviews into a searchable second brain
You handle
Deciding what is worth keeping, and adding to it over time
COURSE LADDER

From a free start to one-on-one setup

The 58AI Bootcamp has six levels, three of them free. Not sure where to start? Start free. (Course pages are in Chinese.)

Workflow

Every step of the job, and exactly where AI sits.

Buying, selling, leasing, content, follow-up, closing, books, and the people around a deal — eight tracks, laid out step by step, each step marked for how far AI actually goes. The third mark is what this page is about: the more a machine can do, the more precisely you have to say what it does not touch.

Three marks

8 tracks · 55 steps · one mark each. Open a track for the detail.

  • Runs on its own

    The machine finishes it and I read the result. A step only earns this mark when a bad run is visible and reversible.

  • AI drafts · I review

    The machine writes it; I go through it line by line. What goes out carries my name, and the responsibility with it.

  • Human only

    The preparation can run fully unattended; the motion that commits has to be a person. Not because the machine cannot reach it — because that motion should not be handed over.

Deal tracks

What one transaction looks like from first call to keys. Commercial is missing on purpose — it goes up when I have real closings behind it, not a generic template.

Buy side 8 steps · from "I want to look around" to signatures
  1. AI drafts · I review

    Needs summary and area shortlist

    What the client tells us comes back as a first-pass needs summary and a shortlist of areas — and it can be done by voice now, because voice already handles the customer-service half of this conversation. The real budget and the why-now get confirmed by a person afterwards.

  2. AI drafts · I review

    Search and shortlist

    Sweep everything on the market, drop the obvious no-gos, rank the rest. I read the list before it goes out — no model knows the elevator in that building breaks weekly.

  3. Runs on its own

    Per-property briefing

    Taxes, maintenance fees, sale history, neighbourhood numbers, what is within walking distance — one page per unit. Pure retrieval and arithmetic, so it runs unattended.

  4. AI drafts · I review

    Showing schedule and route

    Time windows, driving order, and the back-and-forth with the booking system get planned; conflicts resolve themselves.

  5. AI drafts · I review

    Showings, with backup

    A person is in the room and the machine is on call: amenities answered on the spot, a quick read on the surrounding blocks, this unit compared against the last one while you are standing in it, feedback and a recap written up before you reach the car. Light, noise, a water stain, a smell — someone still has to stand there.

  6. AI drafts · I review

    Comparables and offer range

    The machine pulls comparables and lines up the definitions. What we offer and how we pace it is my call.

  7. AI drafts · I review

    Agreement drafted

    Starts from an address or a listing number and produces a draft, clause by clause against the template. Drafting assistance — the agent reviews and decides.

  8. AI drafts · I review

    Offer analysis, negotiation, signing

    Clauses broken down quickly, strategy suggested from options set in advance, e-signature sent out by the system. That only works because an experienced agent loaded the options first — the playbook is human-built and the machine picks from inside it. The call stays mine.

Sell side 8 steps · from pre-list walkthrough to accepting an offer
  1. AI drafts · I review

    Pre-list assessment and pricing strategy

    A detailed pricing strategy with the numbers behind it comes out of the machine. How it gets presented — which part leads, which comparison carries it, how the pushback gets absorbed — is designed in advance, by a person.

  2. Runs on its own

    Comparables and market data

    Same type, same range, same window — sold and active, in one table. Neighbourhood numbers refresh monthly on their own.

  3. AI drafts · I review

    Prep list

    Declutter, repairs, staging, photography and measurement scheduling, laid out backwards from launch day. Which spending is worth it, I edit.

  4. AI drafts · I review

    Listing copy and cards

    English and Chinese written separately, never translated across. Translated copy is the most recognizable kind of AI writing there is. I read it before it goes out.

  5. AI drafts · I review

    Board entry and field checks

    Tab by tab, validated field by field, instead of hunting through a dozen screens — with the agent confirming each step before anything is saved.

  6. Runs on its own

    Traffic and feedback digest

    Clicks, bookings, showing counts and recurring feedback words, summarized weekly — fuel for the next pricing conversation.

  7. AI drafts · I review

    Offer summary and clause review

    Several offers put side by side, clause by clause, risk spots flagged. Price is one line — conditions, deposit, closing date, how solid the financing looks. Ranking them is still judgement, not a sort function.

  8. AI drafts · I review

    Negotiate and accept

    Same as the buy side: strategy drawn from a pre-loaded set of options, signing initiated by the system. Whether to accept, and when, is a person.

Leasing 7 steps · landlord and tenant side merged; differences flagged in place
  1. Runs on its own

    Rent positioning

    Leased and available comparables for the same layout, building and window, resolved into a range.

  2. AI drafts · I review

    Listing and copy

    Both languages written separately; photo order and feature ranking drafted, then finalized by me.

  3. AI drafts · I review

    Showings and pre-screening

    Time windows and grouped showings get scheduled. Who is worth a separate appointment, I decide from the list.

  4. AI drafts · I review

    Application intake

    Checklist generated, missing items chased, formats normalized. What we collect and how far we go is fixed by the compliance line, not by convenience.

  5. AI drafts · I review

    Verification and factual extraction

    Source verification, objective extraction, factual red flags: verify what can be verified, mark what does not reconcile. The system states facts; it does not reach conclusions.

  6. Human only

    The tenancy decision

    Documents, comparisons and timeline arrive assembled. Who gets the unit is the landlord and the agent deciding, and carrying it — always a person, and always inside the tenant-selection boundaries of the Ontario Human Rights Code.

  7. Human only

    Lease signing and keys

    Documents, deposit receipts and the move-in checklist are all staged by the system. Signing, taking the deposit, handing over the keys — that trip is a person.

Operating tracks

These belong to no single deal, and every deal leans on them. Five things running in the background year-round.

Content and reach 7 steps · the one that never stops
  1. Runs on its own

    Topic selection

    Topics come from questions clients actually asked and from the numbers this month — not from a trending list.

  2. Runs on its own

    Bilingual writing

    English and Chinese are written independently. The same fact deserves a different emphasis in each language.

  3. Runs on its own

    Fact and figure checks

    Two rule gates: if a number cannot point at its source, or the wording touches a compliance line, the draft does not pass.

  4. Runs on its own

    Scheduled to go live

    Same time every day, unattended, year-round. One round once failed to go out because a path had a space in it — and every monitor stayed green. So now the monitoring gets verified too.

  5. Runs on its own

    Monthly market data

    Every neighbourhood number refreshes monthly and the pages grow themselves. Local pages carrying real figures with sources are also what machines are most willing to cite.

  6. AI drafts · I review

    Social and short-form rewrites

    The same piece reshaped for each platform, read by a person before it goes anywhere.

  7. AI drafts · I review

    Attribution and review

    Once content touches and follow-up records are wired together, attribution is a thing you can actually compute. Honestly: I built the content first and installed attribution later, and I am still catching up — so what I can give today is reach and real cases.

Follow-up (CRM) 7 steps · follow-up does not break for lack of time; it breaks for lack of memory
  1. Runs on its own

    Intake and cleanup

    Deduplicate, restore last-contact dates, recover what they were looking for at the time.

  2. Runs on its own

    Behavioural tiering

    Reply speed, how specific the questions get, open and revisit frequency. Someone asking about pre-approval, lawyers and closing dates is far closer than someone asking how the market is.

  3. Human only

    Life signals

    A job change, a family change, the real budget, the real reason for hesitating. Not in the data — only in the conversation.

  4. AI drafts · I review

    Drafting the touch

    Email, text, chat — all of it gets drafted. Every message has to carry something real: last month numbers for the neighbourhood they watched, a new listing that fits their criteria. Empty check-ins do more damage than any amount of AI phrasing.

  5. Human only

    Reviewed one by one, then sent

    Send one blast and some trust goes with it.

  6. Runs on its own

    Signal escalation

    They replied, they opened it, they came back — the signal returns and the tier updates itself.

  7. Human only

    Emotion, complaints, legal and tax

    Routed to a person. No exceptions.

Closing coordination 6 steps · the stretch between an accepted offer and handing over keys
  1. Runs on its own

    Timeline, built backwards

    Condition periods, deposit deadlines, financing approval, lawyer cutoffs, closing day — scheduled backwards from the closing date.

  2. Runs on its own

    Document checklist and chasing

    When something expected has not arrived, the system says so early instead of in the final week.

  3. AI drafts · I review

    Tracking every party

    Where the lawyer, the lender, the inspector and the insurer each stand, on one page. Who gets chased and how is my call.

  4. Human only

    Deposit and trust confirmation

    The ledger, the receipts and the timing reminders are staged automatically. The deposit actually entering the brokerage trust account, confirmed one by one, is a person. Money changing hands does not go through an automated path.

  5. Runs on its own

    Pre-closing prep and reminders

    Utility transfers, walkthrough checklist, key and fob counts, what was left behind — each one surfaced when it is due, so nobody has to remember it. The walkthrough itself is the next step.

  6. Human only

    Closing day and keys

    Funds, keys and fobs, the final walkthrough list — all lined up in advance. This is the day the client has been waiting for. You show up.

Books and commission 6 steps · your own business, run like a business
  1. Runs on its own

    Receipts and expense coding

    Photograph it once; it files itself under the right category.

  2. Runs on its own

    Mileage

    The driving that showings actually cost gets logged as it happens, so December is not a memory exercise.

  3. AI drafts · I review

    Commission math and reconciliation

    Splits, deductions and payment timing checked per deal; anything that does not reconcile gets flagged first.

  4. AI drafts · I review

    HST and year-end prep

    Filed quarterly so that what gets handed over is one clean package.

  5. Human only

    Filing and tax judgement

    That goes to the accountant. My job is handing over clean records — I do not answer tax questions on their behalf.

  6. AI drafts · I review

    Annual review

    Deal mix, cost structure, where the hours went. The machine pulls it; I draw the conclusion.

The people around a deal 6 steps · lawyers, lenders, inspectors, appraisers, insurers, movers, trades
  1. Runs on its own

    Who to contact, and when

    By transaction type and stage, the list of who needs contacting and what they need to receive.

  2. AI drafts · I review

    Briefs drafted

    What a lawyer needs is not what an inspector needs. Each brief gets drafted; I edit.

  3. AI drafts · I review

    Scheduling

    Availability, site visits and report turnaround land on the same timeline.

  4. Human only

    Who I recommend

    Profiles, quotes, availability and how they performed last time come assembled onto one page. Which one I recommend lends them my credibility — there is no automatic setting for that.

  5. Runs on its own

    Document routing and chase

    Who received what, who has not replied — status maintains itself.

  6. Human only

    When something goes wrong

    The inspection finds something, financing stalls, the lawyers disagree. At those moments what a client needs to hear is a human voice.

The steps a person has to execute

Every step marked human only, gathered into five kinds. The rest of the page is not unattended — in the AI-drafts-and-I-review tier the person sits inside each step. And this tier is not machine-free either: the preparation can run fully unattended. It is the last motion, the one that commits, that has to be a person.

  • Money and keys

    Preparation, unattended: receipts, the timestamp ledger, closing-day funds and key lists, lease documents — all staged. Execution, a person: the deposit entering the trust account, the keys changing hands, the signature going down.

  • Judgement and responsibility

    Preparation, unattended: profiles, quotes, availability, how they performed last time, assembled onto one page. Execution, a person: who gets the tenancy, which lawyer, which inspector. Recommending someone lends them your reputation — a machine does not get to lend mine.

  • Life signals

    The real budget, the family change, why now. Never in the data — only in the conversation.

  • Emotion and conflict

    Complaints, bad news, an inspection that turns something up, financing that stalls. What a client needs then is a human voice. Legal and tax questions go to a lawyer or an accountant; I do not answer on their behalf.

  • The look before it sends

    Every message that actually reaches a client is read first, one by one. Blast once and trust drops a notch.

AI helps you see it. A person signs it.

ABOUT 58AI

About the 58AI Bootcamp

The 58AI Bootcamp (official site: ai.58class.com) runs hands-on AI courses in Toronto, taught in Mandarin. Arthur Zhao is one of its instructors.

Arthur leads the real estate agent track, built around how agents actually work. Enrolment and schedule notices are posted on the bootcamp page.

58AI Bootcamp page → 58AI Bootcamp official site ↗ General agent training (in Chinese) →

GOOGLE REVIEWS

What do students say about Arthur’s training?

Rated 5.0 on Google from 19 reviews (as of 2026-10-08) · quoted as written

AI training for agents — questions

Do I need a technical background?

No. Classes start from your own business, using ready-made tools and tested templates — no code. A helper in the room sorts out setup problems on the spot.

What language is it taught in, and where?

Mandarin, in person, in small groups in Toronto. The venue for each session is announced with the schedule.

What does the 4-week course cost, and when does it start?

$258 + HST (was $558) for four weeks in four modules: a lead-generation website and data platform, social media branding, a personal AI assistant system, and an automated lead system. Classes are held at Unit 205, 105 Gordon Baker Rd, North York. Classes run Tuesday or Thursday mornings, 10:00 to 12:00; sign up on the course page (in Chinese) with no payment now, and a class opens once 10 people sign up.

Can AI write my contracts and offers?

No, and it should not. AI can gather documents, check dates and help draft wording; the agent reviews every term and signs. That boundary is the first lesson.

Can I put client information into AI tools?

Class covers which information can go to which kind of tool, what should stay out, and how to keep data under your own accounts. Your privacy and compliance duties are set by RECO and your brokerage policy.

How is this different from general agent training?

General agent training covers the business itself — starting out, buyer and seller work, negotiation and offers, client systems and referrals, and team management. This page covers how to bring AI into that work. The general training section is on the Chinese version of this page.

Understand it first, then build

Not sure AI fits your business? Come to a free session first. Once it makes sense, decide whether to sit down and build your own.