How Many Transactions Can a Real Estate Agent Handle?

By Emily Terrell — Top Coach and Speaker at Tom Ferry International. 4 years coaching at Tom Ferry, 9 years prior as a client.

A real estate agent can handle as many transactions as their face-to-face hours allow, and AI raises that ceiling by eliminating admin work, not by showing homes or negotiating repairs. NAR’s 2026 Member Profile puts the typical agent at nine sides a year. This guide covers the capacity formula, the AI stack, and where people take over.

Key Takeaways

• Your transaction ceiling is set by the hours only you can work (showings, appointments, pricing conversations, negotiation), not by your tech stack.
• AI raises capacity by pulling admin work off every deal, which frees selling hours, but it doesn’t shorten the face-to-face work itself.
• NAR’s 2026 data shows four-person teams closing a median of 32 sides, roughly eight per person, so adding people without systems doesn’t multiply output.
• In my coaching, the agents who scale past 50 closings pair AI with at least one person in the transaction pipeline who isn’t them.

What is real estate agent transaction capacity?

Transaction capacity is the number of closings an agent can manage in a year before service quality, response time, or their own schedule breaks down. It comes down to two numbers: how many hours the agent can spend on work only they can do, and how many of those hours each transaction consumes. Everything else, including AI, either protects those hours or wastes them.

Why this matters for real estate agents

According to NAR’s 2026 Member Profile (June 2026), the typical agent completed nine transaction sides in 2025. For the first time, the same report separated team data: teams averaged four members, and team-based brokerage specialists reported a median of 32 sides.

Do the division. That’s roughly eight sides per person, about what an individual agent produces. NAR Deputy Chief Economist Jessica Lautz framed team growth as part of how Realtors are adapting to a hard market. That’s true. But the per-person math shows that adding people increased headcount, not per-person output.

AI hasn’t closed that gap on its own either. According to NAR’s 2025 Technology Survey (September 2025), 46% of agents said AI had no noticeable impact on their business, and only 17% reported a significantly positive one.

Here’s the thing nobody wants to tell you: more people won’t raise your ceiling by themselves, and neither will more tools. Systems do. People and AI are only as effective as the system they plug into.

“AI doesn’t give you more hours with clients. It gives back the hours you were losing to paperwork, and what you do with those hours decides whether you close 20 deals or 50.”
— Emily Terrell, Tom Ferry Coach

How do you calculate how many transactions a real estate agent can handle?

Your real number comes from your own calendar, not an industry benchmark. Work through these four questions in order.

What work can only you do?

Start by listing every task on a transaction that requires you personally. For most agents, that means showings, listing appointments, pricing conversations, offer negotiation, inspection responses, and the handful of relationship moments where the client needs to hear from you directly.

Track the hours you spend on those tasks for 30 days across every active deal. Divide by the number of deals. That’s your face-to-face hours per transaction, and it’s the most important number in your business.

What can AI take off every transaction?

AI should take over any task that repeats on every deal and can be reviewed before it goes out. That includes MLS descriptions, the listing marketing suite, follow-up drafts, CMA summaries, client status updates, and social content for new listings.

The key word is every. A task that happens once a year isn’t worth building a workflow for. A task that happens 40 times a year is. If you’re starting from zero, automating MLS listing syndication is one of the fastest places to win back hours.

What needs a person who isn’t you?

Some work needs a human, just not you. A transaction coordinator owns accountability: chasing lenders, catching missing signatures, and flagging a deadline before it becomes a problem. AI can draft the reminder email. It can’t pick up the phone when the title company goes quiet.

Showings are the next constraint. Once your calendar is full of tours, a showing assistant or buyer’s agent is the only thing that adds capacity.

What’s the capacity formula?

Capacity = annual selling hours ÷ face-to-face hours per transaction.

Here’s an illustrative example. Say you work 2,000 hours a year and admin eats 900 of them. That leaves 1,100 selling hours. At 25 face-to-face hours per deal, your ceiling is 44 closings. Move 500 of those admin hours to AI and a coordinator, and the ceiling rises to 64, without adding a single hour to your week.

This is the actual how. AI doesn’t make the showing shorter. It gives you back the hours the paperwork was taking.

What does capacity look like at each stage?

These are the patterns I see across the agents I coach, not industry benchmarks:

• Solo, no support: Quality usually starts slipping somewhere between 25 and 40 closings a year. The limit is admin load, not talent.
• Solo with AI and a transaction coordinator: Roughly 50 to 60. AI handles repeatable content and drafts, the coordinator owns contract-to-close, and the agent’s calendar is almost entirely face-to-face work.
• Beyond 60: The agent is now running a team, even a small one. The next hire covers showings or buyer consultations, and AI keeps that team smaller than it would otherwise need to be.

How I use this in my own business

I close 70+ transactions a year in San Antonio on roughly five hours a week of active management, and I want to be precise about what that sentence means: I don’t close 70 deals alone. AI is the reason that the team stays small.

My MLS descriptions come from a saved Claude prompt that writes in my voice with Fair Housing constraints built in. I edit the output for about thirty seconds. The listing marketing suite doesn’t live in a chat window. It moves straight into the templates my transaction coordinator already uses, which is why the system keeps running during weeks when I’m on a stage instead of at my desk.

What AI never took over: the listing appointments, the pricing conversations, the negotiations. Those hours went to people, and that’s by design. I coach the same structure at Tom Ferry International. Start with the hours only you can work, then build everything else around protecting them.

Common mistakes

1. Buying tools before measuring hours. If you don’t know your face-to-face hours per transaction, you can’t tell whether a tool raised your ceiling or just filled your week with new tabs.
2. Letting AI send client-facing messages without review. A wrong price or an invented square footage goes out at scale. Every generated property fact gets checked against the MLS record, and every listing description gets reviewed against NAR’s Fair Housing guidance. This is general information, not legal advice; consult your broker on specific listings.
3. Hiring before building systems. NAR’s team data shows the result: four people producing roughly what four individual agents would. Document the workflow first, then hand it to someone. The guide to what agents can safely automate around the MLS is a good starting audit.
4. Comparing your solo numbers to a team’s numbers. A 70-deal benchmark from a team with support staff isn’t a target for one agent working alone. Measure yourself against your own formula.
5. Measuring AI by output instead of hours returned. Ten captions in two minutes means nothing if they never leave the chat window. AI training for real estate agents only works when every workflow has a destination.

Frequently Asked Questions

How many transactions does the average real estate agent do a year?

The typical Realtor completed nine transaction sides in 2025, according to NAR’s 2026 Member Profile. Teams, which averaged four members, reported a median of 32 sides. The gap between individual and team output comes mostly from structure: support staff, delegated tasks, and systems that run whether or not the lead agent is at a desk.

Can AI replace a transaction coordinator?

Not fully. AI can draft status updates, build deadline checklists from a contract, and write client emails, but a transaction coordinator owns accountability: chasing lenders, catching missed signatures, and escalating problems before they cost you the closing. The strongest setup pairs the two. AI produces the drafts, and the coordinator decides what goes out and when.

How many transactions can a solo agent handle without an assistant?

In my coaching, most solo agents without support start losing quality somewhere between 25 and 40 closings a year. The limit isn’t talent. It’s the admin load: every transaction carries paperwork, follow-up, and marketing that compete with showings and appointments. AI raises that ceiling, but a transaction coordinator usually raises it further.

What tasks should real estate agents automate with AI first?

Start with the tasks that repeat on every transaction: MLS descriptions, listing marketing copy, follow-up drafts, and client status updates. They’re high-volume, low-risk, and easy to review before sending. Save contract interpretation and pricing advice for yourself. AI should draft; you decide, and every generated property fact gets checked against the MLS record.

Does AI help real estate agents close more deals?

Only when it’s wired into a system. According to NAR’s 2025 Technology Survey, 46% of agents said AI had no noticeable impact on their business, while 17% reported a significantly positive impact. The difference is usually where the output goes. A prompt that lives in a chat window saves minutes. A workflow that lands in your CRM saves hours.

When should a real estate agent hire help instead of adding more AI?

Hire when the work left on your plate is face-to-face and you’re turning away business. AI can’t attend a showing, sit at a listing appointment, or negotiate an inspection response. If those hours are full and leads are still coming in, the next hire is usually a showing assistant or buyer’s agent, not another software subscription.

Bring this to your team or event

Emily Terrell speaks at brokerage events, real estate conferences, and team trainings on AI, systems, and social media — the exact playbook in this post, delivered live to your audience. As a Top Coach and Speaker at Tom Ferry International and an active agent closing 70+ transactions a year, Emily speaks from the stage about what’s working right now, not theory. Recent stages include NAHREP and eXp Con.

Book Emily to speak at your next event:
Email: eterrell@yourcoach.com
Phone: (210) 400-9191
Web: coachemilyterrell.com

For real estate agents who want to implement this: Get the weekly real estate prompt library at weeklyrealestateprompts.com or follow @coachemilyterrell on Instagram for daily systems and AI breakdowns.