Everyone's being told to "add AI to support." Almost nobody can tell you what share of their tickets AI could actually handle.

That's the problem. The decision to turn on an AI support agent usually gets made on vibes, a vendor demo, and a gut feeling. Then either it underdelivers because the ticket mix was never suited to it, or it sits switched off because nobody could build the business case.

This hack gives you the number. In about five minutes you'll know your automation ceiling - the realistic percentage of tickets AI could resolve or assist with - based on your actual support history, not a sales deck.

 

Why This is Worth Doing

Before you pay for any AI support tool, you should know two things: how much of your volume it could plausibly take off your team's plate, and which ticket types those are.

Without that, you're guessing. With it, you can size the opportunity properly. If 50% of your tickets are repetitive, low-judgement queries, an AI agent is a strong investment. If 80% need genuine human judgement, your money is better spent elsewhere - better documentation, more headcount, or process fixes.

This also gives you a baseline. Run it now, make your changes, run it again in six months, and you can actually measure whether your automation strategy moved the needle.


Steps to Set it Up

Step 1: Export Your Closed Tickets

Go to Service > Tickets in HubSpot and switch to the list (table) view.

Filter for a representative sample of resolved work:

  • Ticket status: Closed
  • Create date: Last 30 days (or filter to your most recent 50 closed tickets)

Fifty tickets is enough to see the pattern without drowning in data. If your volume is low, widen the date range until you've got a meaningful sample.

Before exporting, set your columns to include the fields that help categorisation:

  • Ticket name/subject
  • Ticket description (if you capture it as a property)
  • Ticket category
  • Source
  • Time to close
  • Pipeline/stage

In the top right, click Export, choose CSV, and export the columns in your current view. HubSpot emails you a download link, usually within a couple of minutes.

One honest limitation worth knowing: HubSpot's ticket export includes ticket properties, but not the full email or conversation thread attached to each ticket. The categorisation will work from subjects, categories, and any description property you capture - so the richer those fields are, the sharper the output. If your tickets have vague subjects and no category, the AI is working with less to go on.

 

Step 2: Score Them with Claude or ChatGPT

Open the CSV. Open Claude or ChatGPT. Upload the file and use this prompt:

"Here are my last 50 closed support tickets. For each one, categorise it:

(A) AI could have resolved this alone,
(B) AI could have drafted the response for team approval,
(C) requires human judgement. Then give me the percentage breakdown and list the top 5 ticket types in category A."

What comes back is a clean three-way split with a percentage for each category, plus the specific ticket types that are most automatable. That category A percentage is your automation ceiling - the share of volume an AI agent could realistically resolve end to end. Category B is your assisted-drafting opportunity. Category C is the human-judgement work that should stay with your team.

 

Step 3: Read the Three Categories Properly

Each category points to a different action.

Category A - AI could resolve alone. These are your password resets, "where's my invoice," opening hours, basic how-to questions, and status checks. High volume, low judgement, consistent answers. This is the number that justifies (or doesn't justify) an AI support agent. Most teams find this lands somewhere in the 40 to 60% range - though it varies a lot by industry and product complexity, so treat any benchmark as a starting point, not a promise.

Category B - AI could draft for team member approval. These need a human to check the answer, but not to write it from scratch. Think nuanced account questions or anything where the right answer exists but needs a judgement call on tone or specifics. This is where AI-assisted drafting tools earn their keep, even if full automation isn't appropriate.

Category C - requires human judgement. Complaints, sensitive accounts, complex troubleshooting, anything emotionally charged or commercially significant. This work should stay with people, and that's the point - knowing your category C size tells you how much genuinely human support capacity you need to protect.

 

Step 4: Turn the Number Into a Decision

The category A percentage is the headline, but the top 5 ticket types are where the action is.

If the AI flags "password reset," "invoice request," and "delivery status" as your top automatable types, those are your first candidates for either a knowledge base article, a canned response, or an AI agent scope. Start with the highest-volume, lowest-risk types and expand from there.

If you're considering HubSpot's own Breeze Customer Agent, this number is exactly the input you need. Breeze is priced per resolved conversation (as of April 2026, $0.50 per resolved conversation - you only pay when it actually closes the ticket without personal escalation). Your category A percentage, multiplied by your monthly ticket volume, gives you a realistic estimate of how many conversations it could resolve and what that would cost versus the work hours it frees up.

 

A Note on the Numbers

Treat the output as directional, not gospel. The AI is categorising based on ticket metadata, not reading the full resolution history, so it's making an informed estimate of what could have been automated, not a guaranteed forecast.

The real value isn't the exact percentage. It's that you move from "we should probably look at AI for support" to "47% of our volume is automatable, concentrated in these five ticket types, here's the business case." That's a decision you can actually act on.

Run it once a quarter and the trend matters more than any single reading. As you publish documentation, refine processes, and adjust your product, your automatable percentage shifts. Tracking it tells you whether your support operation is getting more efficient or just busier.

 

Want Help Building the Automation Itself?

Finding your automation ceiling is the easy part. Scoping an AI agent properly, writing the knowledge base it draws from, setting the escalation rules so the human-judgement tickets always reach a team member - that's the work that makes or breaks an AI support rollout.

Neighbourhood is a Diamond HubSpot Partner. We help Service Hub teams turn "we should automate some of this" into a setup that actually holds up with real customers. If your ticket data is telling you there's capacity to claw back, get in touch.

Talk to us about your HubSpot setup. 

 

Get More Hacks Like This

Ops Intel is our newsletter for HubSpot admins and support teams - practical hacks and no filler, straight to your inbox every week. Subscribe to Ops Intel.

We are also on Facebook and YouTube breaking down hacks like this one. Come find us there.

See you!