Speed up support ticket research and triage
A ClickUp support engineer built a system cutting per-ticket research from 15 to 4 minutes across 5,000+ monthly tickets; Mercari handles first replies for 97% of tickets.
Done with a custom-built or unnamed agent
- What they did
- The source is a listing page with only short blurbs, so it has little on mechanics. Corey Smith, a Senior Technical Support Engineer at ClickUp, built a system for the research that comes before a rep replies to each ticket. Mercari built an AI support orchestration system on Zapier that handles first replies.
- How it went
- ClickUp's research time per ticket fell from 15 minutes to 4, about 917+ hours a month across 5,000+ tickets. Mercari handles first replies for 97% of tickets and resolves roughly 47,000 a month through automation alone.
- Worth knowing
- This page gives no build details, tools or costs. Read the full ClickUp and Mercari stories on Zapier's site before copying either approach.
Try it yourself with Zapier Agents
Help me build a Zapier Agent for my support team that, whenever a new ticket arrives in [Zendesk/Intercom/Help Scout], researches it by searching [my knowledge base, past tickets, docs], then adds a note with a likely cause, relevant links, and a suggested reply. Don't send anything to the customer; the note is for my agent to review. You're done when a test ticket gets a useful research note in under [5] minutes.
Source: zapier.com · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Custom agent
Sell services through an agent that takes payment and delivers
An agent runs a transaction flow, creates Stripe checkout links, verifies payment before delivering a service, and asks the owner on Telegram to approve refunds or disputes.
Run marketing research and copywriting drafts with agents
The author built OpenClaw-style agents for research, content structure and first-draft copy; research saved 2-3 hours a week and agents needed oversight.
Review Meta ad performance inside Ads Manager
An agency tested Manus on a real ecommerce client's Meta ads account; it reported a 14.25x ROAS against an actual 1.76x and corrected itself only when challenged.
Turn new Gmail emails into Notion CRM leads
A Zapier Agent triggers on each new Gmail email and creates a lead record in a Notion database with mapped properties filled in.
- Custom agent
Answer tenant and rental prospect questions with AI
A commenter says AI tools handle most tenant questions, prospect inquiries and document preparation, handing harder cases to a human.
Find stale commercial listings and email brokers
A Hermes bot scrapes lease listings, filters by days on market and zoning, calculates commissions and emails brokers.