Kalshi's AI agent handled 80,000 support tickets in one day around the Super Bowl
In plain words
Prediction market Kalshi went live with Fin in about 10 days, just before its biggest weekend ever.
What happened: AI solves about 80% of chats, and replies now take minutes instead of about 23 hours. Fully live in about 10 days.
Source: fin.ai ↗
How to do it yourself
Our suggested steps. The company didn't publish theirs.
- 1
Find your next traffic spike date and work back from it.
- 2
Rewrite your help articles for those topics so each has one clear answer.
- 3
Connect Intercom Fin to your helpdesk and knowledge base and paste the prompt below as its instructions.
- 4
Run it on 50 real past tickets and fix every wrong or vague answer.
- 5
Go live on one channel, review a sample every week, then add channels.
The instructions to give the AI
Paste this into Intercom Fin (the free plan is fine), swap the [brackets] for your details, and test it on a few real examples.
This is one part of the setup. It won't connect to your phone, inbox or other apps on its own; the steps above cover that.
Agent instructions (prompt)
You support [platform] traders. Answer questions on deposits, withdrawals, verification and market rules using the docs. Never give trading advice. For stuck withdrawals over [time], collect the transaction ID and hand to a human.
[Highlighted] = replace with your own details before you run it.
What you should get back: "Your withdrawal of $500 is processing and should land in 1-2 business days."
Written by Quickly and Good, inspired by this case.
More detail: tools, prices and what you'll need
The company used: Intercom Fin
You could use: Intercom Fin
- Intercom Fin
AI support agent that answers customers from your help centre and hands off to humans.
From $0.99 per resolution · Official site ↗
Prices from each tool's own pricing page, checked Oct 2026.
What you'll need
- ☐A help desk or chat widget on your site (e.g. Gorgias, Tidio, Intercom)
- ☐A knowledge base: FAQs, shipping/returns policies, product info
- ☐Connection to your store or orders (e.g. Shopify) so it can look up orders
- ☐Tone and rules for what the AI must never promise
- ☐Testing against 50+ past tickets before going live
- ☐Hand-off to a person when it is unsure or the customer is upset
Can I do this myself?
Yes, for most small shops. The built-in setup does the heavy lifting; the real work is writing a good knowledge base and testing.
Similar cases
CMA CGM's AI voice agents resolve 46% of cargo release calls
More than 46% of cargo release enquiries are resolved by the AI agents, and about a third of 4,000 customers called by the sales agent moved on to active discussions.
ElevenLabs' own AI support agent resolves 65% of its tickets
65% of tickets resolved end to end, first reply in about 60 seconds instead of hours, and 70% positive ratings.
Telstra lets an AI agent sort refunds while customers wait for repairs
Refunds are worked out and paid automatically once service is back, which takes admin off 1,000+ staff.