Underdog's AI agent handles 80% of questions on busy game days
In plain words
Sports app Underdog gets 7,000+ extra conversations in 48 hours on big weekends. Fin checks withdrawals and gives personal updates.
What happened: Nearly 80% of questions at peak times are answered without a person.
Source: fin.ai ↗
How to do it yourself
Our suggested steps. The company didn't publish theirs.
- 1
Look at your busiest 48 hours last year and list what people asked.
- 2
Pick 1-2 actions it may take on its own (e.g. order lookup, address change) and set the limits.
- 3
Connect Intercom Fin to your store or back office and paste the prompt below.
- 4
Test each action on 30 real cases with a human checking.
- 5
Turn it on, track automation rate and CSAT weekly, add the next action.
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 [app] players during live events. Look up the player's recent withdrawals and give a specific status. Follow responsible-gaming rules: if someone mentions losing control, share [support line] and hand to a human.
[Highlighted] = replace with your own details before you run it.
What you should get back: "Your $200 withdrawal is pending — usually 24h on game days. Here's where to track it."
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.