← All use cases
Intercom FinVanta

Vanta's AI agent fully solves 71% of the chats it handles

In plain words

Vanta's old bot was stuck at 45% deflection and didn't cover email. It tested Fin head to head and switched.

What happened: 71% of its chats solved with no person, about 2,500 a month. Chats passed to staff still get 94.1% happy customers.

Source: fin.ai ↗

⏱ About 3-7 days to set up🎓 No-code beginner

How to do it yourself

Our suggested steps. The company didn't publish theirs.

  1. 1

    Take 100 past tickets and test two AI agents on them side by side before you pick one.

  2. 2

    Rewrite your help articles for those topics so each has one clear answer.

  3. 3

    Connect Intercom Fin to your helpdesk and knowledge base and paste the prompt below as its instructions.

  4. 4

    Run it on 50 real past tickets and fix every wrong or vague answer.

  5. 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 are the support agent for [company]. Answer only from the help articles provided. If the answer isn't there, or the customer is upset, say you're handing over and pass to a human with a one-line summary. Keep replies under 80 words, friendly and plain.

[Highlighted] = replace with your own details before you run it.

What you should get back: "Here's how to connect AWS: Integrations > AWS > follow the 3 steps in this article."

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

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.

Useful? Vote so others find it.

Similar cases