Skip to main content
Ari is the customer facing AI agent built into Plain. It answers what it can from your Knowledge Sources, and hands off to your team the moment it is unsure, before one of your customers has to ask twice. There is no flow builder and no decision tree to configure. Turn Ari on, point it at your knowledge, and it starts answering.
  1. Resolves the routine instantly, around the clock
  2. Knows when to step back, and hands off to a human before a customer gets frustrated
  3. Answers only from your knowledge, so its responses stay grounded in what you’ve told it
  4. Answers from your knowledge with no flow to build

​
Ari and Sidekick

Plain has two AI agents. Ari responds autonomously to your customers without a human-in-the-loop; Sidekick works for your team and helps you automate your support process. Set up, test, and deploy Ari in five steps.

​
1. Enable setting

Ari is part of Plain AI, which is enabled by default on new workspaces. Check this page if you’ve previously opted out.

​
2. Add knowledge

Ari automatically reads your customer facing Help Centers. Add anything outside Plain as a Knowledge Sources. Ari only answers from this knowledge; without it, it will have a high deflection rate.

​
3. Route threads

Ari works on threads assigned to it. There are two ways to do that.

​
Assign via workflow

Go to Workflows, create a rule, and use the “Assign to user” action with Ari selected. The conditions on the rule decide which threads Ari picks up, so you can scope it by tier, label, channel, or business hours. Example: “When a new thread is created on the chat channel with tier Free, assign to Ari.” Use this Workflow Template to get started.

​
Manually

Assign Ari to any thread yourself, exactly like assigning a user. Useful for testing on a specific conversation.

​
4. Test

Enable Ari in Shadow Mode to see how it behaves on threads without yet giving it the permission to send messages to your customers. And try out Ari in the Playground, to test specific scenarios and build trust. This is a great time to tweak Ari’s behavior via Custom Instructions, to better suit your support process and tone.

​
5. Go live

When you’re happy with Ari, and have built trust with the agent, then switch the mode from Shadow to Live on the Ari → Preferences page. Ari starts replying to customers on the threads your workflows assign to it.

​
How do I know it’s working?

Head over to either of the following pages to see which threads Ari is working on:

​
What can Ari see?

Each time a customer message arrives on a thread that Ari is assigned to, it assembles a fresh snapshot of the thread to use as context. Ari uses a well defined set of inputs to build the context of a thread, then uses that context to decide what to do next on a thread and act independently. See Context for a full breakdown of what is included.

​
Custom instructions

Custom instructions let you tell Ari how to handle support for your workspace, in your own words. Ari applies them at every step of handling a request: understanding the customer’s message, searching your knowledge sources, and writing replies and handoff messages. For example, you can have Ari:
  1. Introduce itself in a specific way on the first reply of a conversation
  2. Hand every billing question to your team, with a note explaining why
  3. Ask for the exact error message before troubleshooting, then pick the conversation back up when the customer answers
  4. Search using your documentation’s terminology when customers use different words
See Custom Instructions for examples and guidance on writing them.