AI Assistants

Overview

AI Assistants define how Bread Crumbs Bot generates responses for incoming messages. Each assistant is created with an AI type and type-specific integration properties.

Supported AI types

Shared model

All AI assistants are created through the same GraphQL mutations (createAi, patchAi, deleteAi) and queried using ais/ai. The behavior depends on type and integrationProperties.

Bread Crumbs AI

Bread Crumbs AI assistant (Crumby) is a pre-built AI assistant customized to serve most common use cases. This one is created automatically for you when you get an access on Crumby Playground (opens in a new tab).

Runtime features

You can train Crumby with your own data on Crumby files (opens in a new tab) and Crumby text (opens in a new tab) pages.
Crumby can gather client information for you if that is enabled in Crumby settings (opens in a new tab).
Crumby can transfer the conversation to an agent if you have handover enabled in Crumby settings (opens in a new tab).
Crumby can apply tags to the client and/or conversation if you have any tag rules configured in Crumby settings (opens in a new tab).

OpenAI

OpenAI assistant uses your OpenAI API key and model to generate text replies.

AI type

Use openai in AI creation operation.

Integration properties

Attributes	Type	Description
`apiKey`	`string`	Required. Your OpenAI API key.
`model`	`string`	Required. OpenAI model name (for example: gpt-4o, gpt-4.1).

Runtime behavior

Bot sends the incoming message content using the OpenAI AI adapter.
Bot returns a text response.

Special keywords

In case the agent returns a response containing one of the following keywords, Bot will handle them specially:

#HANDOVER#: Handover the conversation to an agent.
#END#: End the conversation.

Create OpenAI AI (GraphQL)

POST https://gateway.bcrumbs.net/bot/gq

mutation createAi($input: AICreateInput!) {
  createAi(input: $input) {
    id
    workspaceId
    name
    type
    integrationProperties
    createdAt
  }
}
 
input AICreateInput {
  workspaceId: Int!
  integrationProperties: JSON!
  name: String!
  type: AIType!
}

Next is an example of the input for the createAi mutation in JSON format:

{
  "input": {
    "workspaceId": 12,
    "name": "My OpenAI AI",
    "type": "openai",
    "integrationProperties": {
      "apiKey": "your-openai-api-key",
      "model": "gpt-4o"
    }
  }
}

Pinecone

Pinecone assistant uses your configured Pinecone integration properties to generate text replies through the bot runtime.

AI type

Use pinecone in AI creation/patch operations.

Integration properties

Attributes	Type	Description
`apiKey`	`string`	Required. API key used by the Pinecone AI handler.
`model`	`string`	Required. Model identifier used by the Pinecone AI handler.

Runtime behavior

Bot sends the incoming message content using the Pinecone AI adapter.
Bot returns a text response.

Special keywords

In case the agent returns a response containing one of the following keywords, Bot will handle them specially:

#HANDOVER#: Handover the conversation to an agent.
#END#: End the conversation.

Create Pinecone AI (GraphQL)

mutation createAi($input: AICreateInput!) {
  createAi(input: $input) {
    id
    workspaceId
    name
    type
    integrationProperties
    createdAt
  }
}
 
input AICreateInput {
  workspaceId: Int!
  integrationProperties: JSON!
  name: String!
  type: AIType!
}

Next is an example of the input for the createAi mutation in JSON format:

{
  "input": {
    "workspaceId": 12,
    "name": "My Pinecone AI",
    "type": "pinecone",
    "integrationProperties": {
      "apiKey": "your-pinecone-api-key",
      "model": "pinecone-model-id"
    }
  }
}

Custom AI

Custom AI lets you connect your own AI provider through a custom integration flow. You can configure it from the portal integrations guide: Custom AI integration.

You can check our playground to explore and interact with GraphQL APIs easily and intuitively with real-time documentation.

Agents Broadcasts