Reference guides for the support apps an AI agent can work with: every endpoint, the permission each one needs, and how to give agents safe, governed access.
The Crisp API is how an app or AI agent works with a Crisp support workspace: listing conversations, sending a message to a customer, moving a conversation to resolved, or creating and updating contact profiles in the CRM.
The Dixa API is how an app or AI agent works with a Dixa customer service workspace: reading and creating conversations, replying to a customer or adding an internal note, closing or transferring a conversation, and managing end users, agents, teams, queues, and tags.
The Freshchat API is how an app or AI agent works with a Freshchat account: reading a conversation, sending a message to a customer, creating or updating a user, or pulling agents and groups.
The Freshdesk API is how an app or AI agent works with a support account: creating and updating tickets, replying to customers and adding internal notes, and managing the contacts and companies behind those tickets.
The Gorgias API is how an app or AI agent works with a support helpdesk: reading and replying to tickets, creating and merging customers, applying tags and macros, and managing the agents who handle conversations.
The HappyFox API is how an app or AI agent works with a helpdesk: listing and reading tickets, replying to a customer or adding a private note, moving a ticket or changing its status and assignee, and looking up contacts and staff.
The Help Scout API is how an app or AI agent works with a Help Scout account: listing and reading conversations, replying to a customer or adding an internal note, creating and updating customer records, and pulling support reports.
The Intercom API is how an app or AI agent works with an Intercom workspace: reading and replying to conversations, creating and updating contacts, managing support tickets, publishing help center articles, and recording the events a customer triggers.
The Kustomer API is how an app or AI agent works with a Kustomer organization: reading and creating customer records, opening and updating conversations, sending messages on a customer timeline, and adding internal notes.
The LiveChat API is how an app or AI agent works with a LiveChat account: listing and reading live chats, sending a reply into a conversation, transferring or ending a chat, and reading or updating customers and agents.
The Zendesk API is how an app or AI agent works with a Zendesk Support account: creating and updating tickets, replying to a customer or adding an internal note, looking up users and organizations, applying a macro, and searching across records.
A support API is how an app or AI agent works with customer tickets and conversations. The platforms here, including Zendesk, Intercom, Freshdesk, and Help Scout, hold support tickets and chats, and their APIs let an agent read a ticket, reply to a customer, update a conversation, or react when a new one arrives.
Replies go to customers and tickets hold their details and history, so a write permission that sends a reply and read access to conversations are both worth scoping. Access runs on an access token scoped to particular actions. A governed layer lets an agent that drafts replies read tickets without being able to send to customers on its own.
Bollard AI sits between a team's AI agents and the apps it runs on. Grant each agent exactly the access it needs, read or write, app by app, and every call is checked and logged.