> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/tech/en/serve.md). # MaiAgent Serve｜Customer Service Integration - [Software Vendor Integration Guide: Embed AI Agents for Your Customers](https://docs.maiagent.ai/tech/en/serve/vendor-integration-guide.md): An end-to-end guide for software vendors to embed Web Chat in their products and integrate permissions, covering embedding, bulk backfilling, login synchronization, Token refresh, and credential revoc - [Web Chat Embedding and SDK](https://docs.maiagent.ai/tech/en/serve/web-chat-sdk.md): Embed MaiAgent Web Chat on any website: embed code, window modes, user identification, the full configuration reference, and the JavaScript SDK API - [Embed in MaiGPT Mode](https://docs.maiagent.ai/tech/en/serve/web-chat-sdk/web-chat-maigpt-mode.md): Embed the full ChatGPT-like MaiGPT conversation interface in your website or product, with support for a designated container or a floating button with fullscreen display - [Inject Page Context](https://docs.maiagent.ai/tech/en/serve/web-chat-sdk/web-chat-context-data.md): Use auth.contextData in the embed SDK to inject page context (such as product IDs, ticket numbers, and user identifiers) into the Agent's LLM System Prompt - [LINE LIFF: What Is LINE LIFF?](https://docs.maiagent.ai/tech/en/serve/whatislineliff.md): What is LINE LIFF (LINE Front-end Framework)？A framework for embedding web applications in the LINE app, and the benefits of opening MaiAgent Web Chat through LIFF. - [LINE LIFF: How to Integrate](https://docs.maiagent.ai/tech/en/serve/whatislineliff/setting.md): LINE LIFF integration steps: create a LIFF app in LINE Developers and set the conversation platform's public URL as the Endpoint URL to open Web Chat within a LINE chat window. - [LINE Flex Message Specifications](https://docs.maiagent.ai/tech/en/serve/line-flex-message.md): How MaiAgent sends LINE Flex Message cards: the FlexMessage tool's template and AI field format, the validation endpoint, flex items in streamed replies, and the limits and failure handling when deliv - [Introduction to Contacts and Integration](https://docs.maiagent.ai/tech/en/serve/contacts.md): Contact overview and integration — map your system's users to end users with sourceId, four ways to create and synchronize contacts, Excel bulk import, and implementation recommendations. - [Contact Identity Synchronization and Token Updates](https://docs.maiagent.ai/tech/en/serve/contacts/contact-credentials-sync.md): Use setup-contact-credentials to synchronize contact identities and update token credentials when enterprise systems add users and on each login - [Differences Between Roles and Contacts](https://docs.maiagent.ai/tech/en/serve/contacts/role-vs-contact.md): Internal members use roles (Role) to manage platform permissions, while external users are identified as contacts (Contact); see the user manual for a complete comparison - [Third-Party Customer Service System Integration (Including Human Handoff)](https://docs.maiagent.ai/tech/en/serve/customer-service-system-integration.md): Connect a customer service system or chat platform to MaiAgent as an AI engine via API: end-to-end specifications for message exchange, handoff to your human agents when AI determines it is needed, an - [Genesys Cloud Integration](https://docs.maiagent.ai/tech/en/serve/customer-service-system-integration/genesys-cloud-integration.md): Connect the MaiAgent conversation platform to Genesys Cloud through Open Messaging, covering architecture, OAuth credentials and APIs, two-way message flow, signature verification, error handling, and - [Conversation Handoff and Continuation API](https://docs.maiagent.ai/tech/en/serve/conversation-handoff-continuation.md): Create a continuation conversation from a handoff summary and identify the relationship between the original and continuation conversations. - [Call Center Outbound API](https://docs.maiagent.ai/tech/en/serve/call-center-outbound-api.md): Use the call center outbound API from an external system to have the Agent bound to a number place a call, then query its status with the call records API. - [Webhook](https://docs.maiagent.ai/tech/en/serve/webhook.md): Conversation platform Webhooks: push visitor messages and AI or human replies to your system in real time, with support for the MaiAgent standard format, Genesys Cloud, and custom Jinja2 templates --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.maiagent.ai/tech/en/serve.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.