Automate lead gen and customer support with Salesforce Live Agent

Rachel Pautler
 on March 18, 2018

Meya now supports Live Agent within the Salesforce Service Cloud

Live chat has long been held as a gold standard for customer support. Being able to respond to customers quickly and solve their issue within minutes has lead to a new age of customer service. Customers demand immediate responses, even outside your company’s office hours. This is where bots excel.

We’ve just made it easier to provide amazing customer service with our latest integration: Salesforce Live Agent. Part of the Salesforce Service Cloud, Salesforce Live Agent is a live chat customer service tool.

With the Salesforce Live Agent integration, you can:

  • Offer personalized, real-time help online or in your apps
  • Escalate to human agents when needed
  • Share user contact details and notes with your agents
  • Provide insight into queue length and wait time
  • Transfer back to the bot if no agent is available
  • Transfer back to the bot after the chat with the agent is complete

Adding the Salesforce Live Agent integration to your bot requires someone with administrator access to your Live Agent account. Detailed integration instructions can be found in our Salesforce Live Agent support documentation.

Human/bot hybrid

Using bots built in Meya, you can answer more chat requests without growing your customer support team. A bot can be used as the first point of contact for all requests, transferring to an agent after gathering information, or solving the customer’s request completely.

The Salesforce Live Agent integration is a customer service integration. A core function of this type of integration is the ability to transfer from bot to human and back.

A chat can be user initiated or happen at a certain point in your bot flow. Once the request to chat with an agent has been submitted, the experience is very similar for your customer service agents. The major difference is that your agents will now have more context. Your agents will see a transcript of the previous conversation with the bot when they open the chat session.

When the agent has completed the conversation, they will close the chat with the customer. When this is done, your bot will take over and can request feedback or see if there is anything else that the customer needs help with.


If you’ve built a customer service bot within Meya using Intercom, Front, or Zendesk, much of the development will be familiar.

We’ve improved our human.transfer component to ensure easy development for Salesforce Live Agent. These properties are new:

  • visitor_details: A list of Salesforce fields that will be updated or created. If a field exists, the field will appear in both the transcript details as well as the visitor details. If the field doesn't exist, the field will only appear in the visitor details.
  • chat_ended: This flow will be triggered when the user or agent ends the conversation.
  • chat_request_failed: This flow will be triggered if no agent is available, or every agent rejects the conversation.
  • chat_transferred: This flow will be triggered every time the conversation is transferred to another agent.
  • queue_update: This flow will be triggered every time the user's position in the queue changes.
  • chat_request_succes: This flow will be triggered when a chat session has been established with Live Agent. Useful for displaying queue information on first connect.
  • chat_established: This flow will be triggered when an agent accepts the chat request.
  • chat_agent_disconnect: This flow will be triggered if the agent disconnects from the session.

Some notable development differences include:

  1. Salesforce Live Agent uses a support queue. This means that a session with your agent will not be initiated until the chat is accepted. Including a queue update (now part of our human.transfer component) will give your customers an idea of how long it will be before they are chatting with one of your agents.
  2. A chat can only be transferred if at least one agent is online. If all agents are offline, or if every agent rejects the chat, the conversation will be transferred back to the bot, and the chat_request_failed flow will be triggered.
  3. Agent or team assignment is not support in Salesforce Live Agent. Each transferred chat will be assigned to a random online agent. If that agent rejects the chat, it will be transferred to another online agent.
  4. Transcript history will be limited to the number of messages that you define in the integration settings. This includes both bot and user messages.
  5. Salesforce Live Agent does not support the ability for an agent to issues commands to the bot. The bot is paused when a conversation is transferred to an agent, and becomes unpaused when the chat with the agent ends.

Your customers deserve the highest standard of customer service. Our integration with Salesforce Live Agent allows you to provide a high level of customer service without growing your customer service team.

Instructions for integrating with Salesforce Live Agent can be found in our support documentation. If you have any questions, please reach out to!

This integration is available for all accounts on the universal plan. If you're not on our universal plan but are interested in adding this integration to your bot, find some time to speak with our sales team here. enables you to build the next-generation of cognitive applications. From bots to intelligent assistants, deliver something your customers will love.

About the author

Rachel Pautler

Helping developers build bots as smart as they are at

Ready to start?

Start trial
  • 14-day free trial, no credit card required
  • Includes advanced mobile & web chat UI
  • Unlimited custom flows and components
  • In-browser developer console with CLI access