Companies use Amazon Lex in AWS to design conversational chat bots, like the bots which power Amazon Alexa. This integration allows Genesys Cloud to call Lex chat bot actions in Architect call, message, and chat flows.

  • Setting your HTTP Proxy on an Edge does not work with this integration. You must allow outbound network traffic from the Edge to the regional DNS entries on TCP Port 443. For more information, see Domains for the Firewall allowlist.
  • The Amazon Lex V1 integration does not support DTMF. If you want to use DTMF, use the Amazon Lex V12 integration. For more information, see About the Amazon Lex V2 integration.

Amazon Lex uses Natural Language Understanding (NLU) to interact with a user speaking conversationally. With the evolving functionality of artificial intelligence tools such as Alexa, Siri, and the like, conversational interactions with computers have become mainstream. Contact centers are a natural progression into this world of virtual assistants.

When a customer can speak naturally, your company can better understand the customer’s intent and then more quickly route the call to a highly skilled agent. The AWS Lex Bot integration within Genesys Cloud enables customers to use NLU within inbound synchronous customer interaction flows.

During a call, the customer uses NLU to obtain the information and assistance they need without involving an agent, or they get to an agent easily. The bot provides the following capabilities:

  • An Edge appliance feeds utterances to Lex. Natural Language Understanding derives the intents and slots. If these terms are unfamiliar, refer to the Amazon Lex documentation.
  • The customer’s response is streamed to AWS Lex for processing. AWS Lex recognizes the intent, understands its meaning, and captures key information into slots. Lex passes these slots back to Architect.
  • When necessary, the flow connects the customer to a live agent.
Note: In an Architect inbound call flow that calls an Amazon Lex V1 bot, make sure to choose the same TTS engine and voice that you configure in the Amazon Lex V1 bot.

Example use case

When a customer interacts through Architect IVR, the Lex bot begins. The system asks the customer an open question, such as “How may I help?”.

After the customer responds, Lex attempts to interpret the intent of the request and then decides the next step. For example, if the customer replies, “I want to check the status of my flight,” then Lex prompts the user for a flight number and returns the flight status.

If Lex cannot establish or understand the customer’s intent, the system routes the call to an agent.

After the task ends, Lex asks if the customer needs any additional help. The customer can ask another question, request to speak to an adviser, or indicate that no further assistance is needed. If the customer needs no further assistance, the call ends.

If the customer chooses to speak or chat with an agent but faces a long wait-time to reach an agent, or the request is outside normal business hours, then the IVR routes the call appropriately.

For more information, see About the Amazon Lex integration.