Targeted generative AI from merged communication transcripts

A system comprising:

• memory;
• and
• one or more processors coupled to the memory, the one or more processors configured for operations including:
• facilitating a voice bot segment of a two-way communication session, wherein the voice bot segment is between a customer device and a non-human bot agent;
• facilitating transfer of the two-way communication session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue;
• accessing survey data describing the two-way communication session, wherein the survey data includes post call data from the customer device including an evaluation of the human voice segment;
• automatically generating a merged transcript in real-time as the voice bot segment and the human voice segment occur, wherein the segments are automatically and separately routed to generate the merged transcript, and wherein the merged transcript includes a transcript of the voice bot segment, a transcript of the human voice segment, and the survey data;
• automatically processing the merged transcript associated with the two-way communication session to identify language data associated with resolution of the customer issue;
• and
• dynamically updating the non-human bot agent using the language data.

A non-transitory computer readable medium comprising instructions that, when executed by one or more processors of a system, cause the system to perform operations including:

• facilitating a voice bot segment of a two-way communication session, wherein the voice bot segment is between a customer device and a non-human bot agent;
• facilitating transfer of the two-way communication session to a human agent device as part of a human voice segment of the two-way communication session, wherein the transfer occurs following a failure of the non-human bot agent to resolve a customer issue;
• accessing survey data describing the two-way communication session, wherein the survey data includes post call data from the customer device including an evaluation of the human voice segment;
• automatically generating a merged transcript in real-time as the voice bot segment and the human voice segment occur, wherein the segments are automatically and separately routed to generate the merged transcript, and wherein the merged transcript includes a transcript of the voice bot segment, a transcript of the human voice segment, and the survey data;
• automatically processing the merged transcript associated with the two-way communication session to identify language data associated with resolution of the customer issue;
• and
• dynamically updating the non-human bot agent using the language data.