How artificial intelligence (in particular LLMs) can assist agents in the contact center
Author: Geouffrey Erasmus | Date: 26/05/2023
There is an incredible amount of hype around artificial intelligence (AI) right now. Plenty of it justified, and plenty more that is not.
Daily, I see a large volume of fearmongering on LinkedIn about how AI will consume 80 percent of jobs. Equally, huge swathes of people embracing AI and offering tips on how to use it most effectively.
As we welcome services such as content generators, website builders, image creators, financial strategists, and code builders etc. into our lives, it’s easy to be overwhelmed.
The pace of change is truly astounding.
But, crucially, as with pretty much anything in life, it’s how AI is harnessed that will determine its impact and effectiveness.
Below, I’ve explored how artificial intelligence is impacting the contact center. In particular, I’ve looked at the use of Large Langue Models (LLM), such as ChatGPT, and how they can assist the agent and operational team, driving performance improvements.
I’ve outlined actual use cases that generative AI can support and look at what’s next for contact centers who embrace AI.
From cost center to profit center
Contact centers have been under immense pressure for some time.
It is widely accepted now that the experience you give customers is a differentiator for your brand and can provide a competitive advantage in a highly commoditized society.
And yet, contact centers are a large drain on resources – something senior management doesn’t like. And are therefore often starved of investment.
Layer in other challenges faced by the contact center, such as;
- Difficulty hiring and keeping agents
- Legacy infrastructure, systems and processes
- Lack of performance insight
- Poor mental health of agents and staff
It starts to paint a very challenging picture.
To try and tackle some of these challenges, progressive contact centers are turning to artificial intelligence for support.
Automating repetitive and mundane tasks. Summarising large volumes of information in seconds. Categorising, filing and coding information that can be retrieved in the future.
All these things have become a reality. Especially with the use of Large Language Models.
Large Language Models and the contact center
Many of you will have given a LLM, such as ChatGPT, a go recently. Feeding in prompts, usually in the hope of an amusing answer.
Businesses too are getting to grips with LLMs to perform a wide variety of functions, especially given the advancements made in where and how they are hosted and data retention policies.
There are two core areas of the contact center than can be supported by LLMs:
- Agents – automating repetitive or time-consuming tasks, such as summarizing a call, or summarizing previous customer interactions to help them solve the issue more quickly
- Operational teams – accelerating performance insights, for example, asking the LLM to read a transcript and mark performance against a scorecard
You can quickly see that the potential is fairly far-reaching.
Any job that is currently manual in nature, involves large amounts of data, or is a time drain can likely be replaced or supported through the use of LLMs.
How Large Language Models can support contact center agents
Below, I’ve outlined some immediately obvious agent support use cases for LLMs.
Call Summarization – Call transcripts are clunky things, especially if the agent has been on a long customer engagement. If a new agent picks up the conversation, then information is often lost, or there is a time delay while the new agent gets up to speed.
Summarizing call details, therefore, using support from LLMs has multiple benefits:
- Agents can instantly be brought up to speed without having to read the full historic interaction transcript
- Operational teams don’t have to listen to long recordings to find information
- Call summaries can be shared with customers as evidence their query has been taken seriously and the previous details are correct
Quality Assurance (QA) – Often still a manual process in many contact centers. QA is the core performance benchmark systemin use today. Automating this process offers clear benefits:
- QA teams spend less time manually listening to calls and more time making performance improvements
- Scorecard completion can be automated – The LLM can ingest the transcription and the performance criteria and tell you how well agents have performed
Call Classification – Still a major challenge for contact centers and a resource drain to manually fix when calls and wrongly classified.
LLMs can be used to read the call transcript and decide, with a high degree of accuracy, how the call should be classified.
Access to Knowledgebase Articles – Agents waste a large amount of call time looking for information to assist the customer.
Through the use of LLMs the agent can ask a question and receive a real-time answer collating information from their (normally vast) knowledgebase articles. Saving time to reach the correct answer.
Talk to the team to see how AI can help your contact center
What I have discussed above is just the tip of the iceberg when it comes to the use of AI and LLMs in the contact center.
Every week I see new use cases and opportunities to leverage this new technology.
If you’d like to discuss how AI can support your contact center operations, then contact the team today.
Found this interesting? Look out for our next two articles in our AI series.
How to configure Intelligent Agent to use it with ChatGPT
How call summarisation will work in practice