Siva S, CEO of Powerupcloud, Global Cloud Practice Head at LTI
Before I start, I sincerely hope you and your loved ones are safe and well.
There are no doubts that COVID-19 Pandemic has brought great distress to our lives, both in the personal and business front. We see businesses, governments, large corporations are reeling from the effect of lockdowns and COVID-19 spread. Over 90% of the businesses worldwide are suffering due to the lockdown. But the tech industry, especially Cloud and AI are seeing a very different trend. Businesses are realizing that they cannot ignore Cloud and AI anymore and with each day passing, they start feeling more and more pain with their existing traditional IT systems.
In today’s article, I would like to focus on the Contact Center AI solution which is currently the #1 sought after technology on the cloud for businesses across the world.
In 2016, I envisioned a Chatbot platform named IRA.AI (now called Botzer.io) as a customer support chatbot which will automate the customer support process by interacting with customers and provide them with answers in real-time. I must admit that it was a super-hard sell back in 2016. We were one of the first to build a robust chatbot development and management platform, well before AWS & Azure launched their versions. We used Python NLTK to power our chatbot platform. Fast forward to the second half of 2019, the scene wasn’t very different. We still saw a majority of businesses experimenting but not fully adopting the AI Chatbot solutions.
But the COVID-19 Pandemic has changed this situation overnight, very much like how it changed a lot of our lives in a very short time. We are seeing the customer care calls going over the roof since January 2020. One instance where the US citizens applying for unemployment benefits had to wait for almost 48 hours to get through a customer support agent. Another instance where a UK based Telco experiencing a surge of 30% increase in the incoming customer care calls as a lot of their users were struggling with internet bandwidth issues with most of the population started working from home. While the large BPO industry in countries like India and the Philippines were struggling to get their employees working from home, some of the US and UK businesses have canceled the contracts and moved the jobs back to their respective home countries in order to comply with the regulations around data security. This has invariably increased the customer care spend for these businesses.
All these have resulted in businesses looking towards AI Chatbot powered digital agents to help them cope up with the surge in demand and at the same time, keep the costs in check.
How was the AI Chatbot adoption before 2020?
As I mentioned earlier, AI Chatbot concept was seen more as an R&D investment rather than a viable solution to automate the customer care center operations. We saw some early success with insurance companies, banks, airlines, and real-estate companies. But it was always a hard sell to the majority of the businesses primarily because of below reasons,
- the existing customer care support process was reliable and relatively cheaper when outsourced to countries like India, Philippines
- there was more emphasis on customer loyalty management, providing the human touch
- the Natural Language Processing (NLP) technology was not very evolved and fool-proof to be considered as a real alternative
- the demand was predictable and the training materials were designed to train humans and not AI
But, several technology companies like us have been relentless in their efforts to solve the above-mentioned problems seen with AI Chatbot technology. The NLP accuracy has improved a lot (proof: Alexa, Google Home, Siri) and the leading cloud platforms have launched these NLP techs as full-fledged services for developers to integrate them and build end-to-end AI Chatbot solutions (Amazon Lex, Microsoft LUIS, Google DialogFlow).
How does the Contact Center AI actually work?
- The customer calls the customer care support number
- The contact center software, once it receives the call, will check with the internal customer database (or CRM) to identify the customer
- The contact center software will then route the call to the workflow tool which will interact with the customer and identify the entity & intent from the customer’s query
- Based on the preset business logic (or algorithm), the workflow tool will then call the right set of application APIs to resolve the customer’s queries or pick the appropriate response from the AI Chatbot
Below is an architecture diagram that depicts a Contact Center AI implementation on AWS using Amazon Connect (cloud-based contact center software), Amazon Lex (cloud-based NLP service), and Amazon Lambda (cloud-based workflow service).
So how do you go about AI adoption for your Contact Center AI?
Rome was not built in a day. So is the case with your vision of bringing in AI automation for a large part of your customer care process. Projects in this space would fail and leave a bad taste if we embark on this journey with very high expectations and immediate results. And I have witnessed the pain several times from close quarters. So how does one go about adopting AI for their contact center?
Step 1: Analyse your existing customer care process and identify the low hanging fruits which can be moved to the AI model quickly (almost all AI Chatbot consulting & product companies can help you with this).
Step 2: Segregate the queries and workflows which can be handled by a simple ‘if-else’ rule vs an ‘intent-entity’ identifying the NLP model. Using NLP for queries that can be handled by a simple ‘if-else’ rule will be an overkill and will bring down the accuracy of your NLP engine.
Step 3: Once you have experienced a fair amount of success with the NLP powered model to identify intents, entities in answering customer queries, bring in Machine Learning to further improve on the accuracy of intent identification, bot training, and customer experience management. Yes, there is a whole different world out there already in the field of Contact Center AI. 🙂
Why AI chatbots win over application design?
I often get this very common question on ‘why chatbots when you have beautifully designed applications which can do the job?’. I totally agree with the fact that the apps with better UX will make a customer’s life easier. But the problem with apps is that you will have to adhere to workflow which has been designed in the app. You cannot skip any step, you cannot change your inputs as you wish. The AI Chatbot however allows you to interact the way you would interact with a human and not a machine. You need not learn to use an app (though the learning curve may be less for better-designed apps), you can simply post your query and get your answers or post your intent and get the workflow executed (like policy claims, refund processing, airline reservations, blocking credit cards, etc).
Let the customers interact with your business in their natural way. AI Chatbots allow you to achieve that and this goes a long way in customer experience.
What should customers look for while choosing to embark on this path?
Building and launching your Contact Center AI solution powered by chatbot agents is just the first step. I see a lot of customers struggling with managing the bot they launch and further improve them on a continuous basis. This leads to a low customer satisfaction rating and eventually resulting in a failed project.
Any business looking to implement Contact Center AI to automate their customer care process should consider below check-points.
- Check if a solution like Contact Center AI will actually improve efficiency and bring down costs. If your existing support model is broken, do not embark on this before fixing the overall support process.
- Choose a bot management platform (like Botzer.io) which will not only help you with building and launching the AI chatbots which will power your contact center, but also help you track the performance of the bots closely.
- The bot management platform should allow you to pick up anomalies and help you train the new queries quickly.
- The bot management platform should also allow the Contact Center AI solution to handover the call to a human agent if the bot fails to resolve the customer’s queries.
- And the most important part, the bot management platform should have rich analytics embedded in the tool which will allow you to track your customer experience score on a real-time basis. This will help you course-correct in your bot training process and will prevent you from experiencing negative reviews in your customer care process.
How will this evolve in future? Will the Contact Center AI replace humans?
No. The Contact Center AI will not replace humans entirely. A healthy model will have a good mix of AI chatbots and human agents working hand-in-hand to support the customers’ queries. The below architecture is highly recommended when you are looking to implement a Contact Center AI for your business.
I am seeing an increase in Contact Center AI adoption from businesses in industries including insurance, food delivery, e-commerce, healthcare, airlines, telco, banks, etc.
If you have been mulling with the idea of introducing AI into your businesses, the time is here for you to initiate the AI adoption. I would suggest you start with the Contact Center AI solution. It works. And it is one of the mature AI solutions that you can adopt.