How to use CAPTCHA in a conversational interface?

In today's digital world, robust authentication mechanisms are an absolute necessity. With the increase in cybercrime, it is essential to protect personal and sensitive information. As stated in the last OWASP 2023 Top 10 Vulnerabilities report, authentication mechanisms are the first line of defence against unauthorized access to online accounts. Furthermore, the new ISO 27001:2022 certification standard dedicates specific controls and clauses to ensure secure authentication procedures.

A robust authentication mechanism is the key to unlocking a great number of self-services. For example, making financial operations, changing insurance policy details or consulting medical test results are operations that individuals can perform online if they pass a strong authentication screening.

However, there are situations where robust authentication mechanisms are not possible. This is the case of quote&buy journeys, where customers are not registered and identified apriori, but also when agents and advisers are about to request some actions on behalf of their clients.

In such cases, the list of self-serve services experiments a physiological reduction because some critical actions won’t be accessible to an unidentified user. Reducing the risk of robots and Denial of Services attacks is also important by using additional security measures like CAPTCHA codes and other techniques.

CAPTCHAs, in particular, are a popular security measure used to prevent automated attacks by requiring users to prove they are human and they nicely fit conversational interfaces. A handy-style text over a noisy background is generated and displayed to the user as an image. Automated Optical Character Recognition (OCR) detectors won’t be able to easily guess the keyword by reading the image.

The main three requirements for a good CAPTCHA code generator are:

All Posts

How to avoid chatbots' failure with Conversational Process Automation

4 min read

If you aren’t already using them, then you would’ve definitely heard of chatbots by now. Along with Artificial Intelligence, they became the talk of the town around 2016 in insurance as in other industries. Recently, you might have heard of the term CPA (Conversational Process Automation). 

What is the difference between CPA and chatbots, though, and how are they linked to each other? Let’s explore.

 

What is a chatbot?

A chatbot is a computer program that simulates human conversation through voice commands or text chats or both. The term "ChatterBot" was originally coined by Michael Mauldin in 1994 to describe these conversational programs. Since the 80s, insurance businesses have always interacted with their customers through different channels, such as phone, email, forms. Chatbots can be seen as an alternative interface between a brand and its customers with the potential benefit of 24/7/365 availability at a fraction of the cost.

A chatbot can be applied to various use cases across the insurance value chain, such as quote & buy, policy administration, claims, or customer service, and is judged upon the quality of the conversation. By the quality of the conversation, we mean the ability of the bot to manage customer requests and to fulfill those requests satisfactorily. The most advanced or “intelligent” chatbot can fail to meet customer needs when lacking a useful goal, which is usually a simple task. It’s like dealing with a nice and kind receptionist that is appeasing you with words while you have a specific need that the receptionist cannot address; it’s all empty talk.

 

How are chatbots linked with CPA?

For customer-facing processes that are critical to generating high business value, chatbots that rely solely on conversational AI and primarily focus on the management of conversations between a human and machine are insufficient. In other words, the generalist Natural Language Understanding (NLU) skill of the chatbot is not the best tool to execute a conversation requiring integration with other systems.

This is where CPA comes in. CPA puts an emphasis on processes requiring integration and advanced business logic, oftentimes customer-facing processes. The aim is to keep interacting with users through an intuitive and personal front-end solution whilst allowing the customer to self-serve in a business process. This isn’t possible with a generic chatbot or a web form. Phones and web chats aren’t feasible either because of the time they take. In other words, CPA augments chatbot capabilities to enable a personal conversational experience into high-value processes at scale and execute tasks that a human would normally do.

On top of this, CPA is powered by a platform designed to analyse conversations and data captured by the chatbot in order to generate knowledge and insights about the critical performance of the process and about the customers subject to it. For example, CPA platforms can highlight which type of customers are selecting a particular coverage option, which time of the day customers are engaging the most, which are the most recurring requests, and where customers dropped the conversation. 

The platform often includes machine learning capabilities to enable continuous improvement. It means that CPA is powered by AI but with different technical skills than conversational AI, as the focus is more on the optimisation of the business performance instead of the conversation itself. In other words, “intelligence” is applied to generate insights based on real customer data- both demographics and behavioural- that inform businesses over the changes to be made in the process, or in the chatbot conversation itself.

 

A practical application from the world of insurance

When applying CPA to a claim process, an expert chatbot is implemented within the insurance company website and manages conversations with customers 24/7/365. The chatbot is linked with the insurer’s policy system and can authenticate the customer. The customer gives all the information related to the claim, including visual documentation (e.g. photos or videos). 

The chatbot is able to open claims within the insurer’s systems. It can also recognise simple and low-value claims to “fast-track” and potentially settle them with or without human supervision. 

Through the CPA platform, insights are generated and conversations can be analysed at a granular level: how many people went through a particular conversational path, which type of customers completed a transaction, etc. The conversational experience can then be iterated according to such data-driven insights. For example, the data can show if customers spend a lot of time at a particular point in the conversation. This might hint that the message at that point is unclear and needs to be rectified.

The implication of this is that in the future, insurers will be able to route complex claims to humans, simpler ones to touchless journeys, and possibly extend the conversation with a group of customers to offer additional information or services.

 

In short, CPA is the solution designed to enhance customer-facing processes by ensuring the effectiveness of chatbot conversations. With rising customer expectations, it is not enough for companies to deploy digital solutions; they must be integrated within the existing system for a smoother customer experience and net ROI for the business. CPA can hit both birds.

Recent Posts

How to use CAPTCHA in a conversational interface?

In today's digital world, robust authentication mechanisms are an absolute necessity. With the increase in cybercrime, it is essential to protect pers...

Read more

The sweet spot between smooth operations and customer experience

3 min read Gone are the days of interactions where customers and businesses would have to come face-to-face for a transaction. Thanks to the mighty po...

Read more

How can customer service operations save money?

5 min read Efficient and effective customer service operations can significantly impact a company's finances. By providing customers with prompt and a...

Read more

What are the 3 steps to reduce the stress experienced by customer service consultants?

5 min read As a customer service consultant, many factors can cause stress and anxiety in the workplace. One of the biggest causes of stress is dealin...

Read more
2024 Spixii WP - How to deliver expert customer service immediately, consistently and around the clock

Download your FREE Spixii White Paper copy

Discover how to deliver expert customer service immediately, consistently and around the clock:
  • Key KPIs that make or break
  • Making compliance teams happy
  • De-risking the transition to automation