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

Why helping Zurich win a British Claims Award is more than a win

3 min read

This month, Zurich Insurance UK scooped the Innovative Use of Technology award at the British Claims Awards  in London. This is one of the biggest recognitions for insurance professionals' work in improving the claims landscape for customers and a shining example of customer-focused innovation. As a product fanatic at Spixii, it helped us clarify what's really behind the win.

633b68a8-9f92-47d7-b594-fe95802bf586-original 

It was with great pride that the award for Innovative Use of Technology was snagged thanks to Zara, the chatbot designed and developed by Spixii for Zurich. Yet, the night of the British Claims Awards was more than a wonderful black tie dinner, with a glass (or two) of champagne.

It celebrated the past two and a half years of building Spixii from the ground up.

From an idea born from while talking to insurance customers to a tangible product, it affirmed its continuing relevance and business value for insurance.

Chatbots are here, and they are here to stay. What cuts the wheat from the chaff is the methodologies and frameworks with which they are made, and the features that make them so powerful. 

 

Beyond the hype

The hype around chatbots reached a peak around 2016. In fact, we wrote about it here in the Future of Insurance. When we first launched our concept at Startupbootcamp's Insurtech Demo Day in April 2016, we were inundated by calls from across the world. 

Many insurers saw this chatbot technology as a clear solution to the problems they were facing: you name it, there was a way chatbots could solve it - from poor customer experiences, expensive inefficient call centres, a loss of trust and spiralling customer acquisition costs. Companies across the board wanted to reduce costs while bringing their digital customer experience into the twenty-first century.

Insurance chatbots promised a win-win.

Then, many projects failed to deliver what they expected.

Some companies promised overnight wonders and off-the-shelf solutions, neglecting the fact that every insurer is unique. If there is one thing we have learnt since then, it is this.

Bespoke insurance chatbot solutions are not just a nice-to-have; they are a must. A pre-designed chatbot with dodgy natural language understanding (NLU) could spell disaster for an insurance customer trying to file a claim.

 

So what now?

Now the hype has deflated, we are entering the exciting part. We can now see the real business value of chatbot technology.

This blog post by Growthbot was brought to our attention by Dennis R. Mortensen of x.ai - a company that develops an AI-powered personal assistant, which schedules meetings for your customers and saves a tonne of time.

The post very succinctly shows how chatbot technology came, went and is yet to conquer. As Growthbot's Head of Growth, Justin Lee, writes:

The hype is over. And that's a good thing. Now, we can start examining the middle-grounded grey area, instead of the hyper-inflated, frantic black and white zone. I believe we're are the very beginning of explosive growth. This sense of anti-climax is completely normal for transformational technology."

As Dennis Mortensen says, "Despite how many perceive the tech world, future shifts do not emerge overnight. It's a slow evolution as the larger population determines what technology is useful, and what isn't."

 

So how can you get started?

Here are three tips to bear in mind as you start your chatbot journey.

1. Innovate, despite your legacy systems.

Legacy systems are often described as "a ball and chain" to incumbents. They carry enormous internal costs and are often not flexible enough to use new technologies, APIs and data sources.

Yet, while a blocker, this is certainly not an excuse. You can still innovate and provide a customer-centric journey. As Alex Last, Zurich UK's Continuous Improvement Consultant, says, "you just need to be savvy about it".

An elegant solution can by-pass your legacy systems or be designed and implemented alongside a long-term roadmap to replace or integrate with them, upgrading their capabilities and flexibility. Yes, integrating with legacy systems is painful. But a solid, high performing integration will set the foundation for you to adopt new customer experiences, and innovate and digitise continuously.

Thus, you are entering the world of dynamism, bringing a traditionally static industry into the agile future.

2. Have a fast go-to-market strategy in place.

It can be difficult to develop new products quickly, bring them to market, make changes and fine-tune them regularly with a dedicated team.

This is one of the ways working with an agile scaleup can help you save costs in the long-term. You are working with a team who are advocates for your success, have done it before and spent time in the Discovery phase to better understand you and your customers. 

3. Approach user experiences from a new angle.

There are often two approaches to chatbot technology.

The first is technical. From the major players like IBM Watson, Microsoft, Google and Facebook, as well as the smaller open source tools such as Raza, openNLP and Google TensorFlow, you can build a chatbot in minutes with natural language understanding (NLU). This technology is remarkable but in reality, only one small piece of the puzzle - particularly in the heavily regulated financial industry. Find out why here.

The other common approach is to use the chatbot to replicate human language. If we tossed the balance sheets, every customer could talk to a real human able to deal with their queries in a timely, compassionate and productive manner. Yet, getting a chatbot to talk like a human can actually be fairly confusing.

 

The Zurich Zara chatbot was our first implementation in claims. Its success proved that our expertise in the insurance sector coupled with methodologies is transferable across the insurance value chain, from lead generation to quote and buy, customer care, mid-term adjustments, renewals and claims.

Already, more than 300 customers have used it to file claims following the 'Beast from the East' storm this Spring. Ultimately, this award is one step closer to getting insurance more accessible, and helping get more people better protected. For more information on our project with Zurich, please check out our new case study page where you can find the latest client stories.

Zurich came, saw and conquered - now it's your turn.

Are you the next Julius Caesar, looking to lead the insurance industry into an era of digital transformation... without the grisly end?

 

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