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

Setting the new benchmark for digital customer experience in claims beyond the FNOL

13 min read

The following blog is based on an interview from Eddie Longworth, claims and supply chain transformation expert, to Gijsbert Cox, Insurance leader at Appian and Renaud Million, CEO at Spixii. The interview, conducted shortly after the solution partnership between Spixii and Appian, aims at exploring how both technologies are addressing the claims resolution process.


Many insurers and TPA feel that their digital transformation is complete when a web form is present on their website to execute the FNOL process. Yet, looking at the time spent collecting the FNOL, this is minimum. Once the information is received by a webform, the claims assessor will either put the information into the legacy claims platform or check if the information is correct to then process to the next step which is asking for more details to the claimant in order to assess the claim. Yet this request for new information follows a codified process which can be automated. A logic that can be applied to the claims update up to the payment.

Dubbed by our friends from InsTech as the bridge from legacy to Digital, low-code has compelling properties such as being able to sit on top of legacy systems and create a layer of powerful digital applications that can connect to other systems which is what Appian did with Spixii.

In this interview, I first start by asking Renaud, the CEO of Spixii who started in London in 2016 to update us on the development of the conversational process automation platform which focused entirely on the insurance industry. Then, I turn to Gijsbert Cox, Insurance leader at Appian to understand more about the landscape of low-code platform providers and see.

Spixii and Conversational Process Automation

EL: Your collaboration with Appian seems to mark a new chapter in the development of your chatbot technology. Tell me a little about how you have been developing chatbot applications in the insurance market.

RM: Insurance products have always been extremely valuable for individuals and companies to protect their belongings, lives and activities. Yet, buying and using an insurance product remains difficult for the majority of people. To counterbalance the complexity of insurance products, insurance professionals sell and service policy covers via conversations, let it be face to face or over the phone. Some insurance companies sell directly to consumers using web-from on their website but the performance in terms of conversions rates is nowhere near what can be achieved with a conversation. Indeed, a webform is a basic one-way data capture tool and cannot compete with a professional human conversation. This disparity of performance can be observed across the whole value chain with renewal, mid-term adjustments, first notice of loss, claims update and settlement. Spixii is addressing the gap created by poor digital capabilities of web forms and performant analogue conversations. The Spixii platform allows insurers to keep the personalisation and professionalism of conversations and to apply it digitally online and at scale. One key success factor of these conversations are the tight integrations between the Spixii platform and insurance systems such as policy, billing and claims systems. The data sit in these systems and Spixii white-label chatbots bring this information straight to the policyholders or prospects to self-serve and make an immediate informed decision to buy, to renew or to claim. Thanks to the growing volume of relevant information available online, individuals are becoming savvier to decide what is best for themselves. Spixii platform is allowing insurance professionals to free time by letting consumers interact with insurance processes directly. Consumers will always seek for human touch for needs that cannot be solved easily meaning that the Spixii platform performs best on well-defined processes that can be more performance when automated. We call it conversational process automation or CPA. We wrote extensive literature available at


EL: Spiixi has chosen to focus on the insurance sector. Why is that? There is a big wide world out there where your technology could be adapted and implemented.

RM: Insurance is our domain of experience and expertise. I spent all my professional career in insurance starting first as a non-life actuary consultant working across specialty and retail. It is by breathing and living the intricacies of the industry that I found a problem big enough to solve that it can make a difference on the performance of insurance companies as well as giving better customer satisfaction. I then co-founded Spixii to help individuals to get better protected by accessing and using their insurance cover easily. It is true that the Spixii CPA platform can be applied to other industries such as banking and utilities. The feedback of the market has been really positive about our specialisation in insurance and this is often what sets Spixii apart from industry-agnostic chatbot platforms that struggle to execute high-value insurance processes in a digital conversation. Delivering performant digital conversation means integrating with insurance systems. This is complex to do as expertise is required in compliance, data security, architecture and systems performance. Orchestrating all these connections in a fluid and simple conversation to use is very difficult with a non-expert platform. Like most of the jobs in the insurance industry are performed by experts, the same applies to this type of technology. Executing customer-facing insurance processes remains a matter of expertise.


EL: This latest collaboration with Appian is specifically focused on the claims sector. What makes this sector appealing and potentially rewarding for you?

RM: The insurance market is really transforming in claims. Most of the staff and activities for insurers are in operations and claims which naturally give rise to continuous improvement of processes. Like quote & buy journeys, claims journeys are following the same path. Traditionally executed over the phone only, webforms made their apparition to capture the information at the FNOL. However, insurers realise that information is often missing from this initial capture and they wish to have asked these two or three additional questions to the claimant while he or she was filling the form and avoid chasing later. It is a great point in case of keeping the use of a conversation to execute customer-facing insurance processes. Large insurers often have multiple systems which tend to be a mix of very old legacy, modern legacy on-premise and cloud-native platforms. These systems and platforms are very good at creating claims records but not so at creating claims processes. Appian Connected Claims provide this upper layer gathering all the data in one place for business analysts and claims teams to create powerful claims processes. Integrated with Appian Connected Claims, Spixii Claims enable meaningful and immediate conversations with claimants and communicate in two ways with Appian. For example, someone could log a claim, be identified and the Spixii chatbot will ask smart questions such as did the claims happen at the same address at the property on the policy requiring the claimant to simply say yes or no without having the need to enter the whole address. Then, more complex processes can be done which gets very interesting. For example, someone can interact with the Spixii chatbot, get identified and ask for a claim update, the chatbot will then pass the request to Appian and Appian will return the information. There is no time wasted on a call or email to get this information. The claimant enquiries have been answered, logged into Appian and customer satisfaction KPI such TNPS can be recorded so that claims handlers can see its evolution with time and intervene if it drops beyond an acceptable level of service.


EL: More broadly, how do you find the insurance sector responds to the opportunities available through your technology? Insurers are notoriously risk-averse and I’m wondering what the barriers are that you encounter when talking about the work that you do.

RM: Doing innovation in a risk-averse industry is very hard, yet understandable. Insurers react positively to the insurance solutions Spixii has to offer. But in order to get such reception, we work really hard on our compliance processes. For instance, every conversational process created is available in a testing environment when it can be versioned before approval to go live in the production environment. Everything is tracked in logs. On top of this, Spixii is certified in information security management with ISO 27001 and we go through an audit every year. This level of compliance is mandatory to engage with the stakeholders running the operations of insurance companies. The same applies to the analytics generated by the conversations held with the chatbots. The Spixii platform provides unique conversation analytics used for continuous improvement. It is like listening to someone guiding a client through a process and analysing carefully what is being said in order to improve it for the next interaction with the next client. This information has to be granular enough to be actionable yet personal information has to be anonymised so that identity is preserved through any point of data or several points of data.


EL: Paint us a picture of where you see your chatbot technology developing and being applied during the next 5 years.

RM: Like every new technology, chatbots were hype in 2016 and 2017, went through the peak of delusion and are now getting momentum. The fact that Spixii was born in 2016 and is still here today with active collaborations with large insurance companies is a sign that this technology is here to stay. Like the trajectory we took in the last three years, specialisation is key. By focusing on the insurance industry, insurance customer-facing processes, compliance and security, we made the chatbot technology meaningful and impactful for insurers using conversational process automation. Automation is the key driver of digital transformation with RPA having led the way the last 5 years. Much has been done in the back and middle office and much is left to do in the front office. This is where we see a lot happening. Combined with new insurance products and constantly evolving consumer behaviour, the need for personal conversations online can only increase, and conversational process automation is a prime candidate to fill this gap efficiently.

Appian and Connected Claims

Now moving from the front-end of the process to the assessment of the claims, from the claimant to the case management, let’s explore how Appian is gaining territory in the insurance industry by building industry-specific applications that are flexible and fast to deploy.


EL: What makes this collaboration with Spixii an attractive proposition for you?

GC: As Renaud pointed out our Appian Connected Claims (ACC) solution brought us together. And combining Spixii with ACC creates a positive synergy for the insurance company. Let me explain that further. The ACC solution enables insurers to unify data from their existing claims, policy and related insurance systems and databases into a single 360-degree view. The key benefits for an insurer include a superior customer experience, complete control of the e2e claims process, and powerful configurability - delivering faster claims settlement - along with speed to implement, accelerating time to value. With that, the solution targets improved customer service for the insurer and reduces claims leakage since the insurer is more in control, can automate where needed and make the claims processes more efficient.

Spixii provides an additional channel for the customer to communicate with the insurer and adds value to the ACC proposition. Connecting Spixii to ACC which has all required data related to the customer and the claims file, gives more power to the chatbot conversation. The chatbot conversation becomes more meaningful for the customer. It can not only capture a claim mimicking a digital form, it can also check for missing information, or spot that a complaint was raised earlier or provide an update. Then it becomes more interesting for the customer to use and avoid the need to call the insurer.

Appian has a lot of automation capabilities in the platform, such as BPM, case management, RPA and AI, but the chatbot functionality is not part of our platform hence adds value. Appian collaborates with more intelligent contact centre capabilities and likes to work with the best of breed in the insurtech market, hence this was a logical partnership.


EL: The ‘low code’ technology market is becoming pretty crowded. What makes Appian stand out from the crowd?

GC: Appian is leader in automation and low code technology. It provides complete automation capabilities for enterprise workflows. We differentiate ourselves because the Appian platform orchestrates your people, systems, data, bots, and AI in a single workflow. Gartner calls this “hyper-automation”. It is not just about RPA or AI only. The combination of these digital workers with humans in one workflow makes modern automation powerful.

And at our customers, we bridge the gap with business and IT because of the rich UI and easy building capabilities. We enable business users to manage all their key data and processes through one engagement layer being Appian. Also, once an application is live, it can be easily changed. With Appian, it remains low code at all times. That makes our customers very agile and able to respond to change quickly.


EL: Tell me a little about the broader strategic objectives of Appian in the insurance market.

GC: Insurers have grown organically and through acquisitions, and with that built and collected various systems. Also, traditionally insurers have organised themselves around products and different departments for products, claims and accounting. This has created a very siloed IT architecture with dispersed data. The growing need in the market due to different customer needs, higher regulation and different business models is to move away from those silos. However, that is not easy, and replacing legacy systems only is too complicated. Insurers need a platform to unlock this data and provide innovation quickly. Appian is supporting the insurance industry with that since it has the flexibility to integrate quickly without the need to migrate the data. It brings speed and agility to insurers and allows them to connect to external data, ventures, communities and insurtech such as Spixii. More information on how we support the insurance industry can be found here:


EL: What do you see as being the barriers to wider adoption of the ‘low code’ approach in the insurance market?

GC: As with all new things, adoption requires an open mindset. People need to see there is an alternative to high coding, and this is taking place across all industries now. Simply because we cannot code all our automation needs anymore in the old way. Analyst firms have already done research on this and by 2021 more than 65% of all application development will be done on low code. Of course, there are barriers when this open mind is not there, but I think these will be forced to re-think and change their tactics quickly if they want to remain competitive in the market.


EL: You have a specific focus on the claims sector with your Connected Claims solution. Tell me a little about that and why you feel the claims sector is attractive for your technology

GC: There are several reasons for focussing on claims. First, claims handling can be very complex. There are several parties involved: the claimant, third parties, experts and an intermediary to mention some. And as often said, handling a claim is the moment of truth for an insurer. That is when they can shine and explain to their customer, often in distress at that moment, why they have an insurance policy. If you get it wrong as an insurer, that is also the moment that you will lose customers, and it is more costly to win them back then to keep them. And lastly, we want to support insurers to pay claims correctly and with speed, and with that save costs. Claims leakage is an issue at a lot of insurers and we want to reduce it by providing a complete automated and connected view on the claims processing.

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
Spixii White Paper

Download your FREE Spixii White Paper copy

Discover how to execute high-value processes sustainably. Included in the White Paper:
  • Expanding propositions with digital
  • Conversational Process Automation (CPA) deep dive
  • De-risking the transition to automation