ABSTRACT

Artificial Intelligence is the filler between Human and

Machine interaction and it is the future.

Subhajit Saha ( Cognizant ) Ajoy

Sinha (Cognizant)

UNLOCK THE POWER OF AI

IN UX DESIGN
Next Gen UX Design
"ARTIFICIAL INTELLENGENCY IS
GOING TO CHANGE THE WORLD
MORE THAN ANYTHING IN THE
HISTORY OF MANKIND. MORE
THAN ELECTRICITY."
PHYSIOLOGICAL PHENOMENON
IN UX DESIGN
User Interface design is closely related with human psychology, specifically,
Social, Behavioral and Cognitive psychology. User experience (UX) is a  person's

sentiment and outlook about using a product, system or service.

To become a true user interface, it must have user emotion and intelligence
Capture capability and react accordingly.
Artificial Intelligence is the game changer to understand Human Physiology and

redefine user interaction with System. Few Physiological phenomenon to consider

about UX are as below.

 UX is a human information processor to interact with machine

interface

 UX is unique to an individual

 UX is closely connected with social culture

 UX is prejudiced by previous experience and current mental state

 UX is context specific and dynamic

Always organize elements of information in categories no larger than 9, but preferably ~5
chunks.

The more chunks of information you add to an ‘interface’, the more difficult it becomes
to ‘work’, using the information at hand. This is especially critical for first time users,
because they haven’t had the ‘practice’ needed to encode the interface into long term
memory, or, for the behavior to become habitual.

User experience design has its conceptual roots in cognitive and behavioral psychology
and it is a blueprint of a human being’s interaction with a machine. No matter how
smart and advanced machines get, the user will always operate it with the human mind
that has some fairly unbreakable patterns and you can use these patterns in your favor
to create the right user experience.
 POWER OF THEORY OF MIND AND
ARTIFICIAL INTELLIGENCE
“Theory of Mind” (ToM), as described by AI Goldman [1]:

‘Theory of Mind’ refers to the cognitive capacity to attribute mental states to self and others.
Other names for the same capacity include “commonsense psychology,” “naïve psychology,” “folk
psychology,” “mindreading” and “mentalizing.” […] How do they [people], or their cognitive
systems, go about the task of forming beliefs or judgments about others’ mental states, states
that aren’t directly observable?

Theory of Mind (ToM) is a key factor of social cognition. In cognitive psychology, the term
“ToM” define set of processes / functions of the human behavior that let an individual to have
characteristic of mental states to others. A machine equipped with Theory of Mind AI will
better recognize the entities it interacts with.

To achieve this, it will need to discern the needs, emotions, beliefs, and thinking of the
individual. This isn’t easy since computers will need to understand that human beings have a
mind, which might have been conditioned by several factors.

“ToM” can have following characteristics

 Computers equipped with Theory of Mind AI will infer the objectives of entities around
them from visible cues.
 Theory of Mind AI-powered systems will be able to simulate the consequences of their
actions.
 A robot/system equipped by Theory of Mind AI should be able to understand the intent
of another similar system.

Social interaction that understands human social dynamics and moral norms, can be truly
integrated with our social life showing empathy and natural social actions. Theory of Mind AI will
Artificial Intelligence has gone from being a figment of fiction to reality in a matter of
years. Machines that could think like humans were an excellent plot for a thrilling
storyline. However, in recent times, it has transitioned from fiction to reality- we are
living that Artificial Intelligence future. People are using AI technologies in their
everyday lives, and somehow it has become an integral part of their daily rituals. From
asking Alexa/Siri to tell you the time to get them to plan your next grocery delivery, you
are carrying AI into your daily routine.

AI is offering personalization to users. As a customer, you may need a different solution

than someone who is residing with you. Your needs are different, and so are your
thought processes. This is when AI can help you. Understanding how you work, what
kind of products you use, and how you conduct your daily lives, the intelligent machine
can process a solution that works best for you and this makes life so much easier!

The best example of how this has impacted the current society can be seen in the e-
content viewership during the pandemic. For a while, when the theatres and all other
forms of outdoor entertainment remained shut, streaming platforms such as Netflix
were on the rise. People subscribed to these platforms to keep themselves entertained.
 USER JOURNEY MAP WITH
ARTIFICIAL INTELLIGENCE

Understanding people and what they’re trying to achieve is a key part of a

solid design process. Mental model diagrams are a powerful way to achieve
this, as they help you map people’s experiences in-depth and in a scalable way.
User Journey

User journey map is a model. It’s a diagram of all the interaction points
through which user come into contact with interface.

It examines the story of how a customer relates to the business, brand or

product over time. As you might expect – no two customer journeys are
identical. However, they can be generalized to give an insight into the “typical
journey” for a customer as well as providing insight into current interactions
and the potential for future interactions with customers.
User Journey Data flow is depicted as below

User Journey with Artificial Intelligence

Artificial Intelligence (A.I) powered systems have made it possible to predict possible
paths consumers might take. A.I systems that are continuously learning and adapting
to latest user context can radically transform how a system engages with them by
assisting them with timely predictions and surfacing hidden intents from the sum total
User Journey enhanced using AI / ML integration

Define User Journey Map using Artificial Intelligence and Machine Learning as below
Many forward-thinking companies have already started deploying AI tools. E-Commerce
companies is already launching an AI system for increasing sales. Intelligent AI system
knows (by analyzing your buying habits) when you will be running out

of a consumable product. It automatically places the order for you. AI uses machine
learning to understand the data and context in order to predict (or identify) certain
customer actions and questions. AI is used by companies that have recognized the value
of anticipating the customers’ needs, therefore reducing any additional effort from the
client.

AI is reducing user journey path by automating few interaction points by analyzing

buying habits
 Algorithm Driven Design – extending
Domain Driven Design

Domain Driven
UX Design & With machine learning support, artificial intelligence
help designer to construct a layout, prepare assets
and content, and personalize the user experience. A.I.
AI designer use algorithms to generate templates
according to content, columns, colors, videos and so
on. An algorithm can be modeled to output
suggestions and possibilities according to the
designer’s choices.
This is – non-human intelligence capable of
generating creative results that seem genuine to the
human eye. And is termed as Algorithms Driven
Design
The “Advanced Design Intelligence” or ADI
Domain Driven Design technology works like a virtual graphic designer.
Rather than offering cookie-cutter templates, it tailors
Domain-driven design (DDD) is a the design through a series of prompts given to the
user, while also pulling in information from the web.
set of modeling techniques that
Since the user offers feedback as the design
can facilitate systems thinking. progresses, the finished product ends up being
DDD is a method to model unique.
software that explain business It also can analyzes rough hand-drawn sketches with
processes by expressing the machine learning and builds a screen using unified
components. The fastest way from a rough idea to a
relationships among teams and
working prototype. It predicts how user's attention
technical systems. distributes on a screen or a graphic design
The DDD concept of context composition, so designers can direct it to important
mapping is a way of illustrating areas. It couldn't replace a proper eye tracking study,
particular types of relationships but it's a good predictor for its results.
between both teams and
technical systems. It’s important
to understand these relationships
from a UX perspective because
they illuminate how interactions
between enterprise systems can
exert significant impacts on the
user experience
Algorithm Driven Design is mainly data driven process. It stars with few inputs, and use
previously cultivated data set to run AI – ML models and generate outputs using
different hypothesis,

This data science method and its cyclical processes of constant evaluation and
refinement. A properly formulated research question helps define the hypothesis and
the types of models to develop in the prototyping phase. The models are the algorithms
that get evaluated before they deploy to production into a “data engine.” Whenever the
experience supported by the “data engine” does not perform as expected, the problem
needs a reformulation to continue the cyclical process of constant refinement.
 PROTOTYPING AND
WIREFRAMING
WITH AI

Wireframing is a process where designers draw overviews of interactive products to

establish the structure and flow of possible design solutions. These outlines reflect user
and business needs. Paper or software-rendered wireframes help teams and
stakeholders ideate toward optimal, user-focused prototypes and products.

As seen in today’s design workflow, there are multiple steps from ideation of a product,
sketching interface, implementing features to testing it with users. This also open
feedback path to re-create layouts with different from sketch and create alternative
digital layouts. Designers are looking for ways to automate those steps. 

Wireframing AI (using computer vision, image processing and machine learning

algorithms) can teach machines to understand manual / paper sketches and turn them
into product user interfaces automatically. Using this technology, it’s possible to skip
few steps in the product development lifecycle and instantly translate sketches into a
finished design.

AI in Prototyping can be used not only as a tool for turning raw drawings into high-
quality usable mock-ups or prototypes, but it can be used as a tool for exploring the
ideas themselves. Machine learning and Deep learning algorithms can take input
parameters (From designers) and propose multiple variations of a design according to
the parameters. This can be modeled to create domain specific template depending on
mental map of different domain specific users.

By using Wireframing AI, designers will be able to specify a general direction of the
design; machines will explore all possible options for them and then propose the best
design solutions based on the original requirements.

Wireframing AI use Deep Learning method to generate real time prototype as depicted
below

The advancement in Artificial Intelligence (AI) technologies is thoroughly changing the

landscape of product prototyping. It is quickly becoming apparent that the utilization of
AI and machine learning (ML) is putting companies ahead because it speeds up the
process at a lower cost, minimizes the risk of errors that may occur in the process, and
makes this vital part of the product development more efficient

Airbnb AI prototyping tool can generate following HTML UI from hand sketch. The
company is currently developing a new AI system that will empower its designers and
product engineers to literally take ideas from the drawing board and turn them into
actual products almost instantaneously.
The AI-powered solution aims to simplify the overall product development routine by
focusing on testing functional prototypes, rather than bouncing half-assed modules and
components between different teams.
 FACE, EMOTION RECOGNITION
AND
MENTAL MODEL
UX specialists create products and services that are useful, usable, and enjoyable.

Fortunately, we have a number of research methods already established to point us in

the right direction in this pursuit. But, this became challenging when it comes to read
human emotion. To read human emotion even more difficult, when users say what they
feel is often not an accurate representation of how they actually feel.

In an effort to help user experience professionals objectively and accurately evaluate

human emotion, several model has been developing in AI space. This technology reads
human emotion through facial expressions. These models works via complicated
algorithms that analyze the facial expressions of people, either offline via video, or in
real time while a person sits in front of a webcam. With existing AI models, facial
expression recognition algorithms can detect basic emotions, such as fear, happiness,
sadness, surprise, anger, disgust, or neutrality. Several can also classify a person’s head
orientation and gaze direction, as well as if a person’s mouth is open or closed, if his
eyes are open or shut, and if his eyebrows are raised, neutral, or lowered.
One of the main benefits that this technology offers to UX professionals is its ability to
be easily used in combination with established research methods, like usability testing
or provide more detailed view of users’ experiences. With advance findings of user
emotions / reactions to product and service, enterprise may potentially get an edge in
service / domain.

Other benefits of facial expression recognition software include the ability to save time
by quickly coding and analyzing video data, the capability to let other applications
uniquely respond to the emotional state of a user during testing, and the option to
detect discrepancies between reported and actual human emotion. Finally, there is the
potential to use facial expression recognition technology to create personalized e-
commerce and entertainment experiences.

In summary, facial expression recognition software is an emerging research tool that can
help UX professionals systematically capture and objectively analyze human emotions.
While the tool’s full potential has yet to be completely discovered, I have no doubt the
technology will be more widely used in the future.

The process of creating a better UX comes down to AI algorithms. These smart-systems

can process information about site visitors or app users, then apply changes to the
model in ways that optimize it for future use. By continually learning and adjusting, the
algorithm improves the user experience to offer a more engaging, personalized
experience.
In advance age, Based on sound art or electroacoustic composition, these should
deal with emotions in human-machine interaction and link themselves
interdisciplinary with Emotional Artificial Intelligence, Affective Computing or
neuroscience.

A mental model is a person’s understanding of how something works and how

their actions affect it. People form mental models for everything they interact
with, including products, places, and people. Mental models help set expectations
for what a product can and can’t do and what kind of value people can expect to
get from it. Mental models can also serve as bridges between experiences. For
example, if you know how to steer a bicycle, you know something about how to
steer a motorcycle.
UX TEST AUTOMATION WITH AI
AND BEYOND
Different kind of Testing is a planned process that assesse, analyze and guarantees
customer satisfaction within an application and helps in safeguarding against potential
failures that may prove to be detrimental down the line.

With the change of Software lifecycle management and introduction of agile

methodology delivery spans reduce to weeks. Hence there is no other choice than to
test smarter and not harder in this day and age. Thus, it is quite evident that the key to
streamlining software testing and
making it more smarter/efficient is
Artificial Intelligence.

By assimilating machines which can

meticulously mimic human behavior,
the team of testers can move beyond
the traditional route of manual testing
models and progressively move
forward towards an automated and
precision-based continuous testing
process. An AI-powered continuous
testing platform can recognize
changed controls and with constant
updates to its algorithms it can run
test process to satisfy quality of changes.

When it comes to automation testing, Artificial Intelligence is used widely in object

application categorization for all user interfaces and it recognized controls. Testers can
create models and pre-train controls as out of the box setup to execute AI based testing
effectively.

When user behavior is being assessed, a risk preference can be assigned, monitored and
categorized accordingly. This data is a classic case for automated testing to evaluate and
weed out different anomalies. Heat maps generated through machine learning and AI
will assist in identifying bottlenecks in the process and help determine the course of
action.
Split testing, or A/B testing, compares two versions of a feature to determine conversion
rate. AI relies on different methods to find and improve conversion rates across
websites. It helps business team to verify whether changes to marketing content
improves conversions or if it was better the first way.

AI constantly makes use of evolutionary algorithms, data metrics, and predictive

algorithms to analyze a web page. This is then followed by a complete breakdown of all
the great-performing elements available in that particular webpage. This enables the
marketers to create a website that is the amalgamation of all the best-performing
features resulting in a massive surge in conversion rates.

AI and ML are so useful for testing that some of the world’s biggest tech companies,
have deployed them or launched pilots for using that purpose. eBay, as one example,
developed a proof of concept to use ML to automatically detect flaws on eBay web
pages.

There’s good reason AI and ML have become so popular for QA and testing. Among the
benefits is that AI and ML can speed up test creation, reduce test maintenance, and
automatically generate tests.

“For now, AI and ML aren’t able to completely replace the work of people,” says Eric
Sargent, vice president of sales for Functionize. “Fundamentally, there’s still no
substitute for human understanding of the underlying intent of a test and expected
behavior of an application, but AI and ML can certainly be powerful tools to fill in some
of the key gaps of the testing process that have presented challenges for some time
now.”

Used properly, AI and ML can also do an excellent job at regression testing. “As
applications become more complex and release cycles accelerate it’s simply not possible
for humans to effectively keep up with the demands of running an maintaining their
regression tests,” Sargent says, “Automation takes some of the burden off of execution.
But by incorporating AI and ML, tests become more adaptable to minor changes. They
self-correct or ‘self-heal’ as necessary. That task could take hours for a human to
complete, as they work through triage of a failed test.”
 BEHAVIORAL
BIOMETRIC IN UX
DESIGN
Behavioral biometrics is used as an identification mechanism: it identifies people
according to how they interact with online applications and devices. It works passively in
the background and make system more secure.

Artificial Intelligence (AI), Deep learning (DL), and Machine Learning (ML) are all
associated with behavioral biometrics.

Physical biometrics technologies such as iris, finger, and facial recognition are based
primarily on a static procedure of measuring points obtained from fixed images.
Whereas, behavioral biometrics is governed by a dynamic approach driven by machine
learning and deep learning, which involves gathering and processing very large data
sets. Using primary device sensors such as accelerometer, gyroscope, and touch,
hundreds, possibly thousands of behavioral patterns can be used to authenticate users
continuously. The tap duration, fingerprint area, device acceleration, swipe speed, and
session duration are among some of the behavioral parameters that are captured and
profiled.

Machine learning makes it conceivable to drive the decision-making processes that are
needed to maintain a large number of parameters and data sets that must be analyzed.
It is being utilized in all aspects of behavioral biometrics. ML is capable of learning from
human behavior and continuously enhancing user profiles that can be used to
authenticate sessions or transactions.
Behavioral Profiling

While the vast majority of sites use knowledge factors, a growing number are turning to
multi-factor solutions in an effort to bolster security; to the detriment of the user
experience. Cue continuous authentication / behavioral biometrics... the process of
identifying a user based on the subtle nuances in their voice, typing patterns, facial
features and location.

As opposed to traditional authentication which is only interested in what you type,

behavioral biometric systems collect & profile how you type too. By actively monitoring
how you type, the system is able to build a profile on you.

In order to achieve this, the system monitors how long each key is depressed (dwell
time), how long between each key press (gap time), how long to type a known string
and hundreds of other metrics.

Deep Labs, a Silicon Valley-based startup founded in 2016, develops artificial

intelligence security tools for banks and credit card companies. The company uses
artificial intelligence and machine learning to leverage the power of behavioral
biometrics to develop the concept of persona-based intelligence. According to its CEO
and co-founder, Dr. Scott Edington, behavior-based security has reached a higher level
of sophistication, because it would be nearly impossible for fraudsters to fake how a
person types their password or holds their phone. If a user’s phone is used even in a
slightly different way, the action is immediately flagged.

Over the next five years, Dr. Edington’s predictions are that the industry will heavily rely
on artificial intelligence and machine learning which will deliver a seamless and
frictionless customer experience. Most industries are looking into delivering a friction
free ecosystem, so in the upcoming years “pressing 1” to confirm transactions will be a
thing of the past. AI will solve most authentication problems and the world will likely be
living “the dawn of the machines.”
 CONVERSATIONAL UX
AND
ARTIFICIAL INTELLEGENCE
A Conversational User Interface (CUI) is an interface that enables computers to interact
with people using voice or text, and mimics real-life human communication. And
Conversational UX design is a way to smooth out the interactions between humans and
technology.

The goal of conversational UX is to make a piece of machine seem entirely human. But
the current state of conversational UX is still apparent that you are talking to a machine
when interacting with AI personalities. To reach at the future goal of conversational UX,
experts are working on establishing a set of guidelines to teach people in the tech world
how to design optimal conversational systems.

The normal approach has always followed a dead-end path. Existing flowcharts are
disappointing when it comes to describing the conversation, hence a quantum leap is
needed. Conversational systems also need to be based off learning systems. Automated
systems will shift away from needing someone to identify how they should respond.
They will eventually be able to determine a response independent of humans. Instead of
designers, conversational systems will require people who fulfil roles more similar to
teachers or coaches.

Many aspects need to be accounted for using AI and bots, and software code must be
written a long time after the bot begins its analysis. Conversational AI will asks for
solutions that will be derived from all three zones (AI, ML, and DL). . A proper bot
solution is integrated with existing software in a multi-channel solution. Any voice
Chatbot must implement Natural Language Understanding (NLU)
NLP [Natural Language Processing] allows AI algorithm to better understand the context
and meaning of users’ requests. By relying on NLP, Chatbots can do the following:

 Process search queries such as “show me the latest products in my cart”.

 Interpret the basic information from the conversation e.g. the topic being discussed,
whether the response was negative or positive and so on.
 Correctly understand and render synonyms, jargon and common abbreviations.
 Format the information they have collected in natural language. For instance, spell
out the weather forecast for the requested destination, instead of throwing in some
numbers.
First, the application receives the information input from the human, which can be either
written text or spoken phrases. If the input is spoken, ASR, also known as voice
recognition, is the technology that makes sense of the spoken words and translates then
into a machine readable format, text.

Second, the application must decipher what the text means. It uses Natural Language
Understanding (NLU), which is one part of Natural Language Processing (NLP), to
understand the intent behind the text.
RPA [Robotic Process Automation] could greatly streamline the rest of the customer
journey by automating the validation checks, configuring policy renewal, and even
settling the claim via direct reimbursement. By applying this paradigm to other
industries, we can easily see how the intersection of CUI and RPA could completely
change how we apply for loans, book holidays, find vendors and initiate business
contracts.

As CUI [Conversational User Interface] technology advances, we are likely to see brands
adopt and configure CUIs as branded digital assistants that handle everything from sales
and marketing to customer support and lead nurturing. Similarly, the managed IT
services sector is just a couple of years from implementing powerful AI assistants that
can efficiently handle workloads from both internal and user-facing divisions.
 AI-BASED CONTENT
GENERATORS
Artificial Intelligence helps the content creation process in many ways. It can analyze
millions of data, giving only useful insights, reusable extract content, or create new one.
There are a few ‘models’ of AI that can actually generate some decent content from AI
alone. AI marketing is used commonly in news feeds and social media, as well as in
improving customer experiences at certain points of the user journey.

Before AI, the search for ideas consisted in surfing the Internet and analyzing what is
popular now and what competitors are up to. However,

AI uses a more accurate technique by analyzing keywords, themes, and domains based
on social share to discover Content idea.

Online marketplace script uses AI to bring good analysis skill and content writing force
to businesses. AI’s job to analyze writing samples and pick the best writers on any topic,
it can analyze the cost and time for content creation.

AI can be modeled to analyze content’s performance. It is able to predict how users

will react to a specific content like photos, keywords, hashtags, and colors. This analysis
can save time and provide superior quality performing content.

Automated content creation is reality. With the help of natural language generation
(NLG), it is possible to create content from given set of data and key words. This
technology uses different types of rules and algorithms to create reports based on the
data. NLG is used by different fields to create automated content from business and
marketing data at scale.

Artificial intelligence is not only able to create and test content but also optimize the
content. AI and ML models can compare an ideal set of content topics, generated by AI,
against a website’s content inventory. Depend on that, it creates prioritized content
plans. It can also improve content on a page level by showing relevant keywords.

Artificial intelligence is able to personalize content for different audiences. Therefore, it

brings the best return on investment from every single resource and people
automatically get the information they need. AI and ML together can analyze all kinds of
data like user, demographic, time, state, emotion and define what kind of information a
particular user would like.

Enterprise brand content also benefits from AI as well. AI and ML can analyze
behavioral data (data collected from customer interaction with content) and define
their preferences and the phase of journey. AI is taught to determine data structure in
order to know what the user will desire next.
 CONCLUSION
AND
FUTURE OF UX WITH AI
Artificial intelligence and Machine Learning is changing the shape of every
industry. AI has performed as the key driver of future technologies and it will remain to
act as a technological modernizer for the predictable future.

UX Design and AI are quite similar in few aspects. Both of them understand patterns of
user interactions and provide better experiences based on the insights gathered from
user interactions. With the improvement of AI in future, intelligent interfaces will be
designed and developed, hence, user interface will also be enhanced and matured
accordingly.

With development of advance AI-Driven UI, industry is moving towards eliminating the

physical screen. Advance level user interface incorporating visual content and gesture
recognition will be used to give the consumer a clear picture of what they really need.
Using AI, Augmented reality (AR), Virtual Reality (VR) users will get an idea of the
product / service before purchasing it.

AI and ML based interface design will be created to provide tailored and personalized

experiences.  With the advancement of UX design industry will see smarter and intuitive
interfaces. Artificial intelligence solution providers will create innovative tools which can
create domain specific dynamic visual styles. Smart experiences-powered by AI will
understand the context of a element (picture / video etc.) and interpret it for users with
visual impairments. AI will help make designers more impactful and intelligent. Also, this
will help in automating data driven repetitive tasks to save time for designers.

With advancement of artificial intelligence, machine learning and natural language

processing, industry will create customized experiences for each customer by
understanding user emotion, customer journey, behavioral pattern and mental model.
--------------------------------------- END -----------------------------------------
 Trend Domain Type Current Implementation
User Journey with AI E-Commerce Domain Design Amazon, or Alibaba, or eBay,
Customer Data Platforms and CRM,
Salesforce
Algo Driven Design Website Design Domain Design https://thegrid.io/, Wix,
Vox Media, Netflix
Wireframing with AI All Template Design Adobe, Uizard, Airbnb’s AI
Emotion Recognition Advertisement Element Design https://www.noldus.com/facereader
AI Test Automation Testing Testing TestCraft from perfecto, functionize
Behavioral Biometric Banking Usability and BioCatch
Security
Content Generator Content Website Content Wikipedia
Conversational UX Support Service Communication Alexa , Siri , FB Messenger

User Journey with AI

https://www.financemagnates.com/thought-leadership/how-to-make-the-
most-of-the-customer-journey-using-ai/

https://www.forbes.com/sites/danielnewman/2020/12/30/ai-and-analytics-
optimizing-your-digital-customer-journey-map/?sh=a4b07a41f491

Algo Driven Design

https://www.smashingmagazine.com/2017/01/algorithm-driven-design-how-
artificial-intelligence-changing-design/

Wireframing with AI

https://xd.adobe.com/ideas/process/wireframing/wireframing-automation-ai-
ux-design/
Emotion Recognition

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0235908

https://uxdesign.cc/ai-emotion-detection-for-user-research-a-ux-case-study-
be6bc485058d

AI Test Automation

https://techbeacon.com/app-dev-testing/how-ai-changing-test-automation-
5-examples

Behavioral Biometric

https://findbiometrics.com/behavioral-biometrics-can-ensure-strong-ux-as-
online-banking-rises-biocatch/

https://findbiometrics.com/biocatch-describes-business-benefits-behavioral-
biometrics-010805/

Content Generator

https://blog.atomicreach.com/artificial-intelligence-content-creation-speed

Conversational UX
https://www.xenonstack.com/insights/what-is-conversational-user-interface/

https://alan.app/blog/what-is-conversational-user-interface-
cui/#whatisaconversationaluserinterface?