Chatbots for WhatsApp

AI Chatbots for WhatsApp

As the world is witnessing an unprecedented disruption due to Covid-19 outbreak, as consumers increasingly turn to digital, and as your agents and staff are forced to work from home, having a fast and accurate shopping assistance service via a conversational interface is becoming as important as having a solid ecommerce website. Businesses, across sectors, are racing to add AI-powered chatbot that can transact with consumers on the website and on other digital communication channels. (If you are wondering why chatbots, you can read the articles “why AI chatbots for your retail business” and “how AI chatbots will transform the retail industry in 2020” to understand more). Since WhatsApp is the most popular and widely adopted messaging channel in modern world, the obvious choice therefore will be to launch your chatbot on WhatsApp. But wait – So far WhatsApp did not allow businesses to launch chatbots on their platform and only in the recent past have they given access to their business APIs for automated messaging. Things work a bit differently in WhatsApp (compared to other messaging channels such as facebook) and in this article I will explain what you as a business need to know regarding launching your own chatbot over WhatsApp.

Firstly, Why WhatsApp?

WhatsApp has emerged as the go-to messaging app for over 1.6 billion users around the world. Users find it simple, fast, reliable and convenient. Users can securely share texts, photos, videos, documents in private or in groups. For AI chatbots, a platform like WhatsApp makes a huge difference because most of the users will already have WhatsApp installed on their devices and they prefer it the most to communicate with friends and family. For interacting with their favourite brands, they do not need to switch to a different interface like a website or a new mobile app. Moreover, given the heavy usage of WhatsApp on a daily basis, it’s more likely that the user will open and read the notification messages sent over WhatsApp.

Getting started with WhatsApp Business?

On WhatsApp, your business account is tied to one registered phone number with which you first create a profile of your company or business. This allows whatsapp users to know whom they are messaging to and are receiving messages from. You can then include this number in your marketing programs to get more customers to connect with you.

For small businesses where owners themselves (or with the help of a small team) resolve a small number of customer queries manually, they can install WhatsApp Business app, set it up with a number and can get going almost instantly. For medium to large-sized businesses where customer messaging has to be automated at scale, they require more than just an app. These businesses need to integrate with WhatsApp business APIs to receive, respond and push automated messages via chatbots over WhatsApp.

Getting access to WhatsApp business API for chatbots

WhatsApp’s Business APIs are not open to the public in general but only to a bunch of carefully selected companies globally who are known as WhatsApp API providers. And unless you’re a large multinational firm or an enterprise scale company, it’s very difficult to get direct access. Some examples of WhatsApp API providers are companies like GupShup, Twilio etc and for you to get access you will need to work through these providers.

So what are steps involved for launching your whatsapp AI chatbot?

  1. Pick one of the API providers first
  2. Develop and test your whatsapp ai chatbot in a sandbox environment provided by your API provider.
  3. Submit details of your company (phone number, email, company details, usecase, Facebook Business Manager ID etc) to the API provider for their approval.
  4. Once approved, you are ready for production deployment and your chatbot will be able to receive user messages sent to your WhatsApp business number, respond to these messages as per the chatbot design and also notify your customer with push notification messages.
  5. Once deployed, API providers will charge you on a per-message basis which typically varies from one provider to the other. Note that this is the base charge for API calls only and on top of it, you will incur the cost of development of the AI chatbot and that of keeping it running.

Limitations of WhatsApp chatbot

WhatsApp was built for messaging and WhatsApp wants to keep it that way. They do not want businesses to exploit this channel for marketing and annoy the users. Hence the API integration is quite tightly controlled and usage have multiple friction points that you should be aware of.

  1. Approval process is tightly controlled and is rigorous:

    WhatsApp and its API providers are very cautious in approving business API integration. Before approving, they will review the phone number, authenticity of your business, use-cases your business is going to address via the chatbot and only upon sufficient validation will they approve usage of the APIs.

  2. Enforces strict guidelines for automated messages:

    To prevent businesses from spamming user’s WhatsApp by automated marketing messages or ads, WhatsApp enforces some guidelines for automated messaging very strictly. These are called opt-in messages and template messages.

    • An opt-in is when your customers agree to receive messages over WhatsApp from your business by providing you with their mobile phone number through a different channel such as your website for example. It is your responsibility to store customer opt-ins and to ensure each customer that you choose to contact through WhatsApp Business has agreed to receive messages in the first place.
    • Template messages are messages of a specific format that your business can send to users proactively and not as a reply to the user’s message. Any message that your chatbot is sending proactively after 24 hours since the user’s last message is qualified as a template message. Template messages use placeholder values that can be replaced with dynamic content. The template message needs to be approved by WhatsApp before you start sending them. Any proactive message whose format is not approved as a template message by WhatsApp will be rejected.
  3. Limited UI design elements in AI bots:

    WhatsApp has limited UI design elements for showing messages and accepting user inputs in the chatbot conversations. Unlike other platforms such as Facebook Messenger, it does not support rich UI elements like cards, carousels, buttons, etc. Only texts, links, images, videos, and documents are supported. This will limit your ai bot experience significantly especially if you compare facebook messenger or webchat.

AI Usecases for Whatsapp chatbots.

Despite the above limitations, your AI chatbot on WhatsApp can solve use-cases that are impactful enough for your business and your customers. The most vital being Customer Service Automation. With the help of AI chatbot you can answer FAQs instantly, provide information on order tracking & ongoing promotions, guide users to the nearest stores and also accept customer service requests automatically. Taking a step further, your whatsapp chatbot can switch to live chat with your human agents only when necessary allowing them to handle 3X-4X more cases than they would normally do via phone or over instant chat service. WhatsApp chatbots can also help users discover the right products and cross-sell or up-sell based on AI.


There is no doubt that AI chatbots have become the need of the hour for businesses with eCommerce. At present, it is the most effective way to automate and scale customer support, bring more leads, engage customers in a timely manner and ultimately lead them down the sales funnel. WhatsApp channel is going to take the chatbots to the next level in terms of user adoption and engagement. If your business is already having a chatbot on channels like website, Facebook Messenger then WhatsApp is the next thing you should be aiming at.

Can AI Exist Without Machine Learning?

Can Artificial Intelligence Exist Without Machine Learning?

We have already talked about artificial intelligence and machine learning in our previous blog. We have seen how machine learning is just a subset of AI and that it helps AI accomplish its goals. Now let’s discuss if AI can exist without ML.

Surely not, right? If there’s no ML, how can AI work? ML is a tool used by AI, surely. But wait.. Not so fast !!

You see, the term artificial intelligence existed long before Machine Learning was commonly used. We are talking about the 1950’s and 60’s here. There were systems which claimed to use AI to work. They are known as GOFAI systems but they didn’t use ML. So what’s going on here? What’s the catch?

What is GOFAI?

Before machine learning, AI generally used a form of AI called GOFAI. GOFAI stands for Good Old Fashioned AI. It is also referred to as Symbolic AI. 

The core belief of GOFAI is that any complex system can be defined using human readable symbols and rules. The rules would define the processes that take place within the system. Some examples of Symbolic systems are,

  1. Algebra – Here we use x,y,z to represent variables and +,-,x,/ to represent operations between variables. So an equation like x = 3y + z is termed as a rule.
  2. Chess – The pieces like king, queen, bishop are symbols and the moves are the operations between the pieces.
  3. Programming languages – many languages use certain keywords like “for, while, class, object” etc. So they would be symbols. Statements like “for x in list: x = x + 2″ would be called rules.

These are obviously not AI systems. But they serve as examples of Symbolic systems. The idea behind Symbolic AI systems is that we can take any complex real world interaction and encode it in this manner.

GOFAI also deals with a class of AI problems called Strong AI

What is Strong AI?

AI problems which fall under Strong AI usually deal with complex real world scenarios. But the best way to understand Strong AI is to look at what weak AI means.

Weak AI problems are narrow in nature. They deal with a specific scenario and nothing else. Most modern machine learning and deep learning tasks are Weak AI problems. It tries to solve simple problems like image classification, text classification etc.

Consider the case where we have to identify accidents in traffic cam feed. The solution would be to build a system which takes the video stream as an input and look for specific signs of accidents in real time. It needs to be able to identify a car crash and the like. This is considered to be a Weak AI problem as it solves a narrow task. This AI would not be capable of doing other tasks.

A Strong AI system is to model more complex systems such as a general artificial intelligence which can act, feel and do as a human would.

GOFAI was seen to be trying to solve these problems. Although unsuccessfully.

Expert Systems

There are many examples of GOFAI systems out there. They are also called expert systems which solve problems in a specific domain. These systems use Symbolic AI to create symbols and collect data from domain experts to form production rules. Examples being

  1. Phone IVR systems – These systems are created by collecting data about what users generally call about. Using this information, an IVR flow chart is created which guides the user through its various functions. These systems encode production rules as flow charts and use symbols on the phone keypad which it can recognise (e.g. 1, 2, 3)
  2. Automated Medical Diagnosis – Systems are capable of identifying specific conditions using patient data, reports, scans, etc. Some of these systems rely on a vast amount of data from domain experts. The final GOFAI system is used to check this knowledge base to find a match. This type of system uses a knowledge base and an inference system.
  3. Simple chat bots – Chatbots fulfilling a simple flow of customer service, food ordering, and ticketing, etc also use a form of GOFAI. They are quite similar to Phone IVR systems, just with a better interface. They follow a flow chart, guiding you through button clicks to reach a specific goal.

Is GOFAI really AI?

So we have seen how AI can exist without ML. Such systems use the concept of GOFAI and symbols. But GOFAI has its detractors. Many do not consider it to be AI at all. There are many arguments against GOFAI and whether or not Strong AI is achievable.

One of the more interesting arguments against Strong AI is John Searle’s Chinese Room Argument in his paper “Minds, Brains, and Programs”. In it Searle asks us to consider that he is sitting inside a closed room. He accepts small pieces of paper from a slot box in the door. His task is to translate from English sentences to Mandarin sentences. He would then use phrase books within the room to help him finish the translation.

He compares Symbolic AI systems to this chinese room experiment. The person within does not understand Mandarin, but is still capable of completing the task. But this does not mean that he truly understands the language at all.


Although GOFAI and Symbolic AI has its opposers, it is true that these systems are all around us. They do not use machine learning, instead they use symbols and rules but still many claim that they use AI. Detractors of GOFAI, on the other hand, argues that systems which uses symbolic AI are not really intelligent and therefore cannot be treated as AI systems.

Curious Much? Drop us a note at or visit our website and let’s start a conversation!

Top 4 reasons Why AI Projects fail?

Top 4 reasons Why AI Projects fail?

For those who are new to AI technology, Artificial Intelligence is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans. The term “artificial intelligence” is often used to describe machines that mimic “cognitive” functions that humans associate with the human mind, such as “learning” and “problem-solving”.  To understand more on AI read this blog article from Tejas

Despite increased interest and adoption of artificial intelligence (AI) in the enterprise, 85% of AI projects ultimately fail to deliver on their intended promises to business, according to a recent industry report. In this blog post, I have put together the top 4 reasons for failures

1. Organizing your AI team

Building your own AI team is not at all easy. Unless you have a budget the size of Google’s, building an in-house data science team is costly and time-consuming. There is a shortage of data science experts everywhere, and the experienced ones are often involved in engaging projects with big projects and companies. So, in this constrained environment, what is the best way forward? If you are starting fresh then trying to build a big team upfront is absolutely unnecessary. At the same time, starting out with college graduates and training them to become experts can be a costly mistake. In the quest of saving dollars, you are compromising on the quality of the deliverable. Experienced folks, usually from engineering background, with deep understanding of the business and the data are the right choice to start with. In we started without an AI expert in the team. We put our best and experienced folks to take a dig at our AI expeditions. We laid out an implementation plan with well-defined and small milestones. One needs to get into a hypothesis and experimentation mind-set. Validate ideas quicker, eliminate or accept based on experimentation outcome and move ahead. In this process, we learnt from our mistakes and we improved at every step and came back strong. The first set of AI engineers then mentored the fresh and lesser experienced AI folks and helped them in productionizing their AI experiments. Today we have a sizeable AI experts team who can go all guns given a problem ahead of them.

2. Lack of proper Data Strategy

The importance of data strategy is often underestimated. In the past, data was just a by-product of processes and business activities. It’s different now. Data is the most valuable resource that allows companies to gain competitive advantage and come up with new ways of improving their operations. In most cases when dealing with AI projects, collection of data is a challenge. There’s not enough of it and if you are somehow able to get hold of the data then there can be issues with labelling, training data, etc. Data doesn’t just have to exist, it has to be labelled. If data isn’t properly organized, humans have to devote their time to the tedious task of labelling it. Data labelling is troublesome and time consuming, yet somehow many companies just don’t think about it at all. Because an AI system can only be as good as the data it’s fed with, you can’t have any tangible results if there’s no meaningful data behind it. Here at, we have tools developed to automate data collection, validate data quality and easily manage it. You have to treat your data like gold and ensure it is not corrupted by any means and over the last 3 years, we have tried to carefully automate a large part of this process.

3. Unrealistic expectations from AI technology

Many organizations are tempted to follow the big players like Amazon, Google, Microsoft, etc. It’s just logical to assume that what they do makes sense. However, companies like Amazon have gathered enough capital to test various, even seemingly crazy solutions with very lofty goals. They can afford it, and experimenting with technology is great. However, smaller companies cannot afford to take so much risk. Observing the giants, learning from their successes and failures – that does bring value. But keep in mind that each business is different and has different needs. Don’t let yourself lose sight of what matters to you. Do some research, get your strategy ready, and then play your game accordingly. Implementing a new piece of technology can be challenging, and that’s something organizations must always remember. AI is not a magical tool – it needs the right use case matching your objectives, the right data, and success criteria, it also has certain limitations. When you identify the AI usecases you think is right for you, learn both the possibilities and the limitations the different AI solutions have to offer. It’s an important part of the process to know what AI can do for your business, realistically, and be able to later track the performance of the deployed models. Please remember – there is no such thing as perfection, even for AI. AI also makes mistakes. No AI algorithms will be 100% error-free. In our case, we have a Question and Answer system which can answer user questions asked through the Chatbot on the client’s ecommerce brand website. There will be times when the AI model is less confident about which question the user is asking and therefore what should be the answer. This is the case when AI is not able to clearly decide from its trained AI algorithms. In such cases, we handle this gracefully by providing the user with Did you mean? – Question suggestions. Small strategies like these will help your organization avoid your AI failing badly but more importantly also allows the AI to self-learn very quickly. Continuing on the same example, today our AI technology is able to answer 80% of all questions asked by website visitors of our client thereby prompting the client to take our solution and launch it even in their retail stores.

4. AI Bias

AI bias, or algorithmic bias, describes systematic and repeatable errors in a computer system that create unfair outcomes. Though the name suggests that AI is at fault, as described above, it really is all about people and how the AI is trained. Chief Decision Scientist at Google, writes: “No technology is free of its creators. Despite our fondest sci-fi wishes, there’s no such thing as ML/AI systems that are truly separate and autonomous…because they start with us. All technology is an echo of the wishes of whoever built it.”.

We faced this situation in with our ecommerce NLP intent model. We saw that more and more user questions and complaints were classified as product discovery. What this means is questions like “How to wash cotton tops?” showed cotton top products, which clearly is not what the user wanted. Upon investigating we got to know that the engineer who tagged it was more biased towards classifying such sentences as product discovery. This created an imbalance in the knowledge-graph which lead to incorrect and biased intents model. To solve this, we had to revisit the labelling and correct it. To avoid such problems, it is advisable that more and more people validate the labelling before it is pushed to the LIVE environment. Again, this does not mean extensive manual effort but smart algorithmic ways to sample the right data set and validate is enough and can do the trick.

One famous example of AI Bias is Microsoft’s AI Chatbot Tay – which could automatically reply to people and engage in “casual and playful conversation” on Twitter. By flooding the Chatbot with a deluge of racist, misogynistic, and anti-Semitic tweets, Twitter users turned Tay – a Chatbot that was described as “a robot parrot with an internet connection” – into a mouthpiece for a terrifying ideology. After a failed effort to clean up Tay’s timeline, Microsoft pulled the plug on their unfortunate AI chatbot experiment.

Conclusion: So, how can you ensure a successful AI implementation?

The good thing is that with so many organizations having already failed at AI, you can learn from their mistakes and avoid making the same ones. It’s a good practice to observe the market, not just in your direct competition, but also in the tech world. This way, you will know what you can realistically expect, what use cases are promising, what limitations you have to take into consideration. Take ‘Fail Fast, Fail Early’ as a motto when it comes to AI. You have to experiment, test hypotheses, go down some blind alleys, learn from them and use these to find success. Having processes and methodologies for agile, rapid experimentation that delivers results quickly and at a relatively low cost is critical for success. Do not expect to draw up the perfect AI strategy for your business at the start and to execute it. Start with the assumption that you will have to evolve and change this as you progress.

If you like this blog or have anything to share, please leave your comments at 



AI without data

AI without data

Artificial intelligence or AI refers to the simulation of human intelligence in machines. (Refer the article Are AI and machine learning the same if you wish to understand more on what is AI) Artificial intelligence-based system learns from data (also referred as “training data”). These systems find relationships hidden in the training data, develop an understanding of the data, make decisions and then evaluate their performance from the data. And better the training data, better the system performs. Or in other words, the training data (both the quality and quantity) dictates how well the AI system will perform. In this article I will cover some hacks one can use if there is not enough training data available. So read on.

But first let’s understand how the training process works in the AI world.

How does the training process work?

Let’s say you want to make an AI-based system capable to do visual search i.e. it should be able to recognize a particular object in a given image (example: is the person in the photo wearing a jacket or not?). The process of training this AI is as follows (refer the picture below)

AI training process

  1. A computer program is fed through a large number, usually thousands, of labelled images of “person wearing jacket” (positive label) and “not wearing jackets” (negative label). This is the training data for the AI.
  2. The program learns on this data and produces a model to detect jackets.
  3. This learning is repeated in fixed iterative cycles till the performance of the model improves and then the model is able to detect the jackets with good precision in new unseen images. This iterative process is called Training.

Businesses often struggle to find enough relevant training data to train their AI and this is because most often the data they need resides in multiple sources, are usually available in an unstructured format and therefore not useful for machines to learn from. So in such situations, how can you still make sure that AI works for you?

What can you do when you don’t have much data?

Here are 5 possible hacks you can try out and it is very likely that one or more will work in your situation.

Top 1 hack: Transfer learning

Transfer learning is about using the knowledge gained while solving one problem for which a lot of labeled data is available and applying it to a different but related problem for which only little labeled data is available.

For example, the knowledge gained while learning to recognize a person in an image could apply to recognize the types of clothes that the person is wearing and finding dominant colors in his clothing.

Top 2 hack: Data augmentation

Data augmentation is a process that increases the diversity of data available for training models, without actually collecting new or more data. As an example, for computer vision-related tasks we have the following options:

  • Horizontal/Vertical Flip: Flip the image horizontally or vertically to add more diverse data.
  • Change in scale: Crop and/or zoom images in various scales
  • Lighting conditions: Change the brightness/sharpness/contrast of the images available.
  • Rotation: Rotate the image by some different degrees.

For text (NLP) related task you can try the following options:

  • Synonym Replacement: Randomly choose some words from the sentence and replace each of these words with one of its synonyms chosen at random. This creates more utterances of as existing sentence.
  • Back Translation: English is one of the languages which is having lots of training data for most of the NLP(Natural Language Processing) tasks. So, if there is less data in a language for a particular task then more training data can be created by translating English data into that language.

Top 3 hack: Problem Reduction

Problem reduction approach refers to modifying the new data or unknown problem to a known problem such that it can be easily solved using existing techniques. Here is an example:

  • Suppose we have a small labeled dataset of “audio clips”, where the sound in each clip belongs to one of the 10 categories like a car engine, piano note, drilling machine, and a dog barking. Now say, we want an AI-based system capable of recognizing the source of audio in these clips.
  • If you try using any existing audio-based algorithms to solve this problem, it might work out. However, the small data set can be a deal-breaker.
  • One alternate method is to try converting the “audio clips” intoimages” thereby reducing the audio problem to an image classification problem. Now we can use any suitable computer vision-based algorithm to train on this “new image” dataset and create a system capable of classifying these “audio” images into one of the 10 categories.
  • Surprisingly results have shown that the performance of these image-based systems is far better than the audio-based systems.

Top 4 hack: One-shot learning

Neural networks are good at learning from high dimensional data like images or spoken language, but only when they have huge amounts of labeled examples to train on. Humans, on the other hand, are capable of one-shot learning – if you take a human who has never seen a fork in his entire life and show him one, next time if you ask him to bring one from that messy drawer of your kitchen, he might be able to fetch that with high precision. For this type of approach, there are advanced algorithms that we will try to cover in later blogs.

Top 5 hack: Open source datasets and APIs

Various data sets are available in the open-source community or on the internet, which can be easily downloaded and used for training purposes. Some examples like the amazon dataset and google dataset are also accessible easily. Apart from these, search engines like google and bing also provide APIs to download datasets and pre-trained models, which can be used in many ways to improve the performance of an AI-based system.


While availability of relevant training data decides whether an AI system will perform well or not, it is certainly not a hopeless case if one does not have enough data. There are multiple techniques and hacks that one can still try out and I have listed the top5 above.

Where chatbots can be used? Who uses chatbots?

Where chatbots can be used? Who uses chatbots?

Chatbot technology have been around for years now. They started out as an accident on Telegram and then developers started creating little bots on Slack – internally for their team’s use. Then WeChat, China’s Biggest Messaging Platform, began supporting bots and it really took off in China. Since Facebook Messenger, WhatsApp, Skype, Slack, and a growing number of bot-creation platforms came online, developers have been churning out chatbots across industries with Facebook’s most recent bot count standing at over 33,000.

With chatbots then becoming a serious business, the question comes – where can chatbots be used? Who uses chatbots?

Here are the top 7 chatbot usecases and application areas for businesses.

Consumer Engagement at Scale:

Brands that engage with their customers on social media platforms make 20% to 40% more money, according to Bain & Company. Nowadays, most businesses have an online and social presence. But since availability of manpower 24/7 is a constraint and comes at a cost, it is not always possible to keep the engagement channel open and active at all times. Businesses can use chatbots as their proxy agents to engage customers at scale 24/7 and across channels such as web, mobile, facebook, whatsapp etc. Chatbots, usually, only give out a slice of information at a time and can guide the interaction based on the inputs provided by the user. That way the engagement becomes a lot more interactive and chances of losing a customer is also a lot lower.

Improve Sales:

Chatbots make the lead generation process faster & easier by interacting & engaging customers in every step. From the moment a customer makes first contact on a business’s website or social handle, a chatbot can engage the customer by understanding her requirement, recommending a product/service and guiding her to the next step in the buying process. With AI powered self-learning models in the background, chatbots can even be trained to make complex decisions such as sending coupons to customers so that they will come to the store and purchase.

Marketing campaigns:

Chatbot technology can be very useful to marketers within an organization – instead of spending money on banner ads which are typically one-way communication, marketers can leverage the chatbot technology and convert their banner ads into a two-way, highly interactive and personalized communication channel with their customers. In the marketing world it is referred to as ‘conversational ads’ and typically these result in improved click-through-rates and higher ROI compared to traditional advertisement methods.


Finance function within a company is often very complex, involves lot of stakeholders and prone to repetitive tasks such as generating same report multiple times or filling up the same forms again and again. A conversational bot can be very useful in this situation leading to not just process improvement but also saving significant money. Here are a couple of use cases that can deliver instant ROI

  • Accounts Payable Virtual Assistant – Your suppliers have submitted invoices and are now chasing you for the payment. Often they will call your team, or send email multiple times and every time your team will check the status and will write back to them with the latest update. An AI bot can take over the entire process from your team and allow your team to focus on the more strategic pieces. Let your suppliers ask their questions to the ai bot and let the chatbot answer them back instantaneously.
  • Expense Filing and approval – Every employee in every company abhors expense claim process since it is mundane and extremely time consuming. It involves filling up the same form every time and then wait for the internal approval workflow to settle the expense. An AI bot can not only automate this entire process, but can also make the experience of expense filing a lot more enjoyable for your employees


The chatbot technology can benefit e-commerce shop owners as it allows them to have a Virtual assistant available always on the Webshop for helping visiting clients find the right product/service quickly. Reports suggest that web shops with virtual assistance service can not only convert 10X more than normal websites, but it also leaves a much more delightful experience for the visiting customers prompting them to come back again for the same personalized service and experience.

Chatbots Customer Service:

70% of questions that customer service agents answer over calls are repetitive in nature i.e. these questions are largely order related or delivery related and therefore are great candidates for automation through an intelligent chatbot. Your customers get instant answers without having to wait in the queue to talk to your agent while you get to save a lot of money by making sure your agents are now able to handle 2X-3X more calls within the same time.

Collect Customer Data & Gaining Insights:

As stated earlier, chatbots are great tools to interact with customers. From the feedback that chatbots collect by asking simple questions, when analyzed carefully, a brand can make improvements in their service or product. Moreover, the insights gained by chatbots can also help a brand optimize their low converting webpages. For instance, if a landing page brings in massive organic traffic but doesn’t convert well, chatbots can reach out to customers to collect information about why they are leaving the page without making a purchase.


Chatbot technology is opening up a world of new opportunities for businesses across industries and sectors. There will be innumerable chatbot usecases where these intelligent assistants can be deployed and in the above paragraphs I have just highlighted a few of those use cases to get you started. The only advice I will leave you with is that always start with the business problem you want to solve and then evaluate whether a chatbot is the right choice to solve that problem. If yes, proceed or else stop and look for another problem.

Curious much? – Mail me at and let’s start a conversation.

Are chatbots really intelligent?

Are AI chatbots really intelligent?

The first thought that we get, as we come across a chatbot is that, if they are really “intelligent”.  And if they are, then how? Is it some sort of Artificial Intelligence? Prior to entering this field, I thought that the chatbots in retail are just fed with numerous Question and Answer pairs(FAQs). In reality, a ChatterBot seems to be a box of surprises.

What makes a conversational AI chatbot intelligent?

A friend of mine said, “chatbots remind me of kids”. I thought it might be an interesting example to explain how chatbots work. Remember how our parents taught us to say thank you? The picture illustrates 3 scenarios, which are kind of self explanatory.

How chatbots learn

What is interesting here is the 3rd scenario, where nobody is teaching the kid to say thank you, but she still does. 

Here we should notice 3 things:

  1. The child understands from its previous experiences that the 3rd scenario is also about giving and taking. 

  2. The child understands it has received something pleasing.

  3. The child knows it should thank the other person every time it receives something from them. 

How did the child learn this? Here’s where human intelligence plays its role. Similarly, when a machine tries to do the same, it needs some intelligence too – which is nothing but Artificial Intelligence.

Can a conversational AI bot learn?

A conversational AI chatbot just cannot reply to whatever we ask, unless it knows and understands the language we speak. Knowing the language helps the bot to understand the semantics of textual data. The concept of language models help us represent any textual data from a language in the form of numbers, preserving all the semantics! So, does that mean a chatbot can speak any language if we create a language model for that particular language? Indeed!

So now that we know that our ai chatbot can learn our language, it now needs to  –

  1. Understand the intention of the user

  2. Identify any specific entities mentioned in the query

  3. Keep track of the context in which the conversation is happening

  4. Generate a reply to be sent back to the user

Relate to the kid’s example above? The way the kid’s mom taught her, our ai bot too needs someone to teach them. Basically, we need to teach our bot how to perform the above tasks. In technical terms, we call this Machine Learning

Do you see how all these fancy terms come together to form a chatbot? Sweet! 

So, can a AI chatbot answer anything and everything?

Well, depends on how you train them. Usually chatbots are trained to serve a specific use case. It may be for example a customer service chatbot, an ai assistant for retail shopping or could be even industry specific such as chatbots in retail or chatbots in fashion industry.  These domain specific bots are more powerful due to their specificity and hence are more popular as well. However, generic chatbots can also be built which can address more general queries which could be as vague as “what should I do today to stay positive”. These chatbots require a huge amount of data and are often the hardest to train. 


  1. Chatbots are not simply hardcoded machines but use Artificial Intelligence and deep learning techniques to learn from given data to try and imitate humans while conversing.

  2. Chatbots can be trained to serve any specific AI use case or to carry general human conversations depending on the need and specificity.

Do have a look at “Are AI and Machine learning the same” by Tejas Venugopal to get a clear picture of AI, Machine Learning and Deep Learning.  

Also i recommend the article by Joseph Mathew Traditional Online Chatbot or Domain Specific Conversational AI? What can create a delightful customer experience online? to know why domain specific chatbots could be a better choice for your business.

Curious Much? Drop us a note at or visit our website and let’s start a conversation

Are AI and Machine Learning the same?

Are AI and Machine Learning the same?

We have all heard or read about how AI is the next big thing. It seems like every 3rd article or blog is about AI and how companies are leveraging this shiny new tech to solve some of their biggest problems. And the same words are seen together. AI vs ML, Machine learning vs Deep Learning, Neural Networks ….. and so on.

Every so often I get asked (by engineers and non-engineers both) “Are AI and machine learning the same?” So let’s answer this.

What is AI? What are its goals?

I don’t want to give a textbook answer here on the AI meaning. I am sick of them myself. So here it goes…

AI’s primary goal is to create an artificial intelligence. This may or may not include a robotic body as such. That’s only for movies, not in real world always. An artificial intelligence needs to be capable of most, if not all, the things that humans do.

  1. It should be able to learn by observation or actions.
  2. It should be able to decide on a goal
  3. It should be able to create a plan to achieve this goal in an optimal way.
  4. It should be able to sense or feel and have an awareness of its surroundings
  5. It should be able to reason and draw conclusions and so on..

As you can see this is a pretty lofty goal. It is quite abstract as to how this can be achieved. And that’s the main point. AI is abstract in general. It has goals but needs ways of achieving them.

How does machine learning assist AI goals?

Machine learning is one of many tools that is used by an AI to achieve its goals. Machine learning unlike AI is very clear about its goals. Machine learning wants to create function approximations or models for some input and output combinations (we call this “training data”). Using these AI models, it can later generate outputs (we call this “predictions”) on unseen data. To create these models, it uses various AI algorithms which have hyper-parameters to help tune them.A very easy example is,

Input (X)         Output (Y)

1                      3

2                      6

3                      9

4                      12

It’s clear from these combinations that the output is 3 times the input. So the function would be,

Y = 3X

Now this becomes our model. If we have unseen X values, we apply the model to predict the Y values. But of course, the AI algorithm is never this simple in real life. Here X could refer to a vector generated by text, image, audio, etc and Y could be any useful prediction.

These types of predictive models are used by AI to reach its goals.

Where exactly is Machine Learning used?

So we know that machine learning is used to create predictive models. But where exactly are these models used? What can you do with them? Let’s look at some relevant examples for businesses.

  1. Personalized recommendations – When netflix recommends movies based on your previous actions, when amazon recommends products for you to checkout, Machine learning is used to predict them
  2. Search engines – Google uses machine learning to provide you with search results for your queries
  3. Maps – Google uses machine learning to recommend the best route for your journey based to driving time calculations taking into consideration the live traffic and road closures data
  4. Virtual Assistants and Customer Service Chatbot – Natural language processing techniques of machine learning are used to provide a conversational AI experience to the user. This can be used in a wide variety of fields like customer service and customer engagement in ecommerce.
  5. Video Surveillance uses machine learning to reduce human effort by predicting any unusual behavior in video feeds
  6. Face Recognition – Many smartphone providers use machine learning to help you unlock your phone with your face
  7. Spam filtering – Email and SMS providers use machine learning to help filter out unwanted messages

AI vs Machine learning vs Deep learning

This is another familiar question – How is deep learning different from machine learning? If I had a nickel…

Machine learning’s goal is to create predictive models. Deep learning wants to do the same. Really. They’re like twins.

While machine learning likes to use traditional models like SVM, Decision trees, etc Deep learning uses fancier (read as “more complex”) neural network AI algorithms which work like the human brain (in theory). And that’s it. Everything else is pretty much the same.

I usually don’t refer to Deep Learning as a separate term. To me they are the same. Deep Learning is Machine Learning with updated AI Algorithms.


To summarise,

  1. AI vs ML – AI is an abstract concept with many goals. Machine Learning is a specific tool used by AI to realise them.

  2. Deep Learning is Machine Learning with updated algorithms.

For more content on AI and how businesses can leverage it, please check this article from Dinesh Sharma  “Can AI make your business far more intelligent

Curious Much? Drop us a note at or visit our website and let’s start a conversation!

How AI chatbots will transform the retail industry in 2020?

How AI chatbots will transform the retail industry in 2020?

Consumer Good manufacturers are an integral part of the retail value chain and while a lot has been talked about application of AI and Chatbots in retail, this article focuses specifically on how Consumer Good brands too can benefit from chatbot technology. It is a known fact that relationship between brand manufacturers and retailers have always been strained through the decades and the quest for the last-mile control for consumers can be seen with more and more brands adopting a Direct-to-Consumer strategy in recent years. A great example of this being Nike announcing that it is pulling back from Amazon in November 2019 after 2 years of signing the partnership deal.

So can AI chatbots help Consumer Product companies? And if so How?

When I speak to consumer good companies about AI chatbots and their potential to impact P&L, one of the most common objections I get is that “we do not sell online but instead we sell through ecommerce channel partners. So how is AI bot relevant for us?”. Having helped some of the largest global CPG companies implement AI assistants or chatbots over last 3 years, I assure you there is a lot chatbots in retail can offer even if you are not selling online. Here are the top 4 chatbot use cases that you can look to implement in 2020

Top 4 chatbot use cases that you can look to implement in 2020

Top1: An AI Chatbot on the brand’s website helping consumers with their product research

Regardless whether you sell online or not, you still have a website and you still have a steady flow of consumers visiting your website every month. Right? (If the answer to this question is “no” then skip this use case – this is not for you). Your consumers are flocking your website for just one reason. They want to research more about your products, they have questions and are searching for answers on your website and this is your chance to engage them, give them what they need and help them decide. An AI chatbot that has been trained well on your products and knows everything about your brand is a great tool to deploy on your website, as a companion app, making it super easy and convenient for your consumers to find the information they need and also personalize the interaction based on the consumer’s context. With every conversation, it is not just that your AI is learning and getting better, but you are also collecting rich consumer behavior data which, if harnessed correctly, can produce deep and unique precision marketing insights on topics ranging from online experience to new product ideas.

Chatbot on website
Chatbot on Dulux website

Top2: An AI chatbot on select product pages of your ecommerce channel partner’s website

Most of the global consumer product manufacturers sell online via e-commerce channel partners and even if they have a direct-to-consumer strategy, it is likely that a bulk of the online revenue is still coming from e-commerce channel partners. If you are one such brand and if you are thinking how can an AI chatbot help you drives more sales, why not explore with your e-commerce channel partner the possibility of having your AI assistant on your product pages of their website? An AI chatbot trained about your products that can answer questions of consumers instantly is a great tool to differentiate your brand from your competition selling on the same channel partner’s website. But it does not stop just there. Remember the conversation data still comes to you (it is your AI chatbot after all and all interactions with the ai bot gets saved) and your marketers get to benefit from all the insights hidden in these conversations.

Top3: An AI chatbot available through a simple QR Code on your retail partner’s store

Is chatbot technology only for the online world? No, they are not and infact they can be your differentiator even in physical stores. Your consumers are buying your products from retail stores and you are left at the mercy of the store associate to sell your products. Why not have your chatbot made available through a branded QR Code inside the store? Your consumer has a question on your product, she scans the QR Code and your AI assistant pops up in her mobile phone assisting her with her questions, connecting her to your in-house experts seamlessly and also probably offering her a personalised discount voucher instantly. Wouldn’t that disrupt your competition? One such great example is Dulux paints, the No1 paints brand in UK that launched their AI assistant in Homebase stores in UK. (If you are based in London and you want to see first-hand how this works, you should visit one of the Homebase stores and check it out yourself.)

Top4: An AI chatbot that converts banners into conversations using Conversational Ads

Digital Ads in the form of intelligent conversational interfaces gives your brand marketers a new and powerful way to engage your consumers and drive productive outcomes. Banner ads are one directional and non-interactive while conversational Ads are two way interactions that can be personalised to the consumer’s context at scale. Also, imagine the effort and cost this saves you from creating a maze of landing pages, forms and navigation steps on your website prior to launching your Ad campaign only to get people come on your website. With conversational Ads, you engage the right customers instantly and drive meaningful outcomes.

In summary, even if consumers do not buy products from the manufacturer’s websites directly, consumers still expect their favourite brands to serve them and help them make the right choice. AI chatbots offer consumer product manufacturers a whole new opportunity to engage their consumers and differentiate from competition and here are the top 4 ai chatbot use cases   for CPG companies

  • An AI Chatbot on the brand’s website helping consumers with their product research.

  • An AI chatbot that runs on product pages of the e-commerce channel partner’s website helping consumers with their product choice on behalf of the manufacturer bringing the insights back to the brand.

  • An AI chatbot available through a simple QR Code in the retail partner’s store to engage in-store consumers and answer her questions.

  • An AI chatbot that converts banners into conversations using Conversational Ads.

AI Curious 101: What is Artificial Intelligence and Machine Learning?

What is the difference between Artificial Intelligence, Machine Learning and Deep Learning?

How are they related to each other? How do we teach machines to perform tasks?

The world of AI (Artificial Intelligence) is vast. Really, it’s huge. One can spend many years of their life learning and prodding and poking and still just end up scratching the surface. And all the jargons surrounding the field do not help either. Where does one even start trying to understand this beast?


There are many articles on the internet trying to explain AI Artificial Intelligence or machine learning using mathematics and theory. For someone just trying to make sense of this world, this approach is just wrong. The best way to explain any topic is through analogies to the real world. It’s much more relatable that way.

So, read on for a simple everyman’s explanation of machine learning.

I will also use ‘Tech Bubbles’ in a few places to give a better technical explanation of the concepts.

Artificial Intelligence Machine Learning

What is Artificial Intelligence?

AI artificial intelligence is just an umbrella term, a vague idea which describes a class of problems and approaches to solve those problems.

Top Problems in the field of artificial intelligence

  1. Learning
  2. Perception
  3. Planning
  4. Knowledge Representation
  5. Reasoning
  6. General Intelligence

Fields that come together to solve AI problems

  1. Computer Science
  2. Information Engineering
  3. Mathematics
  4. Psychology
  5. Linguistics
  6. Philosophy

This seems like such a random combination of people working together. However, this is what it takes to solve the big problems of today.

Machine learning is a part of AI which deals with learning to optimize algorithms using data.

What is Machine Learning?

So, let’s start with the heavily overused word, machine learning. To understand machine learning, one needs to understand human learning. How do humans learn? and specifically how do babies learn? Understanding this is the key to understanding machine learning.

Machine learning is just an umbrella word to lump in a lot of different concepts. When a machine ‘learns’ something, we call it machine learning. A machine here usually means a software program. For e.g. A machine can learn to recognize objects in the real world (from photographs). Here’s a ball, Here’s a toy, Here’s a dog, Here’s the floor. A baby can do the same, usually much faster. Both of these are examples of ‘learning’

Machine learning or traditional machine learning refers to using algorithms to model/fit the data. The final model becomes a function approximation from the input to the output.     F(x) = y, where x is the input e.g. an image of a ball and y is the output e.g. ‘ball’. Here F is some function which transforms x into y. Algorithms such as logistic regression, naïve Bayes, Random forests, Support vector machines, etc. are popular for traditional machine learning

What is Deep Learning?

This is another word that’s really popular. There’s nothing to fear. Deep learning is a type of machine learning. You see how it’s an umbrella word now?

Deep learning is machine learning where we use more sophisticated algorithms like neural networks instead. Deep learning is a way of solving the same problems, but with approaches which are inspired by the human brain. But ultimately, it’s trying to achieve the same goal. ‘Learn’. It’s used as a powerful tool to solve some of the hardest AI problems. E.g. Natural language processing, Machine translation, Question answering, Object recognition, Language modeling, etc.

Deep learning uses neural networks which have more than 1 hidden layer of neurons. Another difference between traditional machine learning is that the features are selected by the network during training. Certain features of the input may be more useful than others, and neural networks use the concept of backpropagation of the loss to tune the weights of these features and every layer in between.

The Attentive, Distracted and Lazy Parent

But how does the machine actually learn? And how good a teacher/parent do we need to be to teach it. Can we be the attentive parent and spend all our time on it? Can we afford to be a bit distracted? Will the machine still learn? Or can we be completely lazy?

Stay tuned for more in our next blog

You can have a look at these:

Why AI Chatbot for Retail Business?


Why AI Chatbots for your retail business?

Why AI Chatbots for your retail business?

When digital marketers and customer service agents think of “chatbots,” they typically think of an automated text-based response program that can only do mundane automation tasks such as answering FAQs. Think of a complex query, and the belief is that ‘a bot will fail’. This is a big underestimation of chatbot software’s capabilities as I have learned over the last 2 years of our conversational ai startup journey. Use this technology for the right use case in your retail business and you will realize that a bot is a lot more than automated text response. A conversational chatbot is a very powerful marketing tool! What matters is the use case and when used correctly, a bot can offer brands exciting marketing benefits such as providing product information directly to prospects and customers, spreading brand awareness at scale and collecting data on market trends and customer service issues.

If your business hasn’t yet implemented an AI chatbot in Retail yet, now is the time to do it. Here are some arguments on how a bot can give your business an edge in your market.

As a Shopping Assistant (Chatbots) in Retail, can convert prospects to paying customers

A smart bot can today answer questions which were considered impossible to answer by a machine five years back. Train the AI working at the back-stage of your chatbot on your retail products data and on your customer service queries, and in a matter of days, it will boost your customer engagement on your social media pages and website leading to far higher conversions.  As a proof point, for one of our customer – a fortune 500 CPG global brand in The Netherlands, our retail AI chatbot has influenced 10X conversions across multiple countries and channels while at the same time learning continuously about the brand’s business from its customers. Also, Juniper Research in its report released on May 2019, says that retail sales resulting from chatbot interactions will reach $112 billion by 2023. That surely makes a great business case – isn’t it?

Chatbots Bots don’t sleep. They are always available and most often accurate.

Your customer support chatbot provides service to your customers twenty-four hours a day, regardless of any circumstance (except technical failures). Moreover, they are quick and efficient – when a customer messages your AI chatbot, they get a fast response. This sort of anytime availability can greatly boost your brand reputation. As an example, one of the customers in the UK looks at the AskSid conversational AI solution as a potent way to establish her brand as ‘the most helpful brand in the UK’.

As Virtual Customer Assistants in your customer service team 

As consumers, we hate the term “automated customer service” because it basically means being met with a boring and frustrating IVR – “press 1 for support, press 2 for complaints” etc. In this instant-gratification age, a pre-recorded phone message is desperately outmoded. Do you remember when was the last time you called your favorite brand’s call center and got overjoyed and ecstatic about your experience? I don’t and probably you don’t either.

Chatbots have made huge strides in automating customer service queries – not just simple ones but even complex queries such as product related queries and product recommendation queries. Let your chatbot handle the simple customer service problems and direct the more complex issues to your customer support agent. For one of our customer in Europe, AskSid conversational AI solution has delivered automation equivalent to adding 8 extra agents at 20% the cost. Isn’t that awesome?

Precision marketing insights from Chatbots messages

Many companies record and log conversations with customers—the all-too-familiar phrase “this call may be recorded for quality assurance” and those communications are often later used to analyze customer pain points and market trends. However, there is effort involved to create those call logs, review the data and build metrics and reports that can then be submitted to business stakeholders for decision making. A chatbot can automate this entire process for you. All communication messages between your customer and your bot get stored automatically and with the press of a button, you can get all the necessary insights out and delivered as dashboards to your business.

Furthermore, the data collected by your conversational AI solution can be used to create personalized communication with your customer, improving customer relations and the overall service experience. Chatbots in Retail have been proven to inherently increase engagement by giving the customer an impression of being personally serviced – something that even the best videos and websites simply cannot do.

In summary, conversational AI technology in retail is the future of customer service with limitless possibilities for your business if used appropriately against the right use cases. No wonder Gartner in its recent report says that 25% of global brands is going to integrate virtual customer assistant technology by 2020, up from 2% in 2017.  So if you are digital marketeer or you manage customer service of your business, 10X conversions and 3X cost savings are your reasons on why you should no longer ignore this AI technology anymore.

(If you wish to know more about, we are available at Just drop us and note and we will be glad to show you a demo of our solution)