Interactive AI Podcasting Debut


If you like listening to a podcast while taking a walk, you are one of millions of people who enjoy doing this every day. Now, you can experience something totally new: interactive AI podcasting. Instead of being a passive listener, you control the flow and use of the content. You curate your own podcast experience.

What is an Interactive AI Podcast?

Interactive AI podcasts allow you to:

  • Have dialogue like talking with an assistant
  • Skip to the next story or next subject matter
  • Ask questions/get answers about something you heard in the story
  • Repeat sections of importance or pause for thinking
  • Express your opinion and provide feedback simply by talking
  • See images and videos accompanying the storyline

Interactive AI podcasts allow the content creator to:

  • Have the AI computer voice the story automatically
  • Learn where listeners skipped and disliked content
  • Understand what questions were posed, and what engaged listeners
  • Receive listener opinions and feedback
  • Overcome the limitations of conventional podcasts as described above

Try Dr. Margo, Interactive AI Podcasting, Subject: Coronavirus


Try the BETA version of interactive podcasting (links below)! The best experience is designed for the mobile use (wearing headphones. The link to download mobile app iOS is here, and Android is here. Mobile apps have complete voice interaction – say or click on “Podcast” to start it, then say “stop podcast” to end it. The app also provides images and videos accompanying the story. Use headphones!


The link for Dr. Margo is here where you can test her using the Web browser. Make sure to click on the speaker button to hear the podcast (the button is at the bottom inside the search box.) Note that the Web browser version does not take your voice, it only takes your typing. Dr. Margo’s virtual expert will continue servicing after the podcast with questions and further information about the coronavirus.

A New Approach to Education and Corporate Training

Podcast can be an effective educational tool. Now that is enhanced by interactive AI control. Most importantly, the listener can talk to it just as talking to a teacher or a tutor.  Once dialogue is introduced, the most important element of learning starts to emerge.

The beauty of mobile phone technology is to connect us to an information source via headphones while we are busy with mundane things in life. Working out, cycling, walking, cleaning, gardening, etc. all may be accompanied by a podcast, as we multi-task and expand our potential. Interactive AI Podcasts allows the listener to pause, repeat, ask a question, or skip ahead. These are all basic functions of learning, which are further enhanced by images and videos.

Turn Your Documents into an AI Podcast

This new technology was created by exClone, which now offers its platform to you to try Interactive AI Podcasting. Click here to request a demo. The platform will be accessible by simple subscription soon.

Happy interactive podcasting!


This article is brought to you by exClone.

Request a Demo from exClone

Join CHATBOTS group in LinkedIn.

You can follow exClone in Facebook, and in LinkedIn.

exClone App (iOS) Ecosystem of virtual experts (beta)

exClone App (Android) Ecosystem of virtual experts (beta)

Artificial Intelligence to Help Fight Pandemics like the Coronavirus


A Forbes article published last week reported that Chinese chatbots (WeChat and Alipay) were used to suppress the spread of the Covid-19 virus. Although the chatbots did something unacceptable in Western societies (i.e., using the assigned color codes like red, green, or yellow to indicate individuals’ freedom level for travel and social activities), they produced effective results in a short period. And the article mentioned nine other ways that AI can be useful in such circumstances.

When it comes to disseminating credible, useful, and unique information, chatbot technologies can deliver valuable insights promptly and accurately. For example, the question “Is plasma donation approved by the FDA?” produces a clear answer by exClone’s virtual expert, Dr. Margo, compared to Google search results.


On the other hand, asking Google the same questions produced contradictory results written in a language that is not easy to understand (April 26, 2020, New York.)

The virtual expert technology delivered by exClone does not only produce more precise answers to single-step questions, but also engages the user in a multi-step dialogue investigation, very similar to how a human expert would deliver advice. The important point here is the capability of the computer to ask the user questions to provide better answers as shown in the example below.


Google, Alexa, or other similar assistants do not ask the user questions for a more refined answer. This is the fundamental difference between the exClone’s dialogue technology (based on AI) versus short cut coding efforts devoid of AI.

exClone’s Dr Margo is a virtual expert that encapsulates knowledge from credible sources (curated by human experts) then disseminates accurate answers in a multi-step, human-like dialogue. The human expert can continue teaching the system after deployment by just talking to it.

The BETA version of Dr. Margo is available via mobile apps (with voice interaction like Alexa) or by the Web app at this link.

Enterprise IQ and Virtual Experts

In its simplest form, the Enterprise IQ concept assumes an imaginary brain of an organization where all know-how and expertise are gathered, then distributed at maximum scale so that the workers can utilize it rapidly and effectively. The AI application of Virtual Experts helps this vision to become a reality as summarized below.

Cloning Experts to yield Virtual Expert


Cloning experts refers to capturing the knowledge of an expert and being able to apply it when appropriate. The curation of the expertise may include documents, reference materials (such as books), articles, news feeds, conversation logs, and media sources like videos. The curator can be an expert person, or a group of experts. Personal choices and dialogue behavior can also be adjusted. The expertise captured by digital cloning is delivered to the end user by a conversational (chatbot) interface. An example is shown below for the particular expertise of Crystallography.

Teaching the virtual expert can continue after the deployment by allowing designated users to teach it via conversations. Such a cloning process makes the in-house expertise captured, preserved, and protected in case of experts leaving the enterprise. An enterprise can launch as many virtual experts as necessary to help its workers and/or customers, or launch a master virtual expert to handle all the subjects.

Expertise Accessible by the Masses


The most important function of a virtual expert is its scalability where 1000s of people (workers and/or customers) can converse with it simultaneously. The value is realized when critical questions are answered instantly without the need to talk to the human expert. The only alternative to virtual experts, today, is going through document stockpiles to find answers manually (or by rudimentary search engines which are notoriously ineffective).

Being able to access expert knowledge instantly via natural language dialogue is an enhancement to Enterprise IQ and improves bottom line.


This article is brought to you by exClone.

Join CHATBOTS group in linkedin.

You can follow exClone in Facebook, and in LinkedIn.

Request a Demo from exClone

Download exClone App (iOS) — Ecosystem of virtual experts (beta)

Download exClone App (Android) — Ecosystem of virtual experts (beta)


#AI #Experts #EnterpriseIQ #Virtualexperts #Voiceassistants #practicalAI #chatbot #chatbots #artificialintelligence #ConversationalAI #Virtualassistants #bots #machinelearning #NLP #DL #deeplearning

Originally published at

Cortana Out exClone In

recent article reports ” Come the end of January, it appears the Cortana app’s getting booted to the Microsoft assistant graveyard. At least poor Clippy will have some company now. That’s according to a support article Microsoft posted to several regional markets this week.” After Siri becoming a laughing stock, Cortana’s departure is not surprising. These “can-do-it-all” voice assistants are simply not delivering the AI promise. Their utility have been questioned with the exception of Alexa due to its clever commercial use attached to playing songs.


Instead of “can-do-it-all”single voice assistant, exClone has just released an app (experimental) that is an ecosystem of virtual experts (chatbots). Starting with 8 examples, each virtual expert is focused on a different subject as designed by its owner. Contributors to the ecosystem can be anyone or any organization who can clone themselves into a virtual expert via exClone’s platform. The cloning process requires nothing but documents (Word or PDF) that contain the knowledge of potential conversation with the visitors. Contrary to “can-do-it-all” attitude, this environment offers number of virtual experts (conversational agents with voice). Once the ecosystem reaches its maturity, finding the relevant virtual expert will be easy via a category search function (i.e. HEALTH, LAW, ART, etc.)

Download the App


Please download the exClone app from the links below. If you already have it, you should update it with the latest version. Please bear in mind, this is an BETA test.


New clones/virtual experts are added regularly without the need for you to update the app. Notifications will highlight the newly added clones and their content changes.

Practical AI: Deep Learning Costs Reduced 100 times via Instant Learning Yielding Industry Level Performance

In reference to my earlier post about the exClone Case Study reported by Forbes, the future of conversational AI signals a shift from data-driven, expensive, and lengthily methods to knowledge-driven, affordable, and fast methods. In short, it boils down to Deep Learning (DL) versus Instant Learning (or its derivatives).

The two different approaches are summarized in the diagram below.

Linguistic NNET

Practical AI, the right side of the diagram above, uses the existing knowledge on linguistics, ontological semantics, psychology, neuro-sciences, and other cognitive sciences. The resulting hybrid method reduces the load of a machine learning algorithm, turning it into a mere knowledge absorption step from documents (similar to how we read and learn). These documents are about the subject matter of which the conversational system talks about, but nothing more. Simplicity and speed give it the name, instant learning.

Conventional AI, the left side of the diagram, dismisses most (if not all) the existing knowledge, and assumes to solve everything by data crunching. The required data set is assumed to contain examples of all cognitive skills in language processing which is an overly optimistic (if not impossible) expectation.

The Cost Issue

When you have to acquire, validate, and process data, the costs can sky rocket. In my earlier article, the example of Morgan Stanley’s AskResearch system, which is reported to bring answers to somewhat mediocre questions like “What is Morgan Stanley’s standpoint on gold?”, took 1 year to train the system. Obviously, the costs associated with such a process, and data services, would wind up in 7 figures. Not to mention the cost of the required staffing, and the repeating cost cycle in every correction attempt.

In contrast, the practical AI example of exClone’s deployment of Virtual Experts for enterprises can cost 100 or 1000 times less. Because, no data is utilized, no AI staff is required, no coding is necessary, no long training cycles are endured. The only required effort centers around editorial, document management, and curation.

If engineering means finding the most practical and affordable solution, then the sole DL application to NLP may be the worst engineered systems to date!

The Difficulty Scale of NLP

One common problem I see in the DL community is the unawareness of the difficulties of different NLP problems which reminds me of the saying “if the only tool is a hammer…” I made a conceptual scale as shown in the diagram below. Some may argue the ranking of few items. Nevertheless, the exponential nature of the complexity involved in these different problems is indisputable. For example, if your problem at hand is Text Labeling, you are light years away from handling Abstraction. Accordingly, if a DL approach proves successful in the former, it does not mean its readiness in the latter. The differences are huge.

NLP Scale

More drastically, data-driven methods have inherent limitations to handle higher level NLP problems no matter the size of the corpus. At the lower end of the scale, most DL applications can be duplicated by statistical linguistics (such as in sentiment analysis) which begs the question “how much better is the conventional AI?”


Data is expensive and risky. Data driven methods make sense to attack problems of high level complexity where (1) the underlying principles are not well known, such is in stock market analysis, or (2) the complexity arises from multi-body nature of the problems, such as in atmospheric modeling or image processing. Applying DL to NLP is treating NLP like atmospheric modeling. More sensible approach is to utilize available knowledge at its maximum, then apply machine learning for the remainder of the problem. This requires innovation of hybrid systems. exClone’s instant learning technology is one good example, however more hybrid solutions are expected to emerge in the near future.


This article is brought to you by exClone, a Virtual Expert & Chatbot technology provider via its proprietary Instant Learning technology.

#AI #ArtificialIntelligence #virtualexperts #chatbots #conversationalAI #ML #DL #deeplearning #Machinelearning #exclone #NLP #humandialoguetheory #instantlearning #virtualreality #VR #StanleyMorgan

exClone Launches Virtual Experts at Black & Veatch to Enhance Knowledge Utilization by Artificial Intelligence


NEW YORK–(BUSINESS WIRE)–Today, exClone Inc. announced the launch of its AI-based virtual experts at Black & Veatch as an enhancement to enterprise knowledge capture, utilization, communication, and search functionality.

exClone’s virtual experts open a new, unprecedented window of communication between experts and employees in an enterprise. In addition to the documents of expertise written in the conventional manner, experts now may be represented virtually through a conversational AI system (chatbot) where the embedded knowledge comes from exClone’s platform that converts documents, such as MS Word or PDF, straight into chatbots. The conversational interaction delivered by such virtual experts helps workers access critical knowledge in a more productive way than by other conventional means such as search engines.

exClone’s technology of converting documents into chatbots does not require any coding, availability of large data sets, long training cycles, or experience in AI. After deployed, the technology also allows “on-the-fly” teaching of virtual experts through conversations undertaken by designated teachers. As a result, virtual experts remain dynamic sources of knowledge updated as often as needed without a redeployment process. Workers’ unanswered questions beyond the scope of the deployed knowledge may be quickly answered by designated teachers thus introducing a new social connection and communication paradigm across the enterprise.

Alan Young, the CEO of exClone, said, “If messaging tools can be used to get answers from friends, we should be able to get answers from virtual experts embedded with knowledge from enterprise documents.” He added: The connection between experts and workers in an enterprise is elevated to a new dimension with virtual experts, and we are proud to lead this new paradigm with visionary companies like Black & Veatch. “We’re excited to deploy and leverage this new connectivity tool for our professionals and capitalize on the efficiencies we believe it will bring to our business,” said Mike Etheridge, Global Chief Engineer for Black & Veatch’s water business. “This tool will help our professionals to find information quicker and harness knowledge and expertise from our global workforce to drive efficiency and effectiveness in new ways moving toward the future.”

About Black & Veatch
Black & Veatch is an employee-owned, global leader in building critical human infrastructure in energy, water, telecommunications and government services. Since 1915, we have helped our clients improve the lives of people in more than 100 countries through consulting, engineering, construction, operations and program management. Our revenues in 2017 were US$3.4 billion. Follow us on and in social media.

About exClone
exClone, Inc. is a New York City-based technology company specializing in virtual experts, chatbots and conversational AI systems to enhance enterprise knowledge utilization, communication, and search functionality.


Turn your MS Word, PDF Documents Straight into Chatbots: Virtual Experts


It is finally here. You can now convert your MS Word/PDF documents into Chatbots and Virtual Experts with exClone technology. No coding involved, no data sets to mingle with, no long training cycles, no experience in AI. This is the highest level of automation in the market today where all AI functions are tucked under the hood, invisible to a chatbot builder. As a result, the path between an expert and his/her virtual version involves no other process/developer in between.

A Chatbot Learning from Documents Becomes a Virtual Expert
Siri, Cortana, Hey Google, or Alexa, lack any expertise they can chat about. If a question is asked with some complexity, they point you to search results. exClone’s process yields a virtual expert where questions are answered about the particular subject. Here is an example, Frank, who is a virtual expert on crystallography solutions using Phenix software system. Frank was built straight from MS Word documents in a single step process (we call it Instant Learning). The documents were written and curated by a real expert.



On-the-fly Learning by Conversations with Teachers After Deployment
In addition to learning from documents for deployment, exClone offers teaching virtual experts on-the-fly through conversations by designated teachers after deployment. This has a number of advantages one of which is the ability to update the system with new or modified knowledge anytime without the need for re-deployment.

Answering Questions at the Concept Level


The most powerful feature of the exClone system is its ontological answering capability where words of the question and its answer don’t match, but the concepts they refer to do match. The proprietary machine learning algorithm (Instant Learning) is able to achieve an almost human level of understanding when answering questions. This means that the system can handle hundreds of various forms of a single question, which points to the same meaning, thus can bring the same relevant answer. This is the ultimate goal in making computers understand language and learn knowledge correctly.

What does this Mean for Enterprises?
Documents in the world of enterprise are the main asset to encapsulate and preserve organizational expertise. Being able to create virtual experts out of these documents easily, with no specialized effort, means that it is now scalable and inexpensive to launch enhancements to enterprise searchhelp deskcall center, and training systems.

With virtual experts, the workers and customers of an enterprise can access critical information via conversational (messaging) type interface, rapidly, accurately, and efficiently. Such an efficiency directly improves bottom line.


Request a demo at

Machine/Deep Learning to Include Evolutionary, Experiential, and Instant Learning Components

In our quest to understand and replicate the cognitive capabilities of the human brain, the AI discipline has focused on the subject of learning rather unevenly. Regardless of the non-scientific reasons, I felt compelled to raise awareness of the most important 3 components of learning mainly distinguished by the “time” factor. Evolutionary, Experiential, and Instant learning. Without taking into account all 3 forms of learning, it is unlikely to achieve ambitious goals in AI regardless of how much computing power, or data collection is available to us. The diagram below summarizes this concept.



When a wildebeest calf is born, it takes only a few minutes for her to run fast enough to escape from predators. It is obvious, evolution has hard-wired some of its learning in the blue print of a new born calf in terms of motor skills. Evolutionary learning is also obvious from the distinct regions of a biological brain which is almost always utilized in a predetermined manner. We can argue that human specie has developed a unique neuron structure suitable for language and logic in response to survival pressure through evolution. If this is true, then the idea of “linguistic neuron” could be what separates us from animals.

Has human specie developed language sensitive neurons in the brain through an evolutionary process so that some neurons take on linguistic roles?

Evolutionary learning is like a factory setting, initial condition, or starting assumptions of any model we want to build for specific learning task. This initial condition step is what is missing in today’s deep learning methods.



Once a biological system is born, experiential learning starts along with the growth of the brain. In case of humans, many activities like walking, speaking, learning how to ride a bicycle, or playing piano fall into this type of learning where repetition is the key. Today’s deep learning methods heavily focus on this model using artificial neural networks. Unfortunately, the network types and learning algorithms do not start from any biological inspiration, and there are no initial assumptions targeted to a certain type of learning. Consequently, most applications turn into a nonlinear mapping exercise rather than modeling a real learning process.



One of the most obvious, yet mysteriously ignored form of learning is instant learning. In case of humans, cognitive activities like reading, conversing, deducing, summarizing, abstracting, and conceptualizing require very small number of iterations to learn. If you ask directions on the street, repeating it twice would be more than enough to learn it. If we are studying a subject, we may have to read it a few times. That is instant learning. You cannot replicate this type of learning using today’s deep learning methods. Assuming the evolutionary learning has yielded a hard-wired design of linguistic neurons, we are experimenting with instant learning at exClone with promising results. In applications involving natural languages and human like dialogue, we believe that the 3 forms of learning is essential to complete the picture. More details are in my previous article about instant learning.

One of the examples that I have come across recently is the RBF learning which is another form of instant learning without mentioning the arguments described above. Their point of departure in RBF Learning is the industrial demand for instant learning systems.

If you know a new learning algorithm relevant to the arguments above, please mention it in the comments below.


This article is brought to you by exClone, a Virtual Expert & Chatbot technology provider.

Join CHATBOTS group in linkedIn.

You can follow exClone in Facebook, and in LinkedIn.

#instantlearning #deeplearning #chatbots #conversationalAI #AI #ArtificialIntelligence #ML #DL #Machinelearning #exclone #virtualexperts #NLP #humandialoguetheory

eTravelSafety Signs on exClone’s Virtual Expert AI Technology


eTravelSafety, a UK firm based in Hereford, who provides corporate travel safety training and technology solutions, have signed on the Virtual Expert technology offered by exClone. The project aims at providing the first ever interactive travel safety training to their user by a virtual expert (an Artificial Intelligence application) who is able to deliver relevant training videos and answers to questions on demand. This approach of utilizing cutting-edge technology is a visionary step where a high-degree of interactivity makes a competitive difference. The product launch will be announced soon.

James Barton, CTO of eTravelSafety says “Working with exClone on our new first-in-the-market Travel Safety Virtual Expert represents a quantum leap in Travel Safety training, allowing travelers to quickly access and interact with powerful training in a way that meets their needs. After looking for partners, The exClone platform provided us with the very best in AI technology, and the best partners to support our desire to provide Travel Safety to everyone”


We all know virtual assistants like Siri, Alexa, Hey Google, Cortana, etc. Virtual assistants do not contain any specific expertise, nor can they converse about any particular knowledge. Their tasks are rudimentary in the category of pointing, arranging, organizing, playing songs, or scheduling. Virtual Expert is the next step-up where the conversational AI system can talk about a particular expertise. It is technologically much more challenging than its counterparts.


A corporation may have a specific expertise captured in a bundle of videos, much like eTravelSafety do. There may be tens of thousands of answers embedded within these videos that a user can benefit from. There are two distinct advantages of virtual experts in such cases.

  • The BUNDLE EFFECT: Ability to locate the most relevant video from a bundle in response to a question asked by the user.
  • The INTERACTIVE VIDEO EFFECT: Ability to answer a question promptly relevant to the content presented in a video.

An example of a Virtual Expert is shown below where a video (on the left) is wrapped with a conversational interface (on the right) and loaded with knowledge that can (in some cases) go beyond what is included in the original video itself. Not only can this system bring answers from the video content, but it can also suggest other videos more appropriate for the question.



Interactivity is the future. Elevating any content to the level of instant conversational engagement holds the obvious key to competitive edge.

You cannot ask a question to a video, slide deck, document, image, diagram, podcast, Web page, etc. But you can ask to its virtual expert as an interactive wrapper.


Creating a virtual expert is mainly an editorial process via the Instant Learning technology offered by the exClone platform. The process involves curating documents of expertise and rendering them into the system. There is no coding involved. Training the system is a single step machine learning process using the content only, devoid of large data requirements.

But the creation process can continue after deployment. Designated teachers can chat with a virtual expert to add more knowledge without re-deployment. This allows organic growth and instant modifications/additions to the system.


This article is brought to you by exClone, a chatbot technology provider.

Visit eTravelSafety, in FacebookLinkedIn.

Join CHATBOTS group in LinkedIn.

You can follow exClone in Facebook, and in LinkedIn.

#virtualexperts #travelbot #instantlearning #deeplearning #chatbots #conversationalAI #AI #ArtificialIntelligence #ML #DL #Machinelearning #exclone #etravelsafety #NLP #humandialoguetheory