The next release of Ida, our digital assistant, will be available for customers beginning at the end of September, 2021. This post contains the highlights of this release which focused on automation and improving the ROI of digital assistants.
21.03 in Summary
21.03 includes many fixes and enhancements with a focus on the Feedback Loop process and the new Oracle Digital Assistant (ODA) NLP module. We are making the process of giving the machine feedback easier, more streamlined and efficient so it takes you less time each cycle. Ida’s Feedback Loop is a differentiating feature which drives its high accuracy marks.
Ida also adds improved automation to accuracy tracking and will now warn you when accuracy starts to slip or there is a growing concern. This will save you time from having to analyze reports and instead just grab your attention when your attention is needed.
Improved user experience features are also part of this release such as the new ability to rate, trap and provide custom outcomes when users are expressing frustration. An example of this is getting them over to a live agent when you sense they are growing frustrated.
The Ida library was also updated and we now have hundreds of pre-built skills for employees, managers, students, faculty, advisors and guests. You can read more detailed release notes below.
Bulk Import/Export Utility for FAQ+
Streamlined CV Configuration Page
Streamlined bot build process
Updated Ida catalog & training data
Autotest support for negative testing
Improved Feedback Loop labeling/help
Ability to record who initiated a chat via handoff
Improvements to Lightbox UX in Feedback Loop pages
Adjust bot export process to allow “empty” NLP Segments
Automated topic-level training data management
Improved QA autotest output
Last Accuracy KPI Dashboard Tile
Accuracy Leak KPI Dashboard Tile
Streamlined UI and choices for Feedback Ratings
Feedback Loop: New unrated option for ‘too vague to rate’
Trap frustration utterances and direct accordingly
Fixed show utterances in FBL in some use cases
Improved thumbs rating UI
Metrics Report: Sort location data by conversation count
Add DE branching logic support for auto-suggest inputs
Friendly not authorized message when guest-to-auth handoff fails
MS Teams Authentication updates
Improved translation performance for HTML responses
Improved filtering and defaults for Feedback Loop
Allow small talk decoupling in a digital assistant setting
Support for custom disambiguation response pre-text
Updated Feedback Loop Metrics Report to accommodate data model changes
Scheduled archiving of old Feedback Loop and Autotest data
jQuery conflict resolution for chat ui
Contact us below to learn more and setup your own personal demo:
Ida 21.02 will be released and available for customers beginning at the end of this month. Here are the highlights in this release as we continue to fine-tune the incredible accuracy performance we see from Ida as well as make various bug fixes and improvements.
No-match text is now configurable
Feedback Loop language toggle button styling changes (see both English and native languages used in this tool)
Capturing auto-utterance & initiator analytics to better understand who is handing off to Ida
Add Oracle ODA 20.09+ NLP model support for improved accuracy
Manual chat-ui language setting to force a specific language vs. auto-detection
Pruning features for audit data
Pruning & archive features for chat data
Check skill version against IUC version prior to testing
FBL Row Padding Fixes
Clean up Thumbs UI/CSS/HTML
Support separate DE processes for Help FAQ and NLP Failure process
Easy On/Off for Thumbs user satisfaction ratings
Audit reports for blank lines in answers
New 80/20 split administration page for training/testing data sets
Feedback loop now filters at server for improved filtering
Fixed MS Teams Variable Error
Now Capturing MS Bot User ID values
Product Update Notes
The focus for this release was to continue to improve NLP and utterance matching performance even beyond the 90% mark most of our clients are seeing. The central part of this improvement is supporting updated NLP models. As part of this support, the automated regression testing was significantly changed to more closely model real life thereby ensuring better quality assurance.
A series of features were added to understand how Ida plays in the larger context of an enterprise by tracking any referrals it gets, where it is being used and what channels it is running on (such as Microsoft Teams).
Next we have features added for better multi-language support such as now having a choice between a configured language for a user vs. auto-detection. Additionally, the language being used can now be passed to integrated systems for an end-to-end experience in your language.
We continue to add more skills to the library of Ida. Clients can get up and running quickly by using this catalog. Recently we have been adding content around the return to work/campus. Finally, many bug fixes, performance improvements and other minor updates are included.
Contact us below to learn more and setup your own personal demo:
At IntraSee, we have been proponents of automation for a very long time. Every new industrial revolution has taken place because a new way of automating things was discovered. In the world of digital assistants (aka extremely advanced chatbots), the benefits of automating both conversations and back office activities were obvious: reduced operating costs and a better user experience (UX).
But despite the glaring need for more automation in the workplace, many organizations have been slow to make it a priority. And then COVID happened. In a matter of weeks, automation went from a low priority to mission-critical for many executives.
A recent study by Bain & Company brought to light a dramatic switch in how organizations now view automation as a way to create business resilience and mitigate risk during a crisis.
As you can see, the COVID crisis has acted as a major jolt to companies globally. The ability to successfully navigate any crisis with the least impact to how the organization is run is now deemed as the number one reason for implementing an automated solution.
Business continuity during any crisis is best ensured by automation. And if this also brings lower operating costs and higher quality, then it should be a slam dunk decision for any organization.
And because of this, barriers to automation are coming down, right across the board, due to the current pandemic.
What is very clear is that executives have made a massive shift in how they intend to use their technology budgets, and for the upcoming year resources will be focused on the automation of the Enterprise, and previous barriers are all being swept to the side.
And this shift shows up in what has actually occurred since the pandemic kicked in. Looking at the chart below, you can see the adjustments being made that are primarily based on workforce actions – which is what you would totally expect. But you can also see that automation has now become a key focus in terms of delivery-based actions.
Even before COVID, automation was on the roadmap across all industry sectors. Only now the focus has intensified.
Bain’s conclusion as to the impact of automation as a pandemic risk mitigation strategy:
While Forrester proclaimed:
The COVID-19 health crisis is on everybody’s mind. Once it passes — which it eventually will — one of its lasting legacies will be a renewed focus on automation
Meanwhile IDC noted:
“I haven’t talked to anyone who’s not doing automation as a way to become more competitive, and more resilient.”
AI in the workplace is set to explode in 2021 as part of the fourth industrial revoluton and the move to AI-fueled automation. COVID-19 has not slowed down this move. Quite the contrary, the current pandemic has accelerated the move to automation as a means of ensuring business-as-usual during a crisis.
Digital assistants are the most logical next step for automating how your entire organization interacts with the Enterprise. Given that, it’s clearly time to implement a robotic means of ensuring business resilience in the COVID and post-COVID world. And if you can reduce operating costs, and improve the UX, all the better.
If you would like more information, or would like to see a demo of how to automate your Enterprise, please contact us below
Statistical analysis revolutionized the game of baseball, to the extent that every single team in the major league now employs a huge stats team that drives almost every decision the organization makes. The days of a “good eye” and a “gut feel” being the deciding factor are long over. Now, it’s all about the numbers.
And the parallels to the world of digital assistants are remarkably close. Successful implementation of a digital assistant solution entails applying advanced statistical techniques to both measure and improve performance. The premise being:
“You can’t manage what you can’t measure”
– Peter Drucker
So, let’s start with the concept, and then examine the details behind the ways that the worlds of baseball and digital assistants collide.
The lesson from Moneyball was that smart organizations could compete with the likes of the Yankees if they used their limited financial resources in ways that were much more efficient. If they could generate a hundred runs a year by spending $1M, while the Yankees were spending $10M, then they would level the playing field. Doing more with less was possible if organizations could change their traditional ways of thinking.
And so it is true in the world of digital assistants. If somebody offered you something ten times better than what you already were paying for, and it happened to also be twenty times cheaper (at least), wouldn’t it make sense to switch to it?
This is the new world we live in. Humans are fantastic are doing certain types of things, and woefully inefficient at doing others. And digital assistants just happen to be great at what humans are poor at. Humans can’t infinitely scale, they also can’t remember thousands of key facts, or update hundreds of records in a few seconds. Humans forget things, are not always fully motivated, and no matter how much you invest in them, humans will eventually leave you.
Digital assistants are the new Moneyball. If you choose the right one, and pay heed to how you implement and grow your new digital worker, it will allow your organization to provide a better service at a tiny fraction of the cost you are paying now.
2. What is a good accuracy score?
It has been said that hitting a ball in major league baseball is the hardest thing to do in all of sports. Yes, hitting a gently tossed baseball in your back yard is something almost anyone can do. But hitting a 92 mph four-seam fastball from Clayton Kershaw? Well, that is something very few people can do.
In the world of baseball, making contact with the ball is considered job #1 of the batter. In the world of digital assistants, being able to accurately respond to a human request is likewise considered job #1.
In baseball, a batting average of over .300 is considered excellent, over .350 is elite, and anything close to .400 is other-worldly. With digital assistants, over .800 is excellent, .850 is elite, and .900 is other-worldly.
Note: there are caveats to this that we will address is subsequent points.
In the following chart, extensive testing (2,500 questions) of the major consumer facing digital assistants took place, where voice recognition was removed as a factor such that this was purely a test of knowledge matching. What was even more interesting was that the test also measured how often a question was attempted to be answered, as well as how accurate it was when it did attempt the answer.
Comparing the results below you can see that some digital assistants attempt to answer (swing the bat) more than others. Plus, the accuracy (makes contact with the ball) is also very different too. Google and Ida both hit in the 80’s. Cortana attempts to answer just over 80% of the questions, but only gets it right just over 50% of the time. Meanwhile, Siri swings at the ball 40% of the time, and even then only makes contact 70% of the time. Which is extremely poor.
Please note: the scores from Ida are results in production environments across multiple customers and are an accumulated average. Also, Ida is being asked questions that are specific to a client’s organization that also may be specific to individual employees, managers, students and advisors. Therefore, the degree of complexity is much higher.
3. Batting Cage Averages
There’s a reason that when batting averages for a player are published that they only include stats captured during an actual game. All players look great in the batting cage, as the degree of difficulty is much lower, and, generally, the player knows exactly which kind of ball is being pitched to them.
Ted Williams was the last player to hit over .400 for a season in 1941. Almost all players hit over .400 in a batting cage. This is why when you see published stats for digital assistant accuracy, it’s important to know that the stats published came from actual usage in a production environment, and weren’t just the result of testing taken place in a QA environment with a bunch of teed up utterances that didn’t truly test the ability to match accurately.
Just as an FYI, we run over 10,000 test utterances against Ida any time we make any change. And in QA Ida scores over 97% accuracy. Whereas in production, in client environments Ida scores around 85%, and that’s the number we publish.
4. The Curve Ball
While it’s obvious why Clayton Kershaw is harder to hit than a pitching machine, it may not be so obvious why humans interacting with a digital assistant is so much more difficult to handle than test utterances in a QA environment. So, let’s do this with some examples:
Now, let’s see an example that a human actually typed:
As you can see, as much as vendors try and emulate utterances in their DEV and QA environments, what actual people say often comes out of left field and can really fool a digital assistant that lacks the technological maturity to filter out the essence of what is being communicated. Complex utterances are really the equivalent of the curve ball in baseball (or splitter, slider, etc.).
5. Swinging the Bat
So, exactly how does a digital assistant know when to try and answer a question (swinging the bat) and when to claim ignorance (lay off the ball)? For many it’s a simple case of confidence levels. When an utterance is passed to an NLP engine, what gets returned is a list of possible things it thinks it has a match to, plus a confidence level attached to each one. Then, for a basic digital assistant, it’s just a case of selecting the one with the highest ranking and presenting that to the human. Sometimes the digital assistant will also include, as an act of disambiguation, a list of those things that are closely grouped in confidence levels.
For really advanced digital assistants like Ida that use nested NLP techniques, much more complex algorithms are used to determine what to present and how to present it. But, ultimately, everything is a combination of either single or multiple confidence levels that may or may not be passed into even more complex algorithms to further establish what the human is asking the robot.
A really good digital assistant doesn’t just have a high accuracy rating, it also has a high rate of responding to questions (swinging the bat). A digital assistant that only replies to really obvious requests will score high on accuracy, but low on satisfaction, and low on its ability to truly solve problems.
6. The Pinch Hitter
As we roll into 2021, a subject that will continue to keep coming up at all organizations will be the concept of the digital assistant “concierge”. Given the inevitable plethora of bots being implemented at many organizations, typically on different technology platforms, the question that will be constant in 2021 is:
“Can’t we just have one digital assistant that everyone interacts with. It’s too complicated for our people to know which one to go to?” And the simple answer is yes.
Organizations have begun to realize that one digital assistant should be the “face” to the organization, and that it is the job of the “face” to handle integration with all the other bots in the organization. Even those on a different technology stack. This is called a “concierge” solution, where the digital assistant can reach out to different bots at runtime to get the answers to questions it knows nothing about. Kind of like how the concierge in a hotel operates.
Technically, and to keep with our baseball theme, “concierging” entails swapping different bots in and out of the lineup based on the question the digital assistant is faced with. Just like bringing in your lefty to face the right-handed pitcher. So, for example, if the digital assistants key strength is HR based requests and the human asks a finance question, the digital assistant will reach out to the bot, or skill, that can best handle it, and acts as an intermediary communicating the responses with the human.
Ida’s underlying technology stack is based on Oracle technology, and so it is easy for Ida to concierge with any skill built on the Oracle Digital Assistant technology stack. Plus, because of the advanced nature of the stack and the middleware Ida uses to integrate with the stack, it is also possible to plug other completely different technology-based bots into the solution too. Like Microsoft LUIS or IBM Watson.
7. Laying Off the Ball
Of course, no digital assistant should be attempting to answer every question or request that it gets. If someone wants to know how tall Tom Brady is, that’s probably not a question it should be trying to respond to. But what it shouldn’t be doing is just responding with an “I don’t know the answer to that”. In baseball, if the ball is pitched a foot outside the plate, the hitter knows enough to know that they shouldn’t be swinging at the ball. That’s how baseball players, and digital assistants, make fools of themselves.
The best way for a digital assistant to lay off the ball is for it to politely say, “I don’t know the answer to that. But here are the topics I do know a lot about. You can browse these topics, or I can pass you to a live agent if you need more help”.
8. Slugging Percentage
For most of this article we have focused on contact with the ball as being the key metric for judging a digital assistant. Was the human utterance correctly matched to what the digital assistant was capable of responding to? Which is why batting average is used as a direct parallel. In reality there is another dimension to all of this that is best described with the comparison to baseball slugging percentages.
In baseball not all hits have the same value. One hit may get the player to first base, while another hit may score a home run. And, as everyone knows, hitting a home run is massively valuable, so slugging percentage is used as means to measure the power of a hitter. If you combine a hitter’s ability to get on base, plus the power they generate with each hit, that equates to a stat called OPS. And if the OPS is greater than 1.000 that means you are a superstar.
Digital assistants are exactly the same. Just being accurate (getting on base) isn’t sufficient. It’s the quality of the response that really counts (slugging percentage).
So, what exactly do we mean by that? Let’s see an example to illustrate the point:
An example of just getting to first base:
An example of the home run:
As you can see, the first example provides a link to web page, where all you can really do is initiate a request for someone to get this done for you. The second example clarifies any outstanding questions, completes the task, and triggers any appropriate workflow. This is called a home run, and it speaks to the deep integration capabilities of the digital assistant.
As is very clear in the examples above, the first example is not much better than an improved means of navigating crude FAQ web pages. Whereas the second example shows the value a superstar digital assistant can bring to your organization.
9. Statistics, statistics, statistics
The world of baseball is measured with every statistic you could ever imagine. And, these days, all organizations used advanced statistics to make pretty much every decision. No human, no matter how good their “eye” is, can process 250,000 data points and make an informed decision without some kind of analytics engine to provide guidance. And this is true in the world of digital assistants. Despite almost every salesperson in the AI world telling their prospect that AI “just learns”, that’s just not true, and nor is it advisable. Once a digital assistant is introduced to your organization, every decision you make in terms of growing its knowledge, and improving its capabilities, needs to be driven from hard data.
Yes, aspects of AI are a black box, but any black box can be measured, and by precise measurement you can predict behavior, and also alter it when needed.
At IntraSee we ask Ida over 10,000 questions every time we add more knowledge to the corpus, plus examine a quarter of a million data points. And, because this is impossible to do by hand, we automate the entire process. This allows us to ensure Ida gets smarter each week, and that there is no regression. Without all this data it would be impossible to do that.
The orchestration of supervised training and measurement is the key to continuous healthy growth. Like humans, digital assistants start life being great at some things, and not so great at others. And it’s important for all organizations to understand exactly what those strengths and weaknesses are. And, just like humans, this information can be used to further train the digital assistant, and also further enhance the quality of the responses.
With an array of statistics that are both high level for your executives, and detailed enough for your business analysts, you will have the tools to effectively manage your digital assistant.
10. Player Development
Most people assume that the use of statistics is confined to trading, drafting, and game strategy. But the most advanced organizations also use statistics to drive player development. It’s one thing to draft or trade for a great prospect, but unless they are coached correctly, you’ll never get the best out of them. Sometimes it will be a case of tiny fractions of adjustment to the length or angle of a swing that makes the difference between a good player and a great player.
Similarly, with digital assistants, they are not a “set and forget” solution. How you develop your digital assistant with continuous learning is what turns a good digital assistant into a great one. Supervised machine learning via automation, and rigorous automated testing, is the key to ensuring that your digital assistant gets smarter every single week.
In many ways you have to view your “digital worker” in the same light as when you hire a human worker. Performance appraisals, continuous feedback, and the setting of goals are just as important to your digital assistant. And, in some ways, more so. However, unlike your human hire, your digital worker can continue to get smarter and more knowledgeable each week, with no plateau. It will work 24/7 for you, and never call in sick. Plus, it will never leave you for a different organization, taking its knowledge with it. In short, it’s an investment that keeps on paying back.
If you would like more information, or would like to see a demo, please contact us below.
It was late July 2019 when Loyola University of Chicago reached out to us about launching a digital assistant by Labor Day just 6 short weeks away. Loyola had established a five-year plan to advance the Loyola Digital Experience (LDE) strategy in part by leveraging artificial intelligence (AI). A digital assistant would be a perfect blend of digitizing previously analog services, like student support, by deploying AI. Loyola, with their long tradition in basketball, would call that an “and 1”!
The digital assistant would be piloted during the fall semester and eventually rolled out to 16,000+ undergraduate students. They named it LUie, and it would provide hundreds of answers to common questions while leveraging information sourced from bookstores, google maps, and PeopleSoft Campus. This posting will take you through the pilot, a sample of use cases, the data collected, and next steps for Loyola.
LUie is a clever play on the acronym Loyola University, or LU for short. Giving their digital assistant a personality while paying homage to its parent, the university.
The end result of this journey was an award-winning project receiving an Innovator’s Award from Oracle. The accuracy of LUie has even surpassed Alexa and on October 7, 2020 you can see LUie for yourself at Reconnect during the session, “Succeed with Chatbots in PeopleSoft”.
LUie helping a student look up what matters most…their grades!
In a mere six weeks, LUie was configured with a mix of Ida’s pre-built campus answers and skills, plus Loyola’s own questions. It was then launched to students who were just arriving on campus. The only way to meet this timeline was to leverage the Ida platform and the IntraSee implementation methodology. Three departments took part in the pilot: the IT service desk, the bursar’s office and advising. Those departments would identify the most common questions fielded, which would then initiate automated testing and NLP learning sessions. Equipped with years of knowledge, LUie was then able to service hundreds of different undergraduate student and advisor requests.
The pilot focused on a fully-authenticated digital assistant because the point of a pilot is to prove LUie can handle the sophisticated features contained in authenticated campus systems like PeopleSoft. LUie would look up secure enterprise data and perform transactions on behalf of the student and advisor, so it needed to be fully authenticated and aware of permissions and roles. Upon login, LUie provided personalized responses applicable to the person’s role at the university. The pilot started with 50 users, but gradually built to around 1,000 users by the end of the semester. The goals were to show LUie in action with real users, prove the integration of enterprise information was successful, and to collect a ton of usage data to prove its usefulness.
During the pilot, LUie hit an accuracy rate of 86%. That is much better than most humans, and also added the benefit of being available 24 hours a day and responding almost instantly. LUie never even had to take a lunch. Interestingly, the top categories of user questions were ones asking about the student’s information and academic data (44% of all questions asked). This observation showed that students didn’t want a basic chatbot nor a link to go somewhere else. They wanted a digital assistant with personalized responses right within the conversation flow, and returned in an instant.
During the pilot, responses were provided by LUie at an accuracy rate of 86%.
Another interesting observation was that 28% of all questions asked during the pilot were on subjects LUie was never trained to answer. An example of one of these was, “how do I get my broken dorm window fixed?” AI is much like a young student in that it needs to be taught to understand a topic. However, it is unlike a student in that LUie only needs to be trained once; as it never forgets, it maintains its accuracy, and never leaves for greener pastures. The type of questions asked were so broad it showed that students expected their digital assistant to do it all. Even if a user was on the Bursar’s page when they launched LUie, it didn’t mean they kept their questions limited to student financials. This is an important fact to consider when launching a digital assistant vs. a chatbot.
On occasion, LUie asked users for feedback about how he performed. 91% of that feedback was positive. It’s hard to imagine having a 91% satisfaction rate on any support experience, but LUie’s speed, availability and accuracy made for a happy user.
Full Launch and COVID
In the Spring, LUie launched to all undergraduates and a portion of advisors for a total of over 16,000 users. During the full roll out, the COVID pandemic hit. Coincidentally, we realized how key a digital assistant would be during this time. There has never been a moment in recent history with so many questions from students, faculty and staff. And the answers to those questions seem to change daily. Speed and accuracy is king in this environment. There is no room for false information and LUie excels at just this task.
LUie took in almost a hundred new questions from Ida’s library concerning institutional policy related to COVID. Topics such as symptoms, living on campus, essential employee status, zoom tech support, drop deadline changes, grading basis, building access and so much more.
Sign used to promote LUie around campus
As with any good AI, Loyola now monitors how LUie is doing and provides it with weekly feedback (just as a teacher would for a student). That feedback automatically evolves LUie’s understanding of the campus such that it is getting better at its job every week.
Not Just Students
There is a lot of focus with chatbot providers on the student, but LUie went beyond students to help advisors too. After all, advisors are key to student success, the ultimate goal. If we make the advisors life easier and save them time, they can serve the students better. LUie’s benefit to advisors can be illustrated by examining one innovative use case at Loyola.
Students are limited to taking 18 credit hours a semester. Loyola doesn’t want them to take on too much and impact the student’s success. However, there are certainly cases where a student can handle taking more, or they simply need to do so in order to graduate in four years. Traditionally, the student would approach their advisor and the advisor had to:
Look up their GPA to ensure they were around a 3.0 or higher and then…
Update two different pages in the student system including about 10 different fields.
This process could easily take 15-20 mins, and it was easy for the advisor to miss a step, or a field, which would create further problems.
LUie took a 15-20 minute advising process and automated it down to under 30 seconds
LUie now automates this whole process. An advisor simply asks LUie, “can you approve John Doe’s overloaded schedule?” LUie then automatically knows to look up their GPA and ask the advisor for approval to proceed. Once approved, LUie will automate the filling in of those 10 fields across two pages. The whole dialogue takes less than 30 seconds! All that time goes back to the Advisor to spend on strategic work.
LUie will not stand still. Different departments at Loyola see the potential and a line is starting to form to get LUie serving those departmental needs. LUie has a developing roadmap, with the following next phases being planned:
Non-authenticated LUie: the ability for users to ask LUie for help and not have to sign in. As long as LUie’s answers are not sensitive or secured, it will provide the help. This includes parents, prospects and community members who can now use LUie. As of September 2020, this feature is now live!
Graduate Students: the audience will expand to include graduate students which will have their own questions and even graduate-specific answers to current questions.
Employees: the HR department wants to serve employee specific questions, including integration into HR applications and COVID related staff questions.
Industry surveys of Higher Education CIOs have highlighted the two top priorities in recent years: digital transformation and artificial intelligence. LUie has helped Loyola address both of these high priority areas while improving student service and helping to navigate a pandemic.
See LUie for yourself this October at the Reconnect conference on Wednesday, October 7 at 5pm ET. Just add Session ID 102210 to your schedule. If you can’t make Reconnect, just contact us below and we can setup a personal demo and show you how digital assistants can help your students, faculty and staff.
Privacy & Cookies Policy
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.