1
00:00:01,936 --> 00:00:38,971
[♫ ♬ Music ♫ ♬]

2
00:00:38,985 --> 00:00:40,520
[Paul Campbell]
Hello everyone and welcome  

3
00:00:40,520 --> 00:00:48,000
to our webinar for Equidox AI, a fully automated 
PDF remediation solution. We're very excited about  

4
00:00:48,000 --> 00:00:53,120
this cutting-edge technology that is solving 
for challenges within the financial services  

5
00:00:53,120 --> 00:00:58,680
sector. By way of introduction, my name is Paul 
Campbell and I will be joined by Tim Needles  

6
00:00:58,680 --> 00:01:07,560
and Dan Tuleta for the next 30 minutes. Just 
some logistics for today: the live audio Q&A,  

7
00:01:07,560 --> 00:01:13,360
as I mentioned a little earlier, is not available 
for this webinar. However, you can drop questions  

8
00:01:13,360 --> 00:01:19,120
in the Q&A chat button at the bottom of your 
screen and we will get back to you after the  

9
00:01:19,120 --> 00:01:25,720
webinar with any answers to questions that 
you post. Additionally, this webinar will be  

10
00:01:25,720 --> 00:01:31,200
recorded and will be sent after the meeting, in 
addition to the deck and a short survey. We're  

11
00:01:31,200 --> 00:01:36,680
happy to do a more direct interactive session 
with you and other team members if they're not  

12
00:01:36,680 --> 00:01:43,080
available to join here today. And we would love to 
further our conversations as to how Equidox AI may  

13
00:01:43,080 --> 00:01:50,040
be a fit for your organization specifically as a 
follow-up. Overview of the agenda for today, first  

14
00:01:50,040 --> 00:01:56,440
Tim Needles our President and CEO has joined us 
to talk a little bit about who is Equidox Software  

15
00:01:56,440 --> 00:02:02,000
Company, who we are where, we've been, and where 
we are going. I will then take over to discuss  

16
00:02:02,000 --> 00:02:06,880
the challenges that we've seen in the financial 
services sector specifically and our solution to  

17
00:02:06,880 --> 00:02:12,760
the problems we've seen. Then Dan will talk about 
why do we make PDFs accessible and what's really  

18
00:02:12,760 --> 00:02:19,680
driving this, followed by an overview of Equidox 
AI and how it works. And lastly the last half of  

19
00:02:19,680 --> 00:02:24,960
the meeting a demonstration of our solution. With 
that said I'm going hand it over to Tim Needles  

20
00:02:24,960 --> 00:02:29,240
to give an introduction to Equidox AI. Tim?
[Tim Needles] Oh, thank you, Paul, for the  

21
00:02:29,240 --> 00:02:34,400
introduction. Much appreciated and thank you 
all for joining us here today. We're exceedingly  

22
00:02:34,400 --> 00:02:40,640
excited that you're here with us while we showcase 
our AI solution. Now we know that many of you have  

23
00:02:40,640 --> 00:02:47,280
been feeling the pain of PDF remediation 
for some time in terms of excessive cost,  

24
00:02:47,280 --> 00:02:53,960
compliance issues, and risk mitigation issues from 
lawsuits. And you'll be pleased to know that there  

25
00:02:53,960 --> 00:03:00,160
is a better way… a better solution… And after the 
demo, I think you'll agree that Equidox AI is a  

26
00:03:00,160 --> 00:03:06,160
superior solution and can solve your problems as 
it relates to PDF remediation. Some of you might  

27
00:03:06,160 --> 00:03:12,200
think we're the new kid on the block, but Equidox 
has actually been in existence for over a decade.  

28
00:03:12,200 --> 00:03:17,320
Way back when a Canadian citizen was trying 
to apply for a government job posting on the  

29
00:03:17,320 --> 00:03:23,160
internet, but she was unable to do so because of 
her visual disability. So she sued the government  

30
00:03:23,160 --> 00:03:27,600
and she won her case. The government sought 
out a solution but they couldn't find one,  

31
00:03:27,600 --> 00:03:33,040
so they asked the marketplace to respond. Hence, 
we started building a solution and haven't stopped  

32
00:03:33,040 --> 00:03:40,120
innovating since. Over a decade ago we created 
a robust SaaS solution that now hundreds of  

33
00:03:40,120 --> 00:03:46,920
customers around the world are using. The solution 
is truly world-class and is adding tremendous  

34
00:03:46,920 --> 00:03:52,840
value to the marketplace of digital accessibility 
for enterprises, government, and educational  

35
00:03:52,840 --> 00:03:57,800
institutions, and certainly financial services. 
Our customers love the product, evidenced by  

36
00:03:57,800 --> 00:04:03,600
the fact that nearly 100% of our customers renew 
their subscriptions every year. Well, that's all  

37
00:04:03,600 --> 00:04:10,560
well and good for the legacy SaaS product, but 
we started hearing years ago from organizations  

38
00:04:10,560 --> 00:04:15,480
like yours that had tens of thousands, or hundreds 
of thousands, or even millions of documents that  

39
00:04:15,480 --> 00:04:20,560
needed to be remediated even on a monthly basis 
that there really wasn't an automated solution  

40
00:04:20,560 --> 00:04:26,560
for that. The traditional service providers were 
sending the documents to India and other countries  

41
00:04:26,560 --> 00:04:31,120
but there was really no efficient way to scale in 
that model. So companies were forced to settle for  

42
00:04:31,120 --> 00:04:38,960
a solution that frankly is really time-consuming, 
expensive, and doesn't truly mitigate the risk  

43
00:04:38,960 --> 00:04:44,680
of a lawsuit for your company. So our demo 
today will prove that there is a better way  

44
00:04:44,680 --> 00:04:52,240
to remediate large amounts of of documents, 
saving you a bunch of time, a lot of money,  

45
00:04:52,240 --> 00:04:57,400
and all the hassles of old-school remediation. 
And, you know, it's great to accomplish these  

46
00:04:57,400 --> 00:05:02,080
benefits and we're really proud of what we've 
done and achieved. But we're really most pleased  

47
00:05:02,080 --> 00:05:08,840
to provide a game-changing solution that assists 
the visually disabled. We're really passionate  

48
00:05:08,840 --> 00:05:14,040
about helping these people and it's invigorating 
to work with organizations like yours that share  

49
00:05:14,040 --> 00:05:20,440
our commitment and passion. So thank you again for 
taking the time to be with us today and we look  

50
00:05:20,440 --> 00:05:26,066
forward to serving you. Paul back to you.
[Paul Campbell] Thank you, Tim. 

51
00:05:26,066 --> 00:05:26,920
[Tim Needles} Welcome.
[Paul Campbell] 

52
00:05:26,920 --> 00:05:32,320
So as Tim mentioned, Equidox AI is a fully 
automated PDF remediation solution that  

53
00:05:32,320 --> 00:05:39,280
removes the traditional manual remediation and the 
auto-tagging methods, while still increasing the  

54
00:05:39,280 --> 00:05:45,320
quality, accuracy, and compliance that we're 
all looking for. And we've really found that  

55
00:05:45,320 --> 00:05:51,360
the financial services sector can get great value 
out of Equidox AI. This is because of number one,  

56
00:05:51,360 --> 00:05:58,520
unfortunately, the rising lawsuits in the industry 
under the ADA and AODA in Canada and the need for  

57
00:05:58,520 --> 00:06:03,280
end users with visual disabilities to access 
important information from their financial  

58
00:06:03,280 --> 00:06:10,040
institutions as an equivalent experience as 
sighted users. Number two, large quantities  

59
00:06:10,040 --> 00:06:15,280
and sheer volume of templated and reoccurring 
documents that consistently need to be accessible  

60
00:06:15,280 --> 00:06:20,160
because of these compliance requirements. And 
then number three, the challenges that these  

61
00:06:20,160 --> 00:06:26,280
organizations have with current processes quality, 
speed, and overall vendor sprawl because of the  

62
00:06:26,280 --> 00:06:35,160
large volumes which we'll expand upon here in a 
moment. So many customers are doing something but  

63
00:06:35,160 --> 00:06:42,360
unfortunately are still exposed or getting sued 
because of the volumes that they have to manage.  

64
00:06:42,360 --> 00:06:48,600
It's a very challenging thing to overcome. Some 
of the larger use cases we see in the financial  

65
00:06:48,600 --> 00:06:56,840
institutions may include, but are not limited 
to, any type of reoccurring monthly quarterly  

66
00:06:56,840 --> 00:07:03,000
customer statements, fund offerings, portfolio 
insights… These are all great candidates for  

67
00:07:03,000 --> 00:07:09,640
Equidox AI because of the high volume, repetitive, 
and templated nature. Now the main challenges for  

68
00:07:09,640 --> 00:07:15,440
financial services organizations when it comes 
to PDF remediation that we have found are:  

69
00:07:15,440 --> 00:07:22,480
number one, costs. Multiple vendors, outsourced 
providers, and overall investment in internal  

70
00:07:22,480 --> 00:07:28,360
personnel is very costly. It can be a runaway 
train of cost because of the industry standard.  

71
00:07:28,360 --> 00:07:34,520
Price per page is exponential and manual 
work to this capacity and scale can be very  

72
00:07:34,520 --> 00:07:42,120
expensive. Quality, number two, because of 
the cumbersome manual processes and corners  

73
00:07:42,120 --> 00:07:48,280
being cut to manipulate checkers the auto-tagging 
mishaps and issues, and then multiplied by volumes  

74
00:07:48,280 --> 00:07:53,800
of pages in scope and complexity really leaves 
organizations exposed to non-compliance lawsuits  

75
00:07:53,800 --> 00:08:00,200
because of these elements. And number three, 
speed. Demanding legal requirements and quick  

76
00:08:00,200 --> 00:08:06,840
turnaround times to get accessible information 
to your customers consistently is really not  

77
00:08:06,840 --> 00:08:13,520
realistic to accommodate with traditional manual 
processes and the auto-tagging methods because of  

78
00:08:13,520 --> 00:08:18,960
the volumes to manage when coupled with quality. 
And, as Tim mentioned, we wanted to create a  

79
00:08:18,960 --> 00:08:26,320
better way and we saw this gap in the market. 
And Equidox AI solves for these challenges. Our  

80
00:08:26,320 --> 00:08:31,200
experts have found a way to truly automate the PDF 
accessibility process for many of the financial  

81
00:08:31,200 --> 00:08:39,080
sector use cases involving high volumes. 
Equidox AI automation allows good quality,  

82
00:08:39,080 --> 00:08:44,440
usability, and compliance every time because of 
our unique model creation. We don't auto-tag,  

83
00:08:44,440 --> 00:08:50,560
or cut corners with checkers, or rely on the 
human element to get the process done. Equidox AI  

84
00:08:50,560 --> 00:08:56,240
automation also accommodates aggressive timelines 
because of relying on technology. We can dictate  

85
00:08:56,240 --> 00:09:02,080
how fast the solution runs and turn the dial up 
or down so to speak to accommodate timelines that  

86
00:09:02,080 --> 00:09:09,880
that may be required for the customer. And lastly, 
Equidox AI automation allows for lower costs,  

87
00:09:09,880 --> 00:09:16,320
process improvements, and vendor consolidation. So 
with that, I'm going to turn over to my colleague  

88
00:09:16,320 --> 00:09:23,360
Dan to talk about why it's important to make 
PDFs accessible, and how Equidox AI works, and  

89
00:09:23,360 --> 00:09:31,120
then lastly a demonstration of our solution. Dan?
[Dan Tuleta] Great thanks, Paul. So hi everyone.  

90
00:09:31,120 --> 00:09:35,800
And I assume everyone on this call is probably at 
least somewhat familiar with various accessibility  

91
00:09:35,800 --> 00:09:43,400
laws like the ADA, Section 508, and the Affordable 
Care Act. Now I'm not a lawyer so I'm not going  

92
00:09:43,400 --> 00:09:48,960
to go into all the details of how these laws 
work, but at a high level, just as there are  

93
00:09:48,960 --> 00:09:54,520
requirements for organizations to provide 
physical access such as wheelchair ramps,  

94
00:09:54,520 --> 00:10:00,520
elevators, Braille signage… Organizations need to 
ensure that their public-facing digital content,  

95
00:10:00,520 --> 00:10:06,640
including PDFs, is accessible to everyone, 
including people with disabilities. Ignoring  

96
00:10:06,640 --> 00:10:12,280
the accessibility of your digital content opens 
up your organization to legal risk. There have  

97
00:10:12,280 --> 00:10:16,520
been thousands of organizations who learned 
that lesson the hard way when they were sued  

98
00:10:16,520 --> 00:10:22,280
for exactly that type of problem. And there are 
thousands more who quietly pay large settlements  

99
00:10:22,280 --> 00:10:26,480
out of court and yet they still have to go 
back and fix their accessibility issues after  

100
00:10:26,480 --> 00:10:32,840
the fact. So long story short, we live in a very 
digital world and we rely so heavily on digital  

101
00:10:32,840 --> 00:10:38,680
information. So digital accessibility is not a 
fad, it is not going anywhere, it's not going  

102
00:10:38,680 --> 00:10:46,400
away anytime soon. So it's always good to be 
aware of it and address it in a proactive way.  

103
00:10:54,520 --> 00:11:00,400
For anyone who isn't sure of why we are making 
why this digital accessibility stuff matters,  

104
00:11:00,400 --> 00:11:05,920
people with disabilities use various types of 
assistive technologies to interact with digital  

105
00:11:05,920 --> 00:11:12,040
content like PDFs. A very common type of assistive 
technology is called a screen reader, which is  

106
00:11:12,040 --> 00:11:18,720
capable of reading digital content like websites, 
applications, and of course PDF documents. Screen  

107
00:11:18,720 --> 00:11:25,840
readers use digital tags to navigate documents and 
tags need to be properly encoded into a document  

108
00:11:25,840 --> 00:11:31,440
to organize the content and make it compatible 
with the screen reader. So think of tags as the  

109
00:11:31,440 --> 00:11:36,400
framework of the document which gives the screen 
reader the ability to navigate and interact with  

110
00:11:36,400 --> 00:11:43,880
all of the various elements in that PDF. Equidox, 
in cooperation with the National Federation of the  

111
00:11:43,880 --> 00:11:50,360
Blind, surveyed about 250 blind and low-vision 
individuals who rely on screen readers every day  

112
00:11:50,360 --> 00:11:56,560
to interact with PDFs. Based on this survey, we 
found that at least two-thirds of the documents  

113
00:11:56,560 --> 00:12:01,400
that they interact with are inaccessible to 
people people with disabilities. If you put  

114
00:12:01,400 --> 00:12:06,640
yourself in the shoes of a blind person, you can 
quickly imagine how frustrated you would be if you  

115
00:12:06,640 --> 00:12:12,360
could not read two-thirds of the documents that 
you came in contact with on a daily basis. And, on  

116
00:12:12,360 --> 00:12:18,520
top of that, imagine the potential privacy issues 
if you have to go ask your neighbor to read to you  

117
00:12:18,520 --> 00:12:23,760
your monthly bank statement, or your credit card 
charges, or your investment portfolio summary.  

118
00:12:23,760 --> 00:12:28,000
Whatever that document might be. Obviously, 
you want to keep that information confidential  

119
00:12:28,000 --> 00:12:40,040
and private. So just to to further emphasize the 
points that I was just making a couple of slides  

120
00:12:40,040 --> 00:12:44,680
back, there's some additional information here 
about the volume and the types of lawsuits that  

121
00:12:44,680 --> 00:12:50,280
the financial sector has faced and will continue 
to face moving forward unless they start doing  

122
00:12:50,280 --> 00:12:54,520
something about it. So just to reiterate, 
the digital accessibility requirements that  

123
00:12:54,520 --> 00:13:03,000
organizations must adhere to are not going away 
and they will continue to increase in attention  

124
00:13:03,000 --> 00:13:09,880
will be paid by state and federal mandates, the 
Department of Justice, disability advocacy groups,  

125
00:13:09,880 --> 00:13:17,440
and individuals who simply want to be able to 
access their critical information. So let's talk  

126
00:13:17,440 --> 00:13:24,480
a little bit about the human element of AI. One 
of the main challenges around PDF accessibility  

127
00:13:24,480 --> 00:13:30,840
is that each PDF document is unique. We've heard 
a lot of empty promises of fully automating PDF  

128
00:13:30,840 --> 00:13:37,320
accessibility but there are so many things about 
PDFs that require human interpretation to decide  

129
00:13:37,320 --> 00:13:43,400
how to tag the specific elements within the 
content. I've been working with PDF in the PDF  

130
00:13:43,400 --> 00:13:49,240
accessibility market for about seven years and I 
have seen a lot of organizations and I've talked  

131
00:13:49,240 --> 00:13:54,400
to a lot of them that have assumed that they are 
accessible… they have accessible documents because  

132
00:13:54,400 --> 00:13:59,600
their documents have some tags in them. But 
they quickly learn that those tag tags and those  

133
00:13:59,600 --> 00:14:05,280
documents are not usable nor are they compliant 
and their organization is still wide open for  

134
00:14:05,280 --> 00:14:13,600
litigation. So just be aware of any organizations 
out there talking about auto-tagging technology.  

135
00:14:13,600 --> 00:14:19,440
Auto-tagging is really just masking itself as a 
solution to fully automate PDF accessibility. But  

136
00:14:19,440 --> 00:14:26,360
auto-taggers are capable of simply putting tags on 
a page. There will always be accuracy issues and  

137
00:14:26,360 --> 00:14:31,960
the inaccuracy of those tags will lead to a lot of 
confusion and frustration for that screen reader  

138
00:14:31,960 --> 00:14:38,840
user. Additionally, auto-taggers can and will 
leave that organization open to further litigation  

139
00:14:38,840 --> 00:14:44,880
because there is no guarantee of compliance with 
any of the web accessibility standards. So if and  

140
00:14:44,880 --> 00:14:50,080
if you pay to outsource your huge batches 
of documents to auto-taggers, you are not  

141
00:14:50,080 --> 00:14:55,160
mitigating your risk of litigation because these 
auto-taggers again fall short of true compliance  

142
00:14:55,160 --> 00:15:01,800
with the standards. And then the alternative of 
outsourcing the remediation work to third parties  

143
00:15:01,800 --> 00:15:08,560
who are almost exclusively located overseas 
introduces a mountain of data privacy issues.  

144
00:15:08,560 --> 00:15:13,360
And even if you can work around that, the volume 
of documents is impossible to keep up with. These  

145
00:15:13,360 --> 00:15:19,160
outsourced remediation providers will cut corners 
and do the bare minimum amount of work to make a  

146
00:15:19,160 --> 00:15:24,560
document pass an accessibility checker, but not 
actually make the document compliant because it  

147
00:15:24,560 --> 00:15:32,640
simply takes too long to meet customer deadlines 
at this type of value. So incorporating artificial  

148
00:15:32,640 --> 00:15:38,240
intelligence, more specifically, computer 
vision and machine learning into high-volume PDF  

149
00:15:38,240 --> 00:15:46,040
remediation allows our accessibility experts to 
train an AI model to accurately identify and tag  

150
00:15:46,040 --> 00:15:54,080
all of the elements in the document template. The 
use of AI developed by our data scientists, paired  

151
00:15:54,080 --> 00:15:59,960
with the human element of trained accessibility 
experts that we have here on staff allows for  

152
00:15:59,960 --> 00:16:06,000
incredibly accurate, usable, and compliant PDFs 
to be returned to the customer in a fraction of  

153
00:16:06,000 --> 00:16:12,600
the time because the AI works exponentially faster 
than humans manually tagging each page. AI doesn't  

154
00:16:12,600 --> 00:16:20,720
need to take vacations, AI can work 24/7, 365 
on demand without any breaks. And, of course,  

155
00:16:20,720 --> 00:16:29,240
AI doesn't need to cut corners to meet deadlines. 
It can do it the right way the first time. So how  

156
00:16:29,240 --> 00:16:35,200
does all of this work? So our accessibility 
experts use example documents of customer  

157
00:16:35,200 --> 00:16:42,160
templates to properly identify the various 
elements on the page. These elements might include  

158
00:16:42,160 --> 00:16:49,560
text and paragraph structure, various levels 
of headings, lists, tables, graphs and images,  

159
00:16:49,560 --> 00:16:55,360
and of course, the very important reading order of 
the content. This training data is then fed to the  

160
00:16:55,360 --> 00:17:00,960
AI models to apply what it has learned en masse 
to many thousands, tens of thousands, millions  

161
00:17:00,960 --> 00:17:10,960
of pages that have simpler similar templates and 
formatting. So although the mechanics of how AI  

162
00:17:10,960 --> 00:17:16,520
technology works is rather abstract and a lot more 
complex than what I'm capable of showing you on a  

163
00:17:16,520 --> 00:17:23,640
simple PowerPoint slide, there's a few examples 
here of how we can visualize AI at work in this  

164
00:17:23,640 --> 00:17:29,920
scatter plot that you see on the slide. Each of 
the green dots represents a page within a PDF.  

165
00:17:29,920 --> 00:17:35,720
They are grouped together based on similarities 
that the computer vision finds. So this cluster  

166
00:17:35,720 --> 00:17:41,360
will contain all of the pages that contain pie 
charts. So you can keep an eye on the pages  

167
00:17:41,360 --> 00:17:45,880
here that are all going to contain pie charts. 
Obviously, these are all going to be kind of  

168
00:17:45,880 --> 00:17:53,440
in the same neighborhood that the AI is capable of 
locating and identifying. In this example, you can  

169
00:17:53,440 --> 00:18:00,160
see there are different multicolumn text layouts 
that the AI will use to recognize different pages  

170
00:18:00,160 --> 00:18:06,160
and then group them together appropriately. The 
AI will also pick up on things like font styles,  

171
00:18:06,160 --> 00:18:14,720
and size, and color, and background colors to help 
it establish the tags on a page. We can even train  

172
00:18:14,720 --> 00:18:22,160
the AI to identify many potential variations in 
tables such as the numbers of columns and rows,  

173
00:18:22,160 --> 00:18:28,400
table headers versus table data, and even tables 
of different sizes that might span across multiple  

174
00:18:28,400 --> 00:18:35,720
pages. The result of all of this extensive 
document analysis in feeding the training  

175
00:18:35,720 --> 00:18:43,680
data to the AI is creating a fully compliant PDF 
without any human remediators who are expensive to  

176
00:18:43,680 --> 00:18:50,720
employ onshore or outsource offshore. And they are 
of course liable to make errors or be forced to  

177
00:18:50,720 --> 00:18:57,280
cut corners just to meet an unattainable deadline 
due to the volume demands of your organization. We  

178
00:18:57,280 --> 00:19:03,240
are also reaching full compliance because this is 
not the auto-tagging method where we're throwing  

179
00:19:03,240 --> 00:19:09,360
sloppy tags on a page and saying good enough. So 
beyond compliance and passing automated checkers,  

180
00:19:09,360 --> 00:19:14,800
the bonus of using AI for high volume and 
hyper-fast remediation is that it will  

181
00:19:14,800 --> 00:19:20,400
produce incredibly accurate and very much usable 
documents for people with disabilities. So your  

182
00:19:20,400 --> 00:19:25,520
customers who rely on assistive technology 
will not be filing complaints or lawsuits,  

183
00:19:25,520 --> 00:19:30,160
they won't be calling your headquarters to 
complain about a document that they can't  

184
00:19:30,160 --> 00:19:37,920
navigate or understand. So we're getting ready 
here to jump into the demonstration of how the  

185
00:19:37,920 --> 00:19:43,760
technology works, but I just want to make it clear 
that this underlying technology can be deployed in  

186
00:19:43,760 --> 00:19:49,120
several ways to align with your organization's 
requirements. We have built an interface,  

187
00:19:49,120 --> 00:19:54,240
which I'll show you during the demo, that can 
allow your employees to run the process from start  

188
00:19:54,240 --> 00:19:59,360
to finish with just a few clicks by uploading 
the document or documents, running the batch,  

189
00:19:59,360 --> 00:20:05,840
and then downloading the finished PDFs. We can 
also embed AI models into an existing document  

190
00:20:05,840 --> 00:20:12,000
creation and delivery system through the use of 
APIs. This would be critical for customers needing  

191
00:20:12,000 --> 00:20:17,880
to download private documents like a monthly 
statement, or an explanation of their portfolio  

192
00:20:17,880 --> 00:20:24,920
summary, or a credit card bill, whatever the use 
case. A document that is supposed to be private  

193
00:20:24,920 --> 00:20:31,720
and confidential can be directly delivered 
to that user. Lastly, another method is that  

194
00:20:31,720 --> 00:20:37,160
Equidox could operate the process as a managed 
service. So we can take care of the remediation  

195
00:20:37,160 --> 00:20:43,480
and validation and get everything back to you in 
a fully compliant way to be posted and distributed  

196
00:20:43,480 --> 00:20:48,680
publicly if that's the use case that you have in 
mind. So there's different methods to implement  

197
00:20:48,680 --> 00:20:57,000
this technology. So just keep that in mind during 
the demonstration. So just one more thing to note:  

198
00:20:57,000 --> 00:21:03,640
Equidox AI is applying the PDF tags at the 
post-processing stage which you will see during  

199
00:21:03,640 --> 00:21:09,120
the demonstration. So these PDFs are already 
created, and we are applying the accessibility  

200
00:21:09,120 --> 00:21:15,480
as a final step before they are publicly 
distributed. The advantage of tagging PDFs at the  

201
00:21:15,480 --> 00:21:21,840
post-processing stage is that we are not having to 
disrupt, or more than likely completely rebuild,  

202
00:21:21,840 --> 00:21:27,520
your document creation process. So your designers 
and your producers and whatever systems you have  

203
00:21:27,520 --> 00:21:33,960
in place of mass document creation can continue 
and we will handle the accessibility component  

204
00:21:33,960 --> 00:21:41,280
at the very end right before the document reaches 
your customer. Okay so I'm going to jump out of  

205
00:21:41,280 --> 00:21:47,160
the slide deck, and for anyone that wants to share 
this webinar later there will be a video of course  

206
00:21:47,160 --> 00:21:52,960
with our demo attached for this slide. But I'm 
going to jump into our actual Equidox AI batch  

207
00:21:52,960 --> 00:22:01,680
interface. So what I'm going to do is I'm going to 
demonstrate the fully automated remediation of a  

208
00:22:01,680 --> 00:22:08,000
set of bank statements. So bank statements are a 
good candidate for Equidox AI technology because  

209
00:22:08,000 --> 00:22:13,680
in general, they will follow a very similar 
formatting and structure. But the data within  

210
00:22:13,680 --> 00:22:20,560
that structure will vary from version to version. 
So for example, if I just open up an example of  

211
00:22:20,560 --> 00:22:26,000
what we're going to be talking about, people's 
names, and account numbers, and mailing addresses  

212
00:22:26,000 --> 00:22:32,040
will always be different. But the location on 
the page will be very consistent. Line items  

213
00:22:32,040 --> 00:22:36,960
on the statement might vary. So for example, 
one customer might just have a single charge  

214
00:22:36,960 --> 00:22:41,960
on their credit card for a month whereas another 
customer might have 500 charges requiring their  

215
00:22:41,960 --> 00:22:48,200
statement to merge onto four or five different 
pages of line items. So there will always be  

216
00:22:48,200 --> 00:22:53,640
enough variants from one version to the next that 
will make old-fashioned auto-tagging inaccurate  

217
00:22:53,640 --> 00:22:58,720
and unreliable. And of course, you cannot 
outsource the remediation of confidential data  

218
00:22:58,720 --> 00:23:04,520
to third-party companies located offshore. Even 
if you could the volume of documents like this,  

219
00:23:04,520 --> 00:23:14,880
that you're producing, would be impossible for 
them to handle. So as I was mentioning before,  

220
00:23:14,880 --> 00:23:21,600
for a use case like this, a recurring monthly 
statement, or an invoice, or a portfolio summary,  

221
00:23:21,600 --> 00:23:30,560
it is more than likely that your organization 
would want to implement this accessibility of  

222
00:23:30,560 --> 00:23:35,400
this at the final step in the process so that 
your customer is automatically receiving their  

223
00:23:35,400 --> 00:23:40,440
accessible document without any human involvement. 
And we can of course accommodate this through the  

224
00:23:40,440 --> 00:23:46,040
APIs. So visualize a scenario where that is not 
me pressing the buttons to operate the system,  

225
00:23:46,040 --> 00:23:51,120
but rather this is directly integrated into 
your document creation process to achieve  

226
00:23:51,120 --> 00:23:58,200
true automation. So what I'm going to do is I'm 
going to start by uploading the documents of  

227
00:23:58,200 --> 00:24:03,000
the the bank statements that I just showed you. 
So I'm going to go to the Upload Documents tab,  

228
00:24:03,000 --> 00:24:08,080
I will open up my folders, and I will just grab 
this .zip folder which contains the documents.  

229
00:24:08,080 --> 00:24:14,240
Once I press the Upload button it will just take 
a few seconds to upload to the cloud. And I will  

230
00:24:14,240 --> 00:24:20,520
then go to the Create and Run Batch tab here on 
the interface. From this tab, I have a drop-down  

231
00:24:20,520 --> 00:24:26,440
menu where I can select the appropriate model that 
I want to apply to this batch of documents. Now we  

232
00:24:26,440 --> 00:24:33,600
have other demonstrations that we can provide for 
different types of use cases depending on the type  

233
00:24:33,600 --> 00:24:37,720
of use case you have in mind. In this example, 
I'm going to be doing that bank statement. So  

234
00:24:37,720 --> 00:24:45,840
I'm going to choose the Statement model. I'm then 
going to choose the .Zip radio button here to then  

235
00:24:45,840 --> 00:24:51,480
select the .Zip folder that I just uploaded. Now 
once I've gone through those three quick steps,  

236
00:24:51,480 --> 00:25:01,800
I simply press Run Batch. Now that the batch is 
running, I can see sort of the steps that are  

237
00:25:01,800 --> 00:25:07,200
of the document in this process. So take note of 
these various dots that represent the stages of  

238
00:25:07,200 --> 00:25:14,720
the process. So Equidox is analyzing each document 
and automatically applying the correct zones or  

239
00:25:14,720 --> 00:25:20,800
tags around the content. Once the document is 
finished at the AI step, they will go through the  

240
00:25:20,800 --> 00:25:28,720
export engine and become available for download or 
automatic direct delivery to your customer. So you  

241
00:25:28,720 --> 00:25:35,240
can see these green dots kind of processing across 
the page. Now just going back quickly to the  

242
00:25:35,240 --> 00:25:40,840
original document, I just want to make note just 
really quickly here that this document coming from  

243
00:25:40,840 --> 00:25:45,760
the original folder is completely untagged. So 
there's no tags at all in this document. It would  

244
00:25:45,760 --> 00:25:52,400
render this entire PDF essentially useless. A 
screen reader user would have all of this content  

245
00:25:52,400 --> 00:25:58,100
just being read in a totally random order. The 
tables themselves would be impossible to navigate  

246
00:25:58,100 --> 00:26:02,880
or understand. So this entire bank statement is 
completely inaccessible. And of course very much  

247
00:26:02,880 --> 00:26:10,600
out of compliance with all relevant accessibility 
standards. So we'll go back to the batch interface  

248
00:26:10,600 --> 00:26:17,080
here and the process is nearly done running. In 
this current version of Equidox, in our little  

249
00:26:17,080 --> 00:26:23,760
demonstration environment, this batch takes 
roughly 80 or 85 seconds to finish running. And  

250
00:26:23,760 --> 00:26:27,800
when it when it does finish, you can see that all 
of these documents have gone through the process  

251
00:26:27,800 --> 00:26:33,720
and there were 20 of them. So 20 documents have 
been fully remediated and exported. And if you  

252
00:26:33,720 --> 00:26:39,720
were to download any of these and then open them 
up in the Adobe Acrobat view we can take a look  

253
00:26:39,720 --> 00:26:50,600
at the tag structure… if Acrobat will wake up… I 
guess I'll save this and we'll open this one up.  

254
00:26:50,600 --> 00:26:55,200
And now when we take a look at it you can see that 
these documents are fully tagged and furthermore,  

255
00:26:55,200 --> 00:26:59,920
they are accurately tagged. So you'll notice that 
set the reading order, as I start to tab through,  

256
00:26:59,920 --> 00:27:06,280
is in a logical logical order. This image, the 
figure which is the bank logo, is tagged with  

257
00:27:06,280 --> 00:27:12,440
alt text which we have built into the AI model. 
The heading structure and the tables are fully  

258
00:27:12,440 --> 00:27:21,640
tagged. So all of this is 100% accurate, 100% 
compliant, and 100% usable for your customer. So  

259
00:27:21,640 --> 00:27:27,040
they can freely navigate all of this information 
all of these various charges and line items and  

260
00:27:27,040 --> 00:27:32,760
debits credits on their statement. And they are 
free to interact with all of this information.  

261
00:27:32,760 --> 00:27:38,480
So without anyone having to manually go through 
this document and set up all of these table tags,  

262
00:27:38,480 --> 00:27:43,360
and heading structure, and reading order, which 
can take a very long time in the old-fashioned  

263
00:27:43,360 --> 00:27:47,960
manual way, we're able to deliver a fully 
usable, fully accessible document to your  

264
00:27:47,960 --> 00:27:58,720
customer. So with that said, that is a quick 
crash course through the actual demonstration.  

265
00:27:58,720 --> 00:28:02,160
Now I'm going to jump back into the slide 
deck here just to wrap things up because  

266
00:28:02,160 --> 00:28:08,520
we are quickly running out of time. So as Paul 
mentioned in the beginning, this slide deck will  

267
00:28:08,520 --> 00:28:12,840
be shared with you and there are some links here 
to learn a bit more about digital accessibility  

268
00:28:12,840 --> 00:28:18,000
and how it relates to PDF documents. And then 
in conclusion, I just want to thank everyone  

269
00:28:18,000 --> 00:28:23,000
for joining us here today and we hope that you 
all see some value in the capabilities of this  

270
00:28:23,000 --> 00:28:28,880
technology. So please don't hesitate to reach out 
to us for a more one-on-one consultation so that  

271
00:28:28,880 --> 00:28:35,040
we can discuss your organization's use cases that 
you have in mind and talk about how Equidox AI can  

272
00:28:35,040 --> 00:28:40,840
be applied to solve for those challenges 
that you have around PDF remediation. Also we  

273
00:28:40,840 --> 00:28:44,720
will be sending the recording of this webinar 
so feel free to share this with anyone in your  

274
00:28:44,720 --> 00:28:50,840
organization who you feel would benefit from it. 
And we will include a link to the slide deck. And,  

275
00:28:50,840 --> 00:28:56,640
for anyone who asked a question during the Q&A 
through the chat we will get back to you as soon  

276
00:28:56,640 --> 00:29:02,520
as we can with a with a response to that question, 
And lastly, there will be a short survey so if you  

277
00:29:02,520 --> 00:29:08,200
don't mind just taking a quick moment to fill 
out that survey we would greatly appreciate it.  

278
00:29:08,200 --> 00:29:15,200
So thank you again, everyone, for joining, 
and have a great rest of your day. For more  

279
00:29:15,200 --> 00:29:20,560
information about how Equidox Software Company 
can help you with PDF accessibility, email us at  

280
00:29:20,560 --> 00:29:32,520
EquidoxSales@Equidox.co, or give us a call at 216 
529-3030, or visit our website at www.equidox.co.