1
00:00:00,000 --> 00:00:09,840
[Pat Needles] Hi everybody my name is Pat Needles. 
I am a Vice President here at the Equidox Software  

2
00:00:09,840 --> 00:00:17,960
Company. I first wanted to thank each and every 
one of you for making yourself available today to  

3
00:00:17,960 --> 00:00:25,040
join us for what proves to be a very exciting 
and new technology that Equidox has developed  

4
00:00:25,040 --> 00:00:31,520
and we're super excited to show you how that 
works and the value that is associated with  

5
00:00:31,520 --> 00:00:38,560
that. And you can see on this first slide up 
top our mission statement, which is “enabling  

6
00:00:38,560 --> 00:00:45,800
PDF accessibility through intelligent automated 
solutions.” and that's kind of a common theme here  

7
00:00:45,800 --> 00:00:52,120
you'll see that throughout today's presentation 
and discussion about the genesis of Equidox.  

8
00:00:52,120 --> 00:00:59,120
Where we started where we've been and where we're 
at today. So we're excited to talk to the folks  

9
00:00:59,120 --> 00:01:04,360
especially we've never ever heard of Equidox. 
This might be their first time at one of our  

10
00:01:04,360 --> 00:01:10,600
webinars – but welcome to you and we're looking 
forward to showing you what we have today. (you  

11
00:01:10,600 --> 00:01:18,320
can move forward Dan) So what we're going to talk 
about today as far as the agenda is concerned is,  

12
00:01:18,320 --> 00:01:25,000
who is Equidox where did we come from, where are 
we going. As I had mentioned before some super  

13
00:01:25,000 --> 00:01:32,920
exciting things that we're going to talk about. 
Why make PDFs accessible. I think most people  

14
00:01:32,920 --> 00:01:39,960
on this call understand a lot of the reasons why 
you might want to do that and that sort of thing  

15
00:01:39,960 --> 00:01:46,520
and so we're also going to talk today about our 
AI-powered PDF accessibility tool and how that  

16
00:01:46,520 --> 00:01:53,320
works and the value of that. And of course we'll 
get into the most important thing here today which  

17
00:01:53,320 --> 00:02:05,000
is the actual demo of the AI solution. So who is 
Equidox and where did we come from? Equidox the  

18
00:02:05,000 --> 00:02:13,160
genesis behind it starts in about 2011 when we 
were asked by a Canadian federal government to  

19
00:02:13,160 --> 00:02:20,360
build a software tool that would make PDFs 
accessible for people with disabilities.  

20
00:02:20,360 --> 00:02:31,240
And when we started this process and building the 
tool our first output was PDF to HTML. Soon after  

21
00:02:31,240 --> 00:02:39,080
that we grew to a PDF-accessible output and from 
there we have built in a lot of different types of  

22
00:02:39,080 --> 00:02:48,000
automation into the tool that we will definitely 
be talking about. We have built over say,  

23
00:02:48,000 --> 00:02:55,240
over the last three years, some detection tools 
into our software application that has made PDF  

24
00:02:55,240 --> 00:03:02,360
remediation much simpler and more efficient. 
And any of those… any of you folks that have  

25
00:03:02,360 --> 00:03:08,240
been that have done remediation that is on 
this call today understands that this is a  

26
00:03:08,240 --> 00:03:14,320
very painful process. It can be time-consuming 
and we've taken a lot of that heavy lifting  

27
00:03:14,320 --> 00:03:21,120
off of the table by building in tools into the 
software application that allows for fast and  

28
00:03:21,120 --> 00:03:29,160
easy remediation. And then secondly what we're 
going to be showing you today is our AI-powered  

29
00:03:29,760 --> 00:03:40,600
software solution for high-volume templated 
at scale recurring documents. (okay Dan) so  

30
00:03:40,600 --> 00:03:46,640
you know we talk about the challenges of PDF 
remediation and how difficult that can be you  

31
00:03:46,640 --> 00:03:53,160
know it's very labor intensive. Folks need 
accessibility skills in order to remediate  

32
00:03:53,160 --> 00:04:00,640
documents properly. It can be very expensive if 
you are outsourcing these types of activities to  

33
00:04:00,640 --> 00:04:10,680
third parties. There is the possibility of human 
error while remediating documents on challenging 

34
00:04:10,680 --> 00:04:21,760
Timelines. (Go ahead, Dan) So the Equidox AI 
solution as I had mentioned earlier is a fully  

35
00:04:21,760 --> 00:04:32,800
automated PDF solution that really takes the 
human element out of actual remediation. And  

36
00:04:32,800 --> 00:04:39,000
so what we're going to show you today is how 
we import documents into our system, how they  

37
00:04:39,000 --> 00:04:47,320
run through our AI engine, and how they come out 
completely tagged and completely accessible. There  

38
00:04:47,320 --> 00:04:54,520
is no need as I had mentioned for any human 
intervention for this too. And we are really  

39
00:04:54,520 --> 00:05:01,200
excited to show you how this works here today. So 
with that, I'll go ahead and I will turn it over  

40
00:05:01,200 --> 00:05:07,320
to you Dan, to do the demonstration of the tool.
[Dan Tuleta] Okay great, thanks, Pat. So before  

41
00:05:07,320 --> 00:05:13,440
we get into the actual demonstration of Equidox AI 
I’m just going to set the table for a little bit  

42
00:05:13,440 --> 00:05:18,360
more just in case anyone is new to accessibility. 
I'm just going to talk through a little bit of  

43
00:05:18,360 --> 00:05:24,840
the process and how it works and also why it's 
important to do this so just so everyone's aware.  

44
00:05:24,840 --> 00:05:32,440
Equidox in in cooperation with the NFB conducted a 
survey of over 250 blind and low vision assistive  

45
00:05:32,440 --> 00:05:37,800
technology users. So that would primarily be 
people who are using screen reading technology  

46
00:05:37,800 --> 00:05:44,400
in order to read digital content on their computer 
screen. And we have found, after surveying these  

47
00:05:44,400 --> 00:05:49,840
250 blind and low-vision users that at least 
two-thirds of PDFs that they interact with on  

48
00:05:49,840 --> 00:05:55,200
a regular basis are not accessible. So they 
cannot interact with those documents if they  

49
00:05:55,200 --> 00:06:01,320
were to use their assistive technology. Adobe, 
who owns the PDF format estimates that there are  

50
00:06:01,320 --> 00:06:09,680
over three trillion trillion PDFs in circulation 
today. So that means there are about two trillion  

51
00:06:09,680 --> 00:06:14,800
completely inaccessible documents out there that 
are floating around in circulation. So that is  

52
00:06:14,800 --> 00:06:20,560
a staggering amount of documents and many people 
who aren't blind or have low vision and don't use  

53
00:06:20,560 --> 00:06:25,200
assistive technology, are probably interacting 
with PDFs on a regular basis and you don't even  

54
00:06:25,200 --> 00:06:30,760
really think about it. But those PDFs present 
a huge barrier to understanding information for  

55
00:06:30,760 --> 00:06:38,080
people who who rely on their assistive technology 
to interact with the content. So the main takeaway  

56
00:06:38,080 --> 00:06:46,080
from from this slide here many people on this 
call have probably heard the the acronym WCAG,  

57
00:06:46,080 --> 00:06:51,200
which stands for the Web Content Accessibility 
Guidelines maybe you've heard of the section 508  

58
00:06:51,200 --> 00:06:55,800
standards. We're not going to get into the 
alphabet soup and start breaking down the  

59
00:06:55,800 --> 00:07:00,000
differences and the similarities between these 
different standards and guidelines but the main  

60
00:07:00,000 --> 00:07:04,680
takeaway from this is that these are the standards 
that are being used to measure the accessibility  

61
00:07:04,680 --> 00:07:10,240
of websites and documents and digital content 
and the number of lawsuits that we're seeing  

62
00:07:10,240 --> 00:07:16,440
every single year is on a steady rise so the 
lawsuits are coming in fast and furious around  

63
00:07:16,440 --> 00:07:22,160
websites and documents and digital accessibility 
as we move to a further and further digital world  

64
00:07:22,160 --> 00:07:30,680
world. So organizations have to be aware that they 
are not exempt from making sure that their content  

65
00:07:31,240 --> 00:07:35,720
is accessible and you have a responsibility to 
make sure that you're providing digital content in  

66
00:07:35,720 --> 00:07:47,160
a way that can be used by everyone. So with that 
said, as Pat kind of alluded to a few slides back,  

67
00:07:47,160 --> 00:07:53,080
the the challenge with PDF accessibility for 
many organizations is just the sheer volume of  

68
00:07:53,080 --> 00:08:00,880
documents that they produce and distribute. So 
the the number of pages can make it extremely  

69
00:08:00,880 --> 00:08:07,600
difficult to manage on a consistent basis. 
Outsourcing this work is extremely expensive.  

70
00:08:07,600 --> 00:08:13,240
You also lose control of the deadlines making 
sure that that outsourced company is getting  

71
00:08:13,240 --> 00:08:19,600
those documents back to you in an efficient 
manner and meeting your deadlines. You can lose…  

72
00:08:19,600 --> 00:08:24,360
you can have concerns over the security and the 
privacy of these documents if you have anything  

73
00:08:24,360 --> 00:08:29,920
that needs to remain confidential and also you're 
putting the faith in these outsource firms that  

74
00:08:29,920 --> 00:08:34,560
they are going to be delivering high-quality work 
which they may not be. And also remediating these  

75
00:08:34,560 --> 00:08:39,920
documents internally for these organizations has 
a lot of the same challenges but mainly you have  

76
00:08:39,920 --> 00:08:46,280
to dedicate very large numbers of staff to be able 
to manage the volume of documents and it becomes a  

77
00:08:46,280 --> 00:08:52,960
big killer of time for these organizations and the 
employees that are the ones that are having to do  

78
00:08:52,960 --> 00:09:00,720
the actual remediation work. So what we have done 
is we have introduced Equidox AI which can fully  

79
00:09:00,720 --> 00:09:05,840
automate the accessibility portion of making 
these documents accessible using artificial  

80
00:09:05,840 --> 00:09:11,920
intelligence, a combination of machine learning 
and computer vision. So we are essentially  

81
00:09:11,920 --> 00:09:16,880
applying training to these artificially 
intelligent models to teach it what these  

82
00:09:16,880 --> 00:09:21,200
documents look like, the different structures 
that are making them up and then it can fully  

83
00:09:21,200 --> 00:09:27,080
automate the process to ensure that the documents 
are accessible and being delivered to the customer  

84
00:09:27,080 --> 00:09:36,040
without any issues of using it with their screen 
reading technology. So Equidox AI, it all starts  

85
00:09:36,040 --> 00:09:42,000
with human programming. So I just want to make 
it clear that Equidox AI is not “auto-tagging.”  

86
00:09:43,440 --> 00:09:48,280
There are many people who will throw around the 
term “auto-tag,” meaning that it's automatically  

87
00:09:48,280 --> 00:09:53,360
creating tags for the PDF and the tags are what 
are being used by screen readers and assistive  

88
00:09:53,360 --> 00:10:00,440
technology to interact with the content. Equidox, 
although it is applying tags in an automated way,  

89
00:10:00,440 --> 00:10:09,960
it is not auto-tagging. Auto-tagging requires 
basically hard coding to teach an auto-tagger that  

90
00:10:09,960 --> 00:10:17,720
this type of font should be a certain type of tag. 
It is very inaccurate it's very unreliable it will  

91
00:10:17,720 --> 00:10:25,000
not produce compliant or usable documents. So what 
we do with Equidox is we start with human work  

92
00:10:25,000 --> 00:10:32,440
being done up front. We train the AI models based 
on the structures of that specific PDF template  

93
00:10:32,440 --> 00:10:37,680
that whatever that template may look like, it 
could be a bank statement, it could be a utility  

94
00:10:37,680 --> 00:10:46,880
bill, it could be an explanation of benefits on 
an insurance form… So we have a combination of  

95
00:10:46,880 --> 00:10:54,280
our data scientists who are doing the actual 
AI training, we have our software developers  

96
00:10:54,280 --> 00:11:00,160
who are implementing this technology, and we of 
course have accessibility experts on staff who can  

97
00:11:00,160 --> 00:11:08,760
assist in that training of the AI models because 
they know exactly how to tag a PDF document.

98
00:11:08,760 --> 00:11:15,760
So just to go through a little bit of the process… 
So Equidox AI is implemented postprocessing.  

99
00:11:15,760 --> 00:11:21,600
And what I mean by that is you do not have to 
completely uninstall and recreate a process for  

100
00:11:21,600 --> 00:11:28,040
building your PDF documents. Many organizations 
already have a very well-established process in  

101
00:11:28,040 --> 00:11:35,080
place to create and deliver these documents to 
their customers. We are are placing ourselves  

102
00:11:35,080 --> 00:11:41,240
into that workflow seamlessly without having to 
completely rebuild that process from the ground  

103
00:11:41,240 --> 00:11:48,840
up which could be a very time-consuming and costly 
endeavor to do so. The first step with Equidox AI  

104
00:11:48,840 --> 00:11:55,280
is, you would provide sample documents to us 
in order for us to analyze the documents. And  

105
00:11:55,280 --> 00:12:00,840
then we would train the AI models based on how 
we analyze those documents. So we teach the AI  

106
00:12:00,840 --> 00:12:05,760
models all of the different elements that are that 
are accounted for in your template. We apply that  

107
00:12:05,760 --> 00:12:10,840
training and then we would integrate the workflow 
so we would figure out how do we want to deliver  

108
00:12:10,840 --> 00:12:16,360
these documents to the customer. Is this something 
where they are downloading a PDF from one of your  

109
00:12:16,360 --> 00:12:22,120
portals? Maybe it's their bank statement, for 
example, or is this something where you would  

110
00:12:22,120 --> 00:12:28,280
like to manage it internally, where perhaps you 
have a bulk import of documents every single month  

111
00:12:28,280 --> 00:12:34,720
that need to be made accessible before they go 
and get posted online? Once that is that decision  

112
00:12:34,720 --> 00:12:38,760
is made as to how we're going to integrate 
the workflow, the process would begin where  

113
00:12:38,760 --> 00:12:44,520
Equidox would apply the tag structure to these 
documents. The documents are then exported from  

114
00:12:44,520 --> 00:12:49,200
the system and then they are delivered through 
whatever mechanism we've determined. Whether  

115
00:12:49,200 --> 00:12:54,800
it's directly to a specific customer of yours, or 
if it's to some sort of data repository so that  

116
00:12:54,800 --> 00:13:02,600
these documents can be uploaded to your internet 
or website or wherever it needs to go. So just a  

117
00:13:02,600 --> 00:13:08,600
a quick rundown of how we analyze PDF documents 
we don't need to get too technical with this but  

118
00:13:11,360 --> 00:13:17,800
basically these color dots that we're seeing on 
the screen here these color dots just represent  

119
00:13:17,800 --> 00:13:24,440
the AI's analysis of different variations 
of documents. So they are grouped together  

120
00:13:24,440 --> 00:13:29,920
in different areas by the AI based on different 
anchors that it's seeing. So for example these  

121
00:13:29,920 --> 00:13:35,920
documents all contain pie charts so that is what 
would group them together in a specific cluster,  

122
00:13:35,920 --> 00:13:41,520
and it would trigger the AI to look for certain 
variables and certain elements on this PDF that  

123
00:13:41,520 --> 00:13:49,120
are consistent with the training that we have 
provided. Here's another example where you can  

124
00:13:49,120 --> 00:13:55,920
see that a number of documents, in this case, 
are sorted into different segments based on the  

125
00:13:55,920 --> 00:14:02,640
number of columns. So you have certain pages that 
might have two-column layouts. Other pages might  

126
00:14:02,640 --> 00:14:09,200
have three or four or a single layer or single 
column layout per page. So it's always based  

127
00:14:09,200 --> 00:14:15,120
on the template and the training that we provide 
from that initial analysis of the documents that  

128
00:14:15,120 --> 00:14:25,160
you've given to us so that we can teach the model 
exactly how to tag the various elements. One final  

129
00:14:25,160 --> 00:14:31,960
thing to call out is just the ability to even tag 
tables. So if you think of like an easy example to  

130
00:14:31,960 --> 00:14:37,880
think of would be like your credit card bill it's 
a very static document could be the same document  

131
00:14:37,880 --> 00:14:43,680
template can be provided to hundreds of thousands 
maybe even millions of customers for a credit card  

132
00:14:43,680 --> 00:14:49,040
company. And that document is being produced on 
a monthly basis. Certain customers of that credit  

133
00:14:49,040 --> 00:14:54,760
card company might have a single charge for the 
month on that credit card and their statement  

134
00:14:54,760 --> 00:15:01,560
might be a single page with a single line item for 
a single charge in that table. Another customer  

135
00:15:01,560 --> 00:15:07,640
might have 500 charges on that credit card for the 
month and that statement, although it comes from  

136
00:15:07,640 --> 00:15:12,320
the same template, will be very different. It 
might be 10 pages long and have page after page  

137
00:15:12,320 --> 00:15:17,840
of tables. So we are able to actually find these 
variances and we can account for them to make sure  

138
00:15:17,840 --> 00:15:23,720
that everything is being tagged accurately. So 
it's not just a static layout on every page there  

139
00:15:23,720 --> 00:15:30,040
can be variables across these templates and we're 
able to train the AI models to identify these  

140
00:15:30,040 --> 00:15:40,000
variables and account for them accordingly. So 
the the training of the AI model, just so everyone  

141
00:15:40,000 --> 00:15:46,560
is aware, we do define the different elements. So 
if you've never tagged a PDF document before, PDF  

142
00:15:46,560 --> 00:15:53,040
documents will contain primarily text but there 
has to be a structure applied to the the text on  

143
00:15:53,040 --> 00:15:59,480
the page. For example, there are headings that are 
used for navigation purposes. Tables have specific  

144
00:15:59,480 --> 00:16:05,200
layouts that need to be tagged in a certain way 
so that assistive technology can interact with  

145
00:16:05,200 --> 00:16:12,400
them. There could be lists. The reading order 
is a very important aspect as well. If a page  

146
00:16:12,400 --> 00:16:18,000
has three columns a screen reader needs to be 
told to read down the left-hand column first,  

147
00:16:18,000 --> 00:16:22,120
then the middle column, then the right-hand 
column. If it's not trained on how to do that,  

148
00:16:22,120 --> 00:16:28,000
the screen reader could easily just read clear 
across the top line of all three columns rendering  

149
00:16:28,000 --> 00:16:33,520
the entire page as completely useless. So these 
are the types of training that we that we put  

150
00:16:33,520 --> 00:16:40,880
into the the models to teach it for all of these 
specific variables for the specific template. And  

151
00:16:40,880 --> 00:16:48,160
then of course we have to test the model. So 
this is not just a one-time we teach it what  

152
00:16:48,160 --> 00:16:53,240
this document looks like and we just hope for the 
best. We of course test these models and continue  

153
00:16:53,240 --> 00:16:58,960
to train them throughout. And so our goal is 
always to both pass the automated checkers as  

154
00:16:58,960 --> 00:17:03,360
well as making sure that these documents are 
fully usable for the end user who's going to  

155
00:17:03,360 --> 00:17:10,280
be interacting with them. So we do apply both 
manual checks as well using screen readers to  

156
00:17:10,280 --> 00:17:16,520
sort of replicate how a blind user might be 
interacting with that document. So these are  

157
00:17:16,520 --> 00:17:23,080
very very important aspects of PDF accessibility 
not just auto-tagging and hoping that it passes an  

158
00:17:23,080 --> 00:17:29,280
automated checker. It really only matters if the 
end user that's receiving the document is able to  

159
00:17:29,280 --> 00:17:37,280
interact with it and that's what really matters 
most to us. And also, I alluded to this earlier,  

160
00:17:37,280 --> 00:17:43,920
but there are different methods of deploying 
Equidox AI technology. So we do have we do  

161
00:17:43,920 --> 00:17:49,320
have an interface that we have built which I will 
be demonstrating here in just a moment. So we've  

162
00:17:49,320 --> 00:17:56,200
built an interface that a customer would be able 
to run this technology themselves if they prefer.  

163
00:17:56,200 --> 00:18:01,640
We can also embed this technology through through 
APIs. So like I said before, we can make sure  

164
00:18:01,640 --> 00:18:08,720
that this is fitting into your existing workflow 
and you're able to apply the tags and deliver an  

165
00:18:08,720 --> 00:18:15,040
accessible document in a fully seamless transition 
where no human is required at all. And then we  

166
00:18:15,040 --> 00:18:22,120
can also operate this as a managed service. So we 
can run the entire process and technology for you  

167
00:18:22,120 --> 00:18:29,120
and deliver those documents to you, depending on 
the use case, depending on security requirements,  

168
00:18:29,120 --> 00:18:34,920
anything. Every customer may have some different 
requirements and we're here to work with you and  

169
00:18:34,920 --> 00:18:41,520
figure out the best method of delivering these 
documents in an accessible way. Okay so what I'm  

170
00:18:41,520 --> 00:18:46,520
going to do now is actually transition out of 
this slide deck and we will get into the actual  

171
00:18:46,520 --> 00:18:52,800
demonstration of Equidox AI. So if I just go 
to this other tab here I have in my browser,  

172
00:18:52,800 --> 00:18:57,400
this is the interface that we have built just 
to kind of demonstrate the technology to make it  

173
00:18:57,400 --> 00:19:02,160
easier to understand what's actually happening. 
So right now I have a completely blank slate I  

174
00:19:02,160 --> 00:19:06,400
have nothing really to work with as we can see so 
what I'm going to do first is I'm going to go to  

175
00:19:06,400 --> 00:19:11,760
the Upload Documents tab. When I arrive at this 
tab here I can then just open up the folders on  

176
00:19:11,760 --> 00:19:17,960
my hard drive and in this case I'll just drag a 
.zip file that contains some bank statements that  

177
00:19:17,960 --> 00:19:24,040
we have scrubbed. See these are just like sample 
bank statements and we will upload that .zip file  

178
00:19:24,040 --> 00:19:32,280
containing the financial statements. So once these 
documents upload, I can then go to the Run Batch  

179
00:19:32,280 --> 00:19:38,000
tab here on the left-hand side. I will then choose 
the model that I want to apply. In this case, here  

180
00:19:38,000 --> 00:19:43,720
we've only got three models currently uploaded 
to my little interface here for demo purposes,  

181
00:19:43,720 --> 00:19:49,320
so what I'm going to do is I'm going to select the 
statement model. I will then choose the .zip radio  

182
00:19:49,320 --> 00:19:54,880
button here and I will select that .zip folder 
that I have just uploaded just a second ago. Once  

183
00:19:54,880 --> 00:20:02,200
I've selected the .zip file and I've selected 
my appropriate model, I just hit Run Batch and  

184
00:20:02,200 --> 00:20:07,560
this will kick off a process where Equidox is 
currently ingesting the documents. It is looking  

185
00:20:07,560 --> 00:20:12,760
at them kind of page by page, one by one and it 
is taking all of that model training that we have  

186
00:20:12,760 --> 00:20:18,880
done ahead of time and it is automatically tagging 
these PDFs. So we'll see these green lights start  

187
00:20:18,880 --> 00:20:25,080
to light up here as we work through the process. 
So you can see one of them is already complete,  

188
00:20:25,080 --> 00:20:31,120
and we will see more of these green lights kind 
of lighting up in just a few seconds. Now keep in  

189
00:20:31,120 --> 00:20:38,320
mind that this is just a demo environment of this 
technology. Equidox AI can be scaled to meet much  

190
00:20:38,320 --> 00:20:44,560
higher demands and throughput. Of course, certain 
organizations might require literally hundreds of  

191
00:20:44,560 --> 00:20:49,760
thousands of documents every single day to be 
remediated. We can just dedicate additional  

192
00:20:49,760 --> 00:20:55,120
resources to it in order to power it to meet those 
types of demands for speed. While these documents  

193
00:20:55,120 --> 00:20:59,840
are going through the process, I'm just going to 
open up one of them here just so that you can see  

194
00:20:59,840 --> 00:21:05,360
what these documents look like. So if I open 
up like randomly statement number four here,  

195
00:21:05,360 --> 00:21:11,480
what I can see is that this is a sort of 
generic-looking bank statement. We have  

196
00:21:11,480 --> 00:21:17,240
images up here, we have text, we have headings, 
we have tables. But this document is completely  

197
00:21:17,240 --> 00:21:23,000
untagged in its current form. If a screen reader 
was to interact with this document it would tell  

198
00:21:23,000 --> 00:21:28,600
them that this is a blank PDF. So they would not 
be able to interact with this. They would have  

199
00:21:28,600 --> 00:21:34,840
no idea what their monthly transactions were. 
They wouldn't know what their balance due was.  

200
00:21:34,840 --> 00:21:40,360
Obviously, that's a huge problem because you want 
to… some people really need to make sure that they  

201
00:21:40,360 --> 00:21:44,800
are being charged appropriately for all of their 
transactions for the month and they, of course,  

202
00:21:44,800 --> 00:21:49,520
need to know how much they need to pay for their 
credit card bill. So we need to make sure that  

203
00:21:49,520 --> 00:21:54,800
these documents are being tagged and delivered 
in an accessible way. So with that said while I  

204
00:21:54,800 --> 00:22:00,080
was talking there the whole process finished. I 
can see the status is now done. So all of those  

205
00:22:00,080 --> 00:22:06,520
documents finished processing. I can look at the 
individual PDF files. So if I were to let's say  

206
00:22:06,520 --> 00:22:18,560
just download one of them I will download this 
and save it to my desktop. And if I were to open  

207
00:22:18,560 --> 00:22:25,160
this up in Adobe Acrobat, I will see that this 
version of the document is now fully tagged. So  

208
00:22:25,160 --> 00:22:30,520
if you're familiar with tag structures, you know 
how complicated it is to manually set up these  

209
00:22:30,520 --> 00:22:35,080
types of tag trees in Adobe Acrobat. If you're 
doing it manually it's a very time-consuming  

210
00:22:35,080 --> 00:22:41,800
process. It requires a lot of technical expertise 
and even if you are the best Adobe Acrobat user in  

211
00:22:41,800 --> 00:22:48,960
the world it is still very very time-consuming. 
So at the scale of things like statements, where  

212
00:22:48,960 --> 00:22:53,000
there could be literally hundreds of thousands 
of them produced every single day by a single  

213
00:22:53,000 --> 00:22:58,360
organization, it is completely unsustainable to 
expect human remediators to go through the process  

214
00:22:58,360 --> 00:23:04,960
of tagging these elements manually. But now if I 
look at this version of the PDF, I have the logo  

215
00:23:04,960 --> 00:23:12,080
has been described. We've trained it to apply 
this company logo alt description to the logo  

216
00:23:12,080 --> 00:23:18,840
whenever it sees this particular image. We have 
text identified so the entire document is tagged.  

217
00:23:18,840 --> 00:23:25,040
As we can see here, we have text identified, so 
the bank name and the customer name. We have our  

218
00:23:25,040 --> 00:23:30,520
figure tag which is just the image, we have our 
heading level one. As we tab through we can see  

219
00:23:30,520 --> 00:23:36,880
we have an H2 for the account summary, the table 
which is nested below it has been properly tagged.  

220
00:23:36,880 --> 00:23:41,360
So you can see all of the rows of the table are 
properly tagged. We jump down to another heading  

221
00:23:41,360 --> 00:23:47,120
level two for the deposits and credits, another 
table that is properly tagged, another heading,  

222
00:23:47,120 --> 00:23:52,880
another table… All of these different elements 
have been accurately accounted for because of  

223
00:23:52,880 --> 00:24:02,760
the initial training that we have put into this 
document template. So at the scale of a company  

224
00:24:02,760 --> 00:24:08,680
that is mass producing these types of documents, 
we can now fully automate that process so none of  

225
00:24:08,680 --> 00:24:16,720
your staff has to spend countless hours of their 
week remediating PDFs. This type of process can  

226
00:24:16,720 --> 00:24:23,720
be applied to other templates. So it's not just 
for bank statements. It could be explanations of  

227
00:24:23,720 --> 00:24:30,760
benefits, it could be bills, like utility bills or 
medical bills, or medical statements and reports  

228
00:24:30,760 --> 00:24:39,680
and test results. There's an endless amount of 
of use cases for Equidox AI. It really just comes  

229
00:24:39,680 --> 00:24:44,400
down to the customer and the types of documents 
that they're producing. But we would certainly  

230
00:24:44,400 --> 00:24:50,520
love to chat with you based on your specific use 
case and your specific template to see if Equidox  

231
00:24:50,520 --> 00:24:58,680
AI would be a good fit for your organization. 
So closing out of this document now I can also  

232
00:24:58,680 --> 00:25:04,160
download all of these documents in a batch as 
well. So if I go to my Batches and Jobs Tab here,  

233
00:25:04,160 --> 00:25:08,880
this is the batch that I just ran. So I would 
be able to extract all of these documents in a  

234
00:25:08,880 --> 00:25:13,000
.zip file as well. So I'm able to download 
them as a .zip just like I delivered it to  

235
00:25:13,000 --> 00:25:18,040
Equidox. But keep in mind you don't always have 
to run this process through this through this  

236
00:25:18,040 --> 00:25:23,360
interface. We can run this process for you as a 
managed service, or the technology that's kind  

237
00:25:23,360 --> 00:25:29,280
of going on behind the scenes can be seamlessly 
placed within your existing workflow so that we  

238
00:25:29,280 --> 00:25:35,880
are not disrupting a longstanding process that 
you have for generating and delivering these  

239
00:25:35,880 --> 00:25:49,640
PDF documents. Okay so just as a quick summary. 
Equidox is a leader in PDF remediation. This is  

240
00:25:49,640 --> 00:25:56,480
all that Equidox does. We are entirely focused 
on PDF remediation. So we can solve your PDF  

241
00:25:56,480 --> 00:26:02,440
remediation challenges whether it's a large or a 
small project. Many of you are here and this may  

242
00:26:02,440 --> 00:26:08,000
be your first introduction to Equidox. Keep in 
mind that that is only part of what we offer. So  

243
00:26:08,000 --> 00:26:14,680
the Equidox AI solution is our newest technology. 
But we also have Equidox Software that is meant  

244
00:26:14,680 --> 00:26:21,520
for more unique one-of-a-kind ad hoc documents. 
So there are many organizations that are producing  

245
00:26:21,520 --> 00:26:27,080
you know marketing flyers or just documents 
that are meant for kind of one-off use. They  

246
00:26:27,080 --> 00:26:34,040
might not be producing them en mass. So Equidox 
software is designed to dramatically speed up and  

247
00:26:34,040 --> 00:26:39,160
make more efficient the process of going through 
and tagging those documents that have completely  

248
00:26:39,160 --> 00:26:44,840
unique elements where we can't necessarily train 
artificial intelligence to fully automate that  

249
00:26:44,840 --> 00:26:50,840
process. We have tools built into that Equidox 
technology that are powered by artificial  

250
00:26:50,840 --> 00:26:56,560
intelligence to speed things up, but there are 
certain examples of documents where you do need  

251
00:26:56,560 --> 00:27:02,720
some sort of human intervention to analyze the PDF 
for context and be able to properly remediate it.  

252
00:27:02,720 --> 00:27:07,320
So if you're interested in those types of use 
cases you can also feel free to reach out to us  

253
00:27:07,320 --> 00:27:13,120
after the fact. We would love to talk to you about 
both or either or use case that you have in mind  

254
00:27:13,120 --> 00:27:18,440
for your organization. And of course, we did just 
see the Equidox AI demonstration there. So you  

255
00:27:18,440 --> 00:27:26,280
have a general idea of how that technology works. 
We will be sharing this slide deck out to everyone  

256
00:27:26,280 --> 00:27:31,400
on the call after after the fact. So there are 
some relevant articles here if you are new to  

257
00:27:31,400 --> 00:27:37,440
PDF accessibility or digital accessibility. If 
anything of anything presented today was confusing  

258
00:27:37,440 --> 00:27:42,360
we will certainly give you some resources of some 
relevant articles and we do have a really large  

259
00:27:42,360 --> 00:27:49,480
library of information on our website as well. 
So feel free to interact with these articles and  

260
00:27:49,480 --> 00:27:54,520
check out some of our past webinars if you're 
interested in seeing our other technology. But  

261
00:27:54,520 --> 00:27:59,960
also please feel free to reach out to us for a 
more personalized demonstration and discussion  

262
00:27:59,960 --> 00:28:06,360
around your use cases. So with that said I'm 
going to pass it back over to Pat. We just have  

263
00:28:06,360 --> 00:28:13,106
a minute or so left to to kind of wrap things up 
but thank you everyone for for attending today. 

264
00:28:13,106 --> 00:28:18,360
[Pat Needles] Thank you, Dan. Great job great 
presentation. I hope that all of the folks here on  

265
00:28:18,360 --> 00:28:26,200
the call today saw the great value in the Equidox 
AI tool. And we'd love to hear from anybody who  

266
00:28:26,200 --> 00:28:32,800
feels as though there might be a proper use case 
not only for our AI solution but as Dan said our  

267
00:28:32,800 --> 00:28:40,040
PDF ad hoc remediation software tool. And you 
could reach us at EquidoxSales@equidox.co,  

268
00:28:40,040 --> 00:28:44,600
of course, you can always reach out to 
us by phone you see the number there,  

269
00:28:44,600 --> 00:28:53,720
or if you would just like general information 
feel free just to visit us at www.Equidox.co.  

270
00:28:57,560 --> 00:29:35,080
And that concludes today's presentation. For 
more information about how Equidox Software  

271
00:29:35,080 --> 00:29:42,200
Company can help you with PDF accessibility, 
email us at EquidoxSales@Equidox.co or give us  

272
00:29:42,200 --> 00:29:50,520
a call at 216-529-3030, or visit 
our website at www.equidox.co.