You have reached our blog, amazing! We want to share with you what we are doing, what we build, how we look at things and hopefully other things you find interesting. As such, we have been writing blog posts which you will find here.


Remote working - got it under control? - 3 minutes reading time

The recent pandemic has accelerated Work From Home (WFM) like nothing before ever could.

The team at Maiky has undergone a very similar evolution. When we started the company in 2019, we always had to goal to make it a remote-first company, but with the pandemic, it was clear we should be a remote-only company.

Fast forward almost 2 years, 6 people, covering 3 countries across the globe, the decision was the best ever made. While it comes with challenges, even in our small world, at the same time there are massive opportunities as well.

When working remotely takes on a new meaning.
The opportunities everybody knows by now; easier access to talent, more flexibility when it comes to combining work and private life and so much more. But what about the challenges. While we are not going to focus on all, I do want to highlight one.

How do you keep control of everything that happens?

The other day a customer of our Maiky platform raised this question: “How can you keep control when most of the information we get these days on control testing is done when chatting with people at the coffee machine?” She is responsible for checking control effectiveness and has to annually validate, together with her team, over 200 different controls.

While the reflection is good, we believe the solution is wrong. The problem with our current way of testing the effectiveness of controls it is; we don’t test often enough, too manual validations and being too much work that could be spent differently. So our proposed solution is to leverage automation for the control testing, and have discussions with teams when problems are discovered.

In general, situational awareness is lacking. Doing a check once or twice a year just isn’t telling you the whole story.

So how do you know what is going on? How do you tackle your control testing program?

Come and have a chat with us, we would love to learn how you tackle it!


Revolutionizing GRC using AI: from tedious reading to fast consultation. 3 Minutes reading time

Regulations are changing fast and regularly which puts pressure on companies' legal and compliance departments to continuously be aware of it, analyze its consequences for the business activity and adapt its organization policies accordingly.
As IT enables to systemize, Maiky developed an in-house AI engine that is capable to assimilate (read not screen) compliance texts, confront the meaning with a company organization’s policies to simplify and speed up the compliance.
The pipeline input is text, and by leveraging NLP we define distinct meanings of the words in a specific context and the output is an accurate text search.

How is Maiky AI different from what exists today?

1. AI industry trends focuses on the results/output while Maiky focuses on the input/data preparation which delivers a much higher content accuracy.
Example: the term “firewall” can only be insightful if used with proper IT context.

2. Compliance industry trends show AI is applied to numbers to calculate statistics to make predictions or uses automation to screen text location (good old “Ctrl F”) and position (good old “Cut & paste”) while Maiky AI engine uses text to understand compliance topics to manage organization policies effectively.
Examples: Fast/immediate identification of internal controls necessary to be updated to comply with the new update of ISO27001.

What are possible business applications?

Efficient and effective

1) policies management to comply with regulatory changes and align with the security posture of business partners

2) contract (and supplier) management
Maiky AI can review the existing text but also indicate lacking info eg. policies, controls or clauses.

--> In short, Maiky AI is a smart digital assistant that saves you tremendous time reading all compliance texts and enables you to focus on what matters that is maintaining policy consistency and taking informed decisions.

If you want to test your policies level of compliance in comparison with a law or standards, contact us!


Inside Maiky AI. 4 Minutes reading time.

Our Maiky AI is based on a symbiotic collaboration between several advanced AI algorithms.

1. OCR – Optical Character Recognition, is a transformation in which all characters from the image are recognized as such from an image of a text by means of pattern recognition and stored separately by a computer (program). In other words, the text from an image is converted into editable text. An example of this is automatic vehicle number plate recognition.

2. SA – Smart Annotator, is the algorithm which comes with Matcher tool that can be used to specify custom rules for phrase matching. The process to use the Matcher tool is pretty straight forward. The first thing you have to do is define the patterns that you want to match or how we call them (keywords). Next, you have to add the patterns to the Matcher tool and finally, you have to apply the Matcher tool to the document that you want to match your rules with. Finally after the text is being matched we begin extraction and annotation of the identified phrases that are described/explained by our keywords.

3. NER – Named Entity Recognition, is the most important, or I would say, the starting step in Information Retrieval. Information Retrieval is the technique to extract important and useful information from unstructured raw text documents. Named Entity Recognition NER works by locating and identifying the named entities present in unstructured text into the standard categories such as policies, regulations, laws, person names, locations, organizations, time expressions, quantities, monetary values, percentage, codes etc. Our Maiky AI comes with an extremely fast statistical entity recognition system that assigns labels to contiguous spans of tokens. The Maiky AI on Spacy NER system contains a word embedding strategy using sub word features and "Bloom" embed, and a deep convolution neural network with residual connections. The system is designed to give a good balance of efficiency, accuracy and adaptability.

4. LDA – Latent Dirichlet Allocation, is one of the most popular topic modelling methods. LDA is a generative probabilistic model that assumes each topic is a mixture over an underlying set of words, and each document is a mixture of over a set of probabilities. Mainly each document is made up of various words, and each topic also has various words belonging to it. The aim of LDA is to find topics a document belongs to, based on the words in it.

All of this algorithms combined compose the Maiky AI which is able to understand contextual text and extract the necessary information namely regarding to compliance. Our preliminary results are already promising and we are already able to find the needle in the haystack.

Remark: Our research of Spacy as well as NLTK implementation of Stanford NLP concludes that both can be used for NER to achieve good results. Spacy has support for word vectors, so it's fast and accurate. It is recommended to use Spacy NER for production over Stanford NER. For customizing the process of NER, both models can be used. This requires data labelling and annotation which means giving tags to entities.