Automate Information Governance with M365 AI and Machine Learning

Atle Skjekkeland


Earlier this year we did a webinar explaining how to automate information governance and records management in Microsoft 365 (M365), and I will in this blog post explain Sensitive Information Types, Trainable Classifiers, and SharePoint Syntex in more detail.

M365 AI and Machine Learning options

Sensitive Information Types

As part of the E3 license, you have Sensitive Information Types with 200+ templates to identify sensitive information. You can also create your custom Sensitive Information Types and then apply Data Loss Prevention policies. Automating the retention or protection for sensitive information requires one of the E5 add-on licenses.

  • Goal: Identify sensitive information, stop or warn users from sharing or saving it, and automate the retention and deletion of it

  • Auto-classification approach: Keywords and proximities, Regular expressions

  • Deployment: tenant wide

  • Pre-built templates: 200+

  • Personas: Compliance admins

Sensitive Information Types

Trainable Classifiers

As part of the E5 license, you have Trainable Classifiers to identify more unstructured content like contracts, resumes, decision memos, etc. If you only have the E3 license, then the E5 Information Protection & Governance add-on license is the cheapest way to get access to Trainable Classifiers.

  • Goal: Automate the identification and classification of unstructured content to ensure compliance and reduce risks, e.g., auto-detect and apply short retention on resumes stored outside dedicated HR sites

  • Auto-classification approach: machine learning with minimum 50 positive samples and review of 200 samples

  • Deployment: tenant wide

  • Pre-built templates: Approx 5 and a lot more coming

  • Personas: Compliance admins

Trainable classifiers

SharePoint Syntex

SharePoint Syntex helps you identify semi-structured information and automate the extraction of data from the files. Syntex requires an extra license in addition to either E3 or E5.

  • Goal: Automate the identification and classification of semi-structured information (similar to Trainable Classifiers), but also automate data extraction.

  • Auto-classification approach: machine teaching with minimum 5 positive and 1 negative samples for auto-classification, but more for data extraction

  • Deployment: selected SharePoint sites

  • Pre-built templates: None

  • Personas: Information workers

Next step: Request a 2-Day SharePoint Syntex, Viva Topics and Trainable Classifiers Workshop

Infotechtion is offering eligible Microsoft customers a free 2-day ‘Knowledge and Governance Discovery‘ workshop on following Knowledge management and compliance capabilities. Request more information by submitting the online Contact Us.

  • Information Architecture – which unlocks knowledge in content to power business processes and compliance

  • Knowledge discovery – to connect you with relevant knowledge from across the organization in real-time, in the context of your work

  • Expertise and answers – to connect you with experts, so you can resource projects, share best practices, and get questions answered; and

  • Workplace insights – which help individuals, teams, and organizations ensure well-being and effectiveness

SharePoint Syntex

 © 2024 Infotechtion. All rights reserved 


By submitting this form you agree that Infotechtion will store your details and send future resources. You may opt-out any time.

Recent posts

Job application.

Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorestandard dummy text ever since.

Please fill the form

Job application.

Join Infotechtion for an impactful career filled with passion, innovation, and growth. Embrace diversity, collaboration, and continuous learning. Discover your potential with us. Exciting opportunities await!

Please fill the form

By submitting the form, you confirm that you do not require a visa sponsorship to work in the country of application.