Loading video...

Video Failed to Load

Go Home

I kept meaning to write an article for this, decided to record a quick video instead 🎥 TL;DW - Create an auth context, target the auth context in a CA policy (SIF Every time, other conditions), select auth context in PIM role settings Thanks Stephan G for the reminder :)

15,843 views • 1 year ago •via X (Twitter)

8 Comments

Stephan G's profile picture
Stephan G1 year ago

Thanks again for that great input on how to make security better.

Nathan McNulty's profile picture
Nathan McNulty1 year ago

Thank you! So glad I can help 😊

GrittyBlu's profile picture
GrittyBlu1 year ago

@StephanG_AIM Why build a policy only for the auth context? Is there a difference in building a CA policy that targets the app(s) and includes phish-resistant auth with session controls?

Nathan McNulty's profile picture
Nathan McNulty1 year ago

@StephanG_AIM This is a great question! :) Auth contexts are amazing and allow us to do things that resource based policies can't For PIM, we are using Sign-in Frequency - Every time to force a fresh authentication on role activation to prevent an attacker with a stolen token from activating

Andy's profile picture
Andy1 year ago

@StephanG_AIM Would be interesting to also see the sign-in behavior once the above policy is set, because for me; if I set 'sign-in frequency' along with auth context / auth strength, I get stuck in a constant sign-in loop using passkeys in the MS auth app.

Nathan McNulty's profile picture
Nathan McNulty1 year ago

@StephanG_AIM We deploy like this often and it works great, but you do need to have registered the method already. If you don't, I believe it attempts to send you to register and gets stuck.

@m1ru1's profile picture
@m1ru11 year ago

@StephanG_AIM What is the recommendations for high privilege admins GA, Intune, Sharepoints?

Nathan McNulty's profile picture
Nathan McNulty1 year ago

@StephanG_AIM I usually recommend a few CA policies for activating privileged admins (using auth context): 1) Block all users except filter for devices listing explicit deviceIds of admin devices 2) Require phishing resistant auth, SIF - Every time 3) Block outside network location/GSA

Related Videos

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 views • 1 year ago