We currently ended up having 3 Knowledge repository making it difficult to upkeep the search indexes optimized and continue offering a consistent user experience.  Any suggestions on best practices or tools that sit on top of them to provide an enterprise experience? 

Security Strategy & RoadmapIT Strategy & Roadmap
3.2k viewscircle icon2 Comments
Sort by:
Director of Enablementa year ago

+1 for using a LLM as a chatbot, but with caveats.

A LLM like chatgpt will tokenise a response to generate a synthetic output, but is often prone to hallucinations. So you need to ensure that guardrails are up to limit the scope of potentially incorrect information; however it’s the future of KCS.

I’m currently testing this vendor as a cheap proof of concept. No way affiliated or endorsing, but it might be a good start for you as well before investing further: https://supportchat.link/

Co-Founder & CISO in Finance (non-banking)a year ago

I’m sure you have heard this before but this is actually where AI (LLM) shines. You can hire a dev agency to build you a custom AI knowledge these days for 10-15k. You iwll be able to import all your knowledge repos and simply ask the AI your questions and it should be able to give pretty good answers.

Content you might like

I would like to hear from others that have implemented SailPoint Identity Security Cloud how they staffed after go-live and skills needed. Were there added duties, change in roles, etc. We have provisioners currently and going live with ISC in a few weeks. I am looking ahead to where I can implement role changes with the team. Any help would be appreciated. 

How are you currently managing SIEM costs? Have you found effective ways to actually reduce storage costs for your SIEM?

Read More Comments

What’s the top cybersecurity challenge concerning your organization right now?

AI-driven threats (deepfakes, automated attacks) 25%

Software supply chain risks 8%

Insider risk (both malicious & accidental) 8%

Regulatory compliance 17%

Cloud misconfigurations 8%

Shadow IT (or shadow AI) 8%

Ransomware 8%

Talent shortage in cybersecurity8%

Something else (comment to explain)8%

View Results

‘AI’ Business Model – With many components flowing into the AI domain (cost, data, E&C, people, value, strategy, duplication of everything, etc.), I’ve started to think about splitting out ‘AI’ from the operating model and putting it into a separate legal entity. This way, I could manage a) risk and compliance, b) cost, c) resource allocation, d) governance, e) IP, f) revenue generation, etc.

Of course, this isn’t new in general, but I’m especially interested in how this approach could help with the ongoing challenge of ensuring compliance with data privacy and regulations related to LLMs and data access/usage over time.

My question: Is anyone else thinking about this, or has anyone already done it? I know there are examples in the literature, but I wanted to float this here for general comments and discussion.

What is the most critical information you expect your cybersecurity team to deliver to you on a consistent basis?

Strategies to prevent ransomware from impacting data backup & recovery33%

What it will take to restore minimal operations after a compromise48%

How prepared the organization is to engage law enforcement in the event of an attack15%

How prepared it is to engage cybersecurity investigators2%

Other (share below)

View Results