Skylar AI - The Future of AIOps and Observability
As continued from Part1 of this blog ScienceLogic’s flagship AIOps product, has arguably the industry’s most complete set of integrations for telemetry collection, enabling insights and rapid automation, and supports almost any kind of device and environment - from legacy through to containers and cloud platforms. Skylar AI is designed to work alongside SL1 to deliver a new class of insights, recommendations, visualizations and user experience. At a high-level, the engine behind Skylar AI receives telemetry from SL1 and sends insights back to SL1 that can drive automations, third-party integrations and leverage all other capabilities of SL1. It also has future support to ingest third-party streaming telemetry and customer documents (such as KB articles and support tickets). The data lake within Skylar AI can also be accessed via third-party tools that support ODBC. Skylar AI is Being Released as a Suite of Services Skylar AI will initially comprise three primary services which are briefly described below. 1. SkylarAutomated RCA - AI-based Root Cause Analysis for Logs Solves the pain point of identifying and troubleshooting problems found in application and infrastructure logs. Streaming logs are analyzed in real-time to quickly identify details of problems and summarize their root cause showing key log lines and using GenAI to create plain language summaries. Skylar Automated RCA is available now. 2. Skylar Analytics – A set of AI/ML and advanced analytic and data exploration capabilities Skylar Analytics is designed to derive new value from data collected by SL1 by offering: Predictive Alerting – Accurately models and predicts impending issues with key resources such as disks, memory and CPU. Predictive alerting is designed to let you know about potential future issues with enough time to act and prevent them from happening in the first place. Always on Anomaly Detection – When troubleshooting a problem, allows you to see any associated metrics that appear to be abnormal. There is also a capability to set up alerting when a particular metric is anomalous. Data Visualization – A modern and highly flexible dashboarding environment and no-code visualization builder with over 40 visualization types. Data Exploration – The ability to use third-party reporting and data exploration tools that support the industry standard ODBC interface. Skylar Analytics is planned for release in the fall. 3. Skylar Advisor – Automated guidance to optimize IT operations and proactively avoid issues Skylar Advisor introduces a fundamentally new user experience for the IT Operator. It will automatically provide the user with important insights, predictions and actionable recommendations to keep everything running optimally. Details onavailability of Skylar Advisor are coming soon. The latest information about Skylar AI can be found by visiting: https://sciencelogic.com/platform/skylar-aihttps://sciencelogic.com/platform/skylar-ai.Skylar AI - The Future of AIOps and Observability
Everything’s down. Frustrated customers are calling, emailing and posting on social media. You assemble a war room. News of the problem is spreading like wildfire and has just reached the CEO at the most inopportune moment (think dinner/vacation/out with the kids). Your cell phone and Slack feed are going nuts. Meanwhile, the front-line technical teams are looking at dashboards and digging through logs, events and metrics, trying to understand what happened. They’re not making much progress, so you escalate and call in more experts. An hour later there’s still no obvious answer. You escalate it again, but this time to the development team. And, eventually, 14 very long hours later, a “rockstar” developer figures it out. The immediate crisis is over, but there will be painful days of work ahead for you and your team dealing with disgruntled customers, driving a detailed postmortem process and then coming up with an action plan to prevent a repeat occurrence of what just happened. Enter Skylar AI - The Future of AIOps and Observability Now imagine a different scenario: Skylar: “Your orders server just went down because it hit a race condition in one of the open source components. Good news, there’s a quick solution. You are running v2.3.1.2 of the component and the issue has been fixed in v2.3.1.4. Would you like me to show you how to upgrade to the fixed version?” The goal of Skylar AI is to reason over not just telemetry, but also the stored knowledge of an organization to deliver accurate insights, recommendations, and predictions, so that: When something fails, it will tell you in plain language what happened and how to fix it. If something is going to fail, it will tell you how to prevent it from failing and impacting production. It will also be able to deliver all insights and answer any question asked of it by drawing on telemetry together with relevant information from a company’s stored knowledge (e.g. KB articles, support tickets, bug databases, product documentation, etc.) Gen AI is Everywhere,how is Skylar AI Different? The Fundamental Challenge Before explaining how Skylar AI is different, it’s important to understand the problem Skylar AI was designed to address: that today’s best-of-breed AIOps, monitoring and observability tools place too much reliance on human expertise. The situation above is a prime example. The problem had never been seen before (an “unknown/unknown”) and so there were no rules in place to catch it. This meant human experts with the right tribal knowledge were needed to figure things out. The tools provided all the information needed to ultimately solve the problem, but at each step of the way, the right human expert(s) needed to interpret and analyze the data, decide on the next course of action and keep iterating until the problem was finally solved. Ultimately, this required multiple escalations and a lot of wasted time and frustration. The goal of Skylar AI is to make Level 1 and 2 teams more effective and productive and able to solve a broader range of problems more quickly. So that situations like the above can be handled without the pain and wasted time. So why not Follow the Industry Trend and Build an AI Assistant? The industry is quickly moving towards the use of Generative AI (GenAI) and large language models (LLMs) in the form of “AI Assistants” or “AI Chatbots”. These appear as small chat panels in a product’s UI and allow a user to ask questions of the tool in plain language. So, instead of learning how to construct a complex query and visualize it on a chart, with an assistant, you can simply ask, “create a dashboard showing average latency for the top 10 devices over the last 3 months”, and it will do just that. However, although assistants are useful in simplifying the way a user interacts with a tool, it is important to understand that a skilled user still needs to know what questions to ask of the assistant at each step of the way – in other words reliance on deep expertise is still required to get the most out of the tool. Our Breakthrough Invention: An AI Advisor, rather than an AI Assistant To deliver on our vision, a new paradigm was needed: an “AI Advisor.” The concept of Skylar Advisor is that instead of a skilled user having to always know what questions to ask of the tool, the Advisor automatically tells the user the answers to the curated questions tailored to the user role without the user having to even ask them in the first place! In other words, Skylar Advisor automatically tells the user what the user needs to know in the form of easy-to-understand insights, predictions, and actions to take. This allows teams of all levels to be far more effective, without wasting precious time and perform more tasks with less effort. The creation of Skylar Advisor, didn’t just necessitate building a pipeline of AI and machine learning (ML) technologies including a self-hosted LLM, — it also required a completely reimagined user experience: An uncluttered and intuitive UI (not a traditional dashboard/event list display) A curated list of what’s most important to user based on the user’s role and areas of responsibility A multi-modal interface to describe a problem The use of contextual “Quick Prompts,” where Skylar suggests what actions a skilled expert would take at each step of the way To see a demonstration of Skylar Advisor, please visithere. Make sure to read Part 2 of this blog that explains the components of Skylar AI and how it works with SL1Introducing our newest Blogger: Gavin Cohen VP of AI Product Management
Hello Nexus Community Members and ScienceLogic Customers, I wanted to take a minute to introduce our newest blogger who will be keeping us up to date on AI Product related announcements, trends and best practices. Gavin Cohen is VP of AI Product Management at ScienceLogic and has over 20 years’ experience across a diverse range of technology roles. At ScienceLogic, he is responsible for defining the company’s AI/ML product roadmap and strategy, working closely with customers, partners and internal teams. Gavin joined ScienceLogic through the acquisition of Zebrium, where he was VP of Product and Marketing and part of the founding team. Prior to joining Zebrium, he was VP of Product and Solutions Marketing at Nimble Storage where he redefined the company’s category and positioning leading to a successful acquisition by HPE. He has also held senior product management, business development and technical evangelist roles in Australia and the U.S. Gavin has a Bachelor of Computer Science and an MBA.
