Cisco Splunk for AI Operations (CSAIOPS)

Upon completing this course, the learner will be able to meet these overall objectives:

• Understand the basics of Splunk and its core software

  • Develop skills in collecting, indexing, and analyzing machine data using Splunk

  • Introduce Splunk data analysis and correlation techniques to enable fast decision making, cost reduction and better customer services in your environment

  • Describe machine learning models and their applications for various tasks using Splunk

  • Introduce Splunk’s feature engineering capability

  • Discuss Splunk Security Essentials and Incident Response for security management

  • Explore the role of Splunk AIOps in supporting Observability in IT Operations

  • Get Hands-on experience in setting up, configuring, and managing a Splunk environment

  • Apply Splunk AI capabilities to real-world use cases and scenarios

The knowledge and skills that a learner should have before attending this course are as follows:

• Familiarity with Cisco Products

• System Engineers
• System Administrators
• Architects
• Channel Partners
• Data Analysts

Module 1: AI Operations Fundamentals

• Understanding AIOps: What it is and why it matters.

• Role of AI in IT operations.

• Overview of Splunk’s AIOps capabilities.

Module 2: Splunk Essentials

• Introduction to Splunk and its core software.

• Navigating the Splunk interface.

• Splunk interoperability.

• Data ingestion and indexing.

• Basic search queries and visualization.

Module 3: Data Preparation and Cleansing using Splunk

• Benefits for the companies using Splunk AI engine in cost reduction and operational efficiency improvements.

• Data quality and preprocessing.

• Handling missing values and outliers.

• Data analysis and correlation techniques in Splunk

Module 4: Cisco Splunk AIOps Use Cases

• Data modeling in Splunk.

• Overview of AIOps and its role in IT Operations.

• Data analysis and correlation techniques in Splunk.

• Predictive analytics for incident prevention.

• Anomaly detection and root cause analysis.

• Full visibility, AIOps, and incident intelligence with Splunk AI.

Module 5: Machine Learning with Splunk

• Introduction to ML algorithms.

• Machine learning models for classification, regression, clustering, and anomaly detection.

• Building Predictive Models using Splunk ML Toolkit

Module 6: AIOps Data Analysis Techniques

• Implementing real-time search, analysis, and visualization of large datasets.
• Event correlation techniques using search commands.
• Clustering and anomaly detection.

Module 7: Operationalizing AIOps with Splunk

• Integrating AIOps insights into incident management.
• Splunk Security Essentials and Incident Response.
• Real-time monitoring and alerting using Splunk Enterprise Security.
• Testing, validating, and fine-tuning security use cases.
• Rapid event detection and human-assisted automation for SecOps, ITOps, and engineering teams.
• Automating responses based on ML predictions.

Module 8: Case Studies and Best Practices

• Success stories from organizations using Splunk for AIOps.
• Integrating AI into everyday workflows for service performance enhancement.
• Tips for effective implementation.

1. Lab Outline

   Lab 1: Setting Up Your Splunk Environment

   • Install and configure Splunk.

   • Navigate Splunk Enterprise UI.

2. Lab 2: Data Analysis Introduction

   • Upload dataset to Splunk.

   • Index sample data for analysis.

   • Create visualizations.

3. Lab 3: Data Preparation

   • Cleanse real-world data.

   • Create relevant features for ML.

   Lab 4: Building Your First AIOps Model using Splunk

   • Train a model to predict incidents.

   • Evaluate model performance.

   Lab 5: Advanced Data Analysis

   • Advanced data analysis techniques.

   • Machine Learning Model deployment.

   • Security Incident Response use case.

   Lab 6: Real-World AIOps Scenarios

   • Analyze live data streams.

   • Implement automated actions based on ML recommendations.