Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Introduction to LLMs and Agent Frameworks
- An overview of large language models in infrastructure automation.
- Key concepts underlying multi-agent workflows.
- Exploring AutoGen, CrewAI, and LangChain: specific use cases within DevOps.
Setting Up LLM Agents for DevOps Tasks
- Installation of AutoGen and configuration of agent profiles.
- Utilizing the OpenAI API and other LLM providers.
- Establishing workspaces and CI/CD-compatible environments.
Automating Test and Code Quality Workflows
- Prompting LLMs to generate unit and integration tests.
- Employing agents to enforce linting, commit rules, and code review guidelines.
- Automating pull request summarization and tagging processes.
LLM Agents for Alert Handling and Change Detection
- Designing responder agents for pipeline failure alerts.
- Analyzing logs and traces using language models.
- Proactively detecting high-risk changes or misconfigurations.
Multi-Agent Coordination in DevOps
- Role-based agent orchestration, including planner, executor, and reviewer roles.
- Managing agent messaging loops and memory states.
- Implementing human-in-the-loop designs for critical systems.
Security, Governance, and Observability
- Addressing data exposure and ensuring LLM safety within infrastructure.
- Auditing agent actions and restricting operational scope.
- Tracking pipeline behavior and monitoring model feedback.
Real-World Use Cases and Custom Scenarios
- Designing agent workflows for effective incident response.
- Integrating agents with platforms like GitHub Actions, Slack, or Jira.
- Best practices for scaling LLM integration within DevOps environments.
Summary and Next Steps
Requirements
- Practical experience with DevOps tooling and pipeline automation.
- Proficiency in Python and Git-based workflows.
- A foundational understanding of LLMs or prior exposure to prompt engineering.
Target Audience
- Innovation engineers and AI-integrated platform leads.
- LLM developers focused on DevOps or automation domains.
- DevOps professionals exploring the capabilities of intelligent agent frameworks.