AOS-8 AI Operations, Reliability & Observability
AOS-8 AI Operations, Reliability & Observability
- Course description
- Course CodeAOS-8
- Level of Study5.2
- Program of StudyAI Operations Specialist
- Credits10
- Study Plan CoordinatorMonde Sineke
This course develops students' competencies in operating, monitoring and maintaining AI-enabled applications and integrations. Students explore how development and operations teams collaborate and apply observability practices, including logging, metrics, tracing, dashboards and alerting. They monitor application availability, AI output quality, response times, usage and operational costs.
Students investigate incidents, performance issues and failures involving external AI services, and implement appropriate reliability measures such as retries, timeouts, rate limits, fallbacks and recovery procedures. They assess operational security and data protection requirements, develop runbooks and participate in post-incident reviews to identify improvements. Throughout the course, students document operational decisions and reflect on practices for maintaining reliable and cost-effective AI-enabled solutions.
The candidate...
- has knowledge of processes and tools for operating AI-enabled applications and integrations, including observability, logging, metrics and tracing
- can assess the operational security of AI services in relation to requirements for protecting sensitive information
- has knowledge of how development and operations work together in the industry to keep AI services and integrations running
The candidate...
- can apply relevant monitoring and troubleshooting techniques to evaluate availability, performance, AI output quality and operational costs
- can reflect over incidents and their own operational practice through post-incident reviews, and adjust it under guidance
- can assess an incident or quality problem in a running AI service, including failures of external AI services, identify the cause and determine what measures need to be implemented
The candidate...
- can plan and carry out the configuration of observability, alerting and operational automation for an AI-enabled application or integration
- can contribute to organisational development by monitoring and improving the reliability and cost of AI services the organisation depends on
Students use a combination of written content, videos and practical learning activities designed to help them achieve the course learning outcomes.
Industry Relevance
Course content, learning activities and tools reflect industry standards and are developed in collaboration with industry partners and experts from the field.
Practical Work
The course includes regular practical activities where students apply their knowledge and practise relevant skills.
Collaboration
Collaboration is facilitated through the LMS and Teams, and students are encouraged to work together for peer support and shared learning.
Guidance
Teachers are available for guidance at scheduled times. Students are encouraged to share work in progress and use feedback from teachers and fellow students to develop their work further.
| Form of assessment | Grading scale | Grouping | Duration of assessment |
|---|---|---|---|
Course Assignment | Pass / Fail | Individual | 1 Week(s) |