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.
Course Outline
Core Foundations of Agentic Systems in Production
- Agentic architecture components: loops, tools, memory, and orchestration layers
- The full agent lifecycle: from development and deployment to continuous operation
- Key challenges in managing agents at production scale
Infrastructure and Deployment Paradigms
- Deploying agents within containerized and cloud-native environments
- Scaling strategies: balancing horizontal vs. vertical scaling, concurrency management, and throttling
- Orchestrating multi-agent systems and managing workload distribution
Monitoring and Observability Practices
- Critical metrics to track: latency, success rates, memory consumption, and agent call depth
- Visualizing and tracing agent activity and call graphs
- Implementing observability stacks using Prometheus, OpenTelemetry, and Grafana
Logging, Auditing, and Compliance Standards
- Implementing centralized logging and structured event aggregation
- Ensuring compliance and auditability across agentic workflows
- Building audit trails and replay capabilities to facilitate debugging
Performance Tuning and Resource Efficiency
- Minimizing inference overhead and streamlining agent orchestration cycles
- Leveraging model caching and lightweight embeddings to accelerate retrieval
- Conducting load testing and simulating stress scenarios for AI pipelines
Cost Governance and Financial Control
- Analyzing primary cost drivers: API calls, memory usage, compute resources, and external integrations
- Implementing agent-level cost tracking and chargeback models
- Establishing automation policies to curb agent sprawl and eliminate idle resource consumption
CI/CD Integration and Rollout Strategies
- Embedding agent pipelines into existing CI/CD workflows
- Defining testing, versioning, and rollback protocols for iterative agent enhancements
- Executing progressive rollouts and ensuring safe deployment mechanisms
Reliability Engineering and Failure Recovery
- Designing systems for fault tolerance and graceful degradation
- Applying retry, timeout, and circuit breaker patterns to enhance agent reliability
- Developing incident response and post-mortem frameworks specific to AI operations
Capstone Project
- Construct and deploy a fully monitored agentic AI system with comprehensive cost tracking
- Simulate load, benchmark performance, and refine resource utilization
- Present the final architecture and monitoring dashboard to peers
Course Summary and Future Steps
Requirements
- A robust understanding of MLOps and production-grade machine learning systems
- Hands-on experience with containerized deployments using Docker and Kubernetes
- Working knowledge of cloud cost optimization strategies and observability tools
Target Audience
- MLOps engineers
- Site Reliability Engineers (SREs)
- Engineering managers responsible for overseeing AI infrastructure
21 Hours
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
