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 21 hours
Course Outline
Foundations of Agentic Systems in Production
- Agentic system design: operational loops, tool utilization, memory management, and orchestration layers
- Agent lifecycle: development phases, deployment strategies, and continuous operation
- Key challenges in managing agents at production scale
Infrastructure and Deployment Models
- Implementing agents in containerized and cloud-native environments
- Scaling strategies: horizontal versus vertical expansion, concurrency handling, and rate limiting
- Multi-agent coordination and workload distribution
Monitoring and Observability
- Essential metrics: response time, success rates, memory consumption, and invocation depth
- Tracking agent execution paths and dependency graphs
- Establishing observability standards using Prometheus, OpenTelemetry, and Grafana
Logging, Auditing, and Compliance
- Centralized log management and structured data collection
- Ensuring regulatory compliance and audit capabilities within agentic workflows
- Developing comprehensive audit trails and replay mechanisms for diagnostic purposes
Performance Tuning and Resource Optimization
- Minimizing inference latency and refining orchestration cycles
- Utilizing model caching and efficient embeddings to accelerate retrieval processes
- Conducting load testing and stress analysis for AI service pipelines
Cost Control and Governance
- Analyzing cost factors: API usage, memory allocation, compute resources, and third-party integrations
- Monitoring agent-specific expenditures and implementing chargeback frameworks
- Establishing automated policies to mitigate unnecessary agent proliferation and idle resource usage
CI/CD and Rollout Strategies for Agents
- Incorporating agent workflows into continuous integration and delivery pipelines
- Executing testing, versioning, and rollback protocols for iterative agent improvements
- Implementing gradual rollouts and secure deployment controls
Failure Recovery and Reliability Engineering
- Architecting for fault tolerance and managed service degradation
- Applying retry, timeout, and circuit breaker patterns to enhance agent dependability
- Defining incident response and post-incident review frameworks for AI operations
Capstone Project
- Constructing and deploying a complete agentic AI system with integrated monitoring and cost tracking
- Simulating high-load scenarios, assessing performance, and refining resource allocation
- Presenting the final architecture and monitoring interface to colleagues
Summary and Next Steps
Requirements
- Advanced understanding of MLOps and production machine learning systems
- Experience with containerized deployments (Docker/Kubernetes)
- Proficiency with cloud cost optimization and observability tools
Audience
- MLOps engineers
- Site Reliability Engineers (SREs)
- Engineering managers overseeing AI infrastructure
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
