Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Foundations of Agentic AI

• Defining autonomous agents: conceptual frameworks and classification
• The agent loop: the perceive, decide, act, and observe cycle
• Structuring agent responsibilities and defining operational scope

Python Ecosystem and Agent SDKs

• Leveraging LangChain and comparable SDKs to initialize agents
• Implementing async programming, task queues, and subprocess management
• Managing packaging, virtual environments, and reproducible development processes

Connecting External Tools and APIs

• Creating secure tool interfaces and safe invocation patterns
• Linking agents to web APIs, databases, and internal services
• Oversight of credentials, secrets, and least-privilege access controls

Handling Memory, State, and Context

• Optimizing short-term context windows and applying prompt engineering techniques
• Designing long-term memory structures: utilizing Redis, vector stores, and retrieval augmentation
• Maintaining consistency, implementing caching strategies, and ensuring memory hygiene

Orchestration, Planning, and Multi-Step Processes

• Managing action chains, subagents, and task decomposition
• Comparing planning algorithms with heuristic orchestration methods
• Addressing failures, implementing retries, and executing compensating actions

Safety, Testing, and Observability

• Establishing threat models, conducting red-teaming, and sanitizing inputs/outputs
• Performing unit, integration, and end-to-end testing for agent systems
• Implementing logging, metrics, tracing, and alerting for agent behavior

Deployment, Scaling, and MLOps for Agents

• Utilizing containerization, CI/CD pipelines, and effective rollout strategies
• Managing costs, applying rate limiting, and optimizing resource usage
• Overseeing monitoring, governance, and operational playbooks

Recap and Future Directions