Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Foundations of Agentic AI

• Defining autonomous agents: core definitions and classifications
• The agent loop: the perceive, decide, act, and observe cycle
• Establishing design patterns for agent responsibilities and scope

Python Tooling and Agent SDKs

• Utilising LangChain and similar SDKs to initiate agent development
• Managing async programming, task queues, and subprocesses
• Implementing packaging, virtual environments, and reproducible development workflows

External Tool and API Integration

• Creating tool interfaces and secure invocation patterns
• Connecting to web APIs, databases, and internal services
• Managing credentials, secrets, and least-privilege access

Memory, State, and Context Management

• Managing short-term context windows and prompt engineering techniques
• Building long-term memory architectures using Redis, vector stores, and retrieval augmentation
• Ensuring consistency, applying caching strategies, and maintaining memory hygiene

Orchestration, Planning, and Multi-Step Workflows

• Chaining actions, sub-agents, and task decomposition
• Comparing planning algorithms with heuristic orchestration
• Managing failures, retries, and compensating actions

Safety, Testing, and Observability

• Developing threat models, red-teaming, and sanitising inputs/outputs
• Conducting unit, integration, and end-to-end testing for agents
• Implementing logging, metrics, tracing, and alerting for agent behaviour

Deployment, Scaling, and Agent MLOps

• Implementing containerisation, CI/CD pipelines, and rollout strategies
• Controlling costs, applying rate limiting, and optimising resources
• Monitoring, governance, and developing operational playbooks

Summary and Next Steps