Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Foundations of Agentic AI

• Understanding autonomous agents: key definitions and classification
• The agent loop: the perceive, decide, act, and observe cycle
• Designing agent responsibilities and defining their operational scope

Python Tools and Agent SDKs

• Bootstrapping agents using LangChain and similar SDKs
• Mastering asynchronous programming, task queues, and subprocess management
• Managing packaging, virtual environments, and reproducible development workflows

Connecting to External Tools and APIs

• Crafting tool interfaces and safe invocation patterns
• Establishing connections to web APIs, databases, and internal services
• Handling credentials, secrets, and least-privilege access controls

Managing Memory, State, and Context

• Leveraging short-term context windows and prompt engineering techniques
• Architecting long-term memory using Redis, vector stores, and retrieval augmentation
• Maintaining consistency, implementing caching strategies, and ensuring memory hygiene

Orchestrating Multi-Step Workflows and Planning

• Chaining actions, managing subagents, and decomposing tasks
• Comparing planning algorithms with heuristic orchestration
• Managing failures, implementing retries, and executing compensating actions

Ensuring Safety, Testing, and Observability

• Developing threat models, conducting red-teaming, and sanitizing inputs/outputs
• Executing unit, integration, and end-to-end testing for agents
• Implementing logging, metrics, tracing, and alerting to monitor agent behavior

Agent Deployment, Scaling, and MLOps

• Implementing containerization, CI/CD pipelines, and rollout strategies
• Optimising costs, rate limiting, and resource utilisation
• Establishing monitoring, governance, and operational playbooks

Wrap-up and Future Directions