Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Foundations of Agentic AI

• Defining autonomous agents: core concepts and classification
• The agent loop: the perceive, decide, act, and observe cycle
• Architectural patterns for defining agent scope and responsibilities

Python Tools and Agent SDKs

• Leveraging LangChain and comparable SDKs to initialize agents
• Async programming, task queuing, and managing subprocesses
• Managing dependencies, virtual environments, and reproducible dev workflows

Connecting External Tools and APIs

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

Managing Memory, State, and Context

• Optimizing short-term context windows and applying prompt engineering techniques
• Designing long-term memory systems using Redis, vector stores, and RAG
• Ensuring data consistency, caching strategies, and memory hygiene

Orchestrating Planning and Multi-Step Workflows

• Linking actions, managing subagents, and decomposing complex tasks
• Comparing planning algorithms with heuristic orchestration methods
• Addressing failures, implementing retries, and executing compensating actions

Ensuring Safety, Testing, and Observability

• Applying threat models, red-teaming, and input/output sanitization
• Conducting unit, integration, and end-to-end tests for agents
• Implementing logging, metrics, tracing, and alerts for agent performance

Deployment, Scaling, and Agent MLOps

• Utilizing containerization, CI/CD pipelines, and effective rollout strategies
• Controlling costs, managing rate limits, and optimizing resource usage
• Overseeing monitoring, governance, and operational procedures

Recap and Future Directions