Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Core Concepts of Agentic AI

• Defining autonomous agents: definitions and classification
• The agent loop: the cycle of perception, decision, action, and observation
• Design patterns for defining agent responsibilities and scope

Python Tools and Agent SDKs

• Bootstrapping agents using LangChain and similar SDKs
• Async programming, task queues, and subprocess management
• Packaging, virtual environments, and reproducible development workflows

Integration of External Tools and APIs

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

Memory, State, and Context Management

• Short-term context windows and prompt engineering strategies
• Long-term memory architectures: Redis, vector stores, and retrieval augmentation
• Maintaining consistency, caching strategies, and memory hygiene

Orchestration, Planning, and Multi-Step Workflows

• Chaining actions, subagents, and task decomposition
• Comparing planning algorithms with heuristic orchestration
• Handling failures, implementing retries, and executing compensating actions

Safety, Testing, and Observability

• Threat modeling, red-teaming, and input/output sanitization
• Unit, integration, and end-to-end testing for agents
• Logging, metrics, tracing, and alerting to monitor agent behavior

Deployment, Scaling, and MLOps for Agents

• Containerization, CI/CD pipelines, and deployment strategies
• Cost control, rate limiting, and resource optimization
• Monitoring, governance, and operational playbooks

Summary and Future Directions