Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Core Concepts of Agentic AI

• Defining autonomous agents: key definitions and classifications
• The agent loop: the perceive, decide, act, and observe cycle
• Design patterns for defining agent responsibilities and scope

Python Tools and Agent SDKs

• Leveraging LangChain and comparable SDKs to initiate agent development
• Asynchronous programming, task queuing, and subprocess handling
• Packaging, virtual environments, and reproducible dev workflows

External Tool and API Integration

• Crafting tool interfaces and secure invocation patterns
• Linking with web APIs, databases, and internal services
• Handling credentials, secrets, and least-privilege access controls

Memory, State, and Context Handling

• Short-term context windows and prompt engineering methods
• Long-term memory frameworks: Redis, vector stores, and RAG
• Ensuring consistency, caching techniques, and memory maintenance

Orchestration, Planning, and Complex Workflows

• Linking actions, subagents, and breaking down tasks
• Comparing planning algorithms with heuristic orchestration
• Managing failures, retries, and corrective actions

Safety, Testing, and Observability

• Threat modeling, red-teaming, and I/O sanitization
• Unit, integration, and end-to-end testing strategies for agents
• Logging, metrics, tracing, and alerting on agent performance

Deployment, Scaling, and Agent MLOps

• Containerization, CI/CD pipelines, and release strategies
• Cost management, rate limiting, and resource efficiency
• Monitoring, governance, and operational runbooks

Wrap-Up and Future Directions