Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Fundamentals of Agentic AI

• Defining autonomous agents: core concepts and taxonomy.
• The agent loop: the perceive, decide, act, and observe cycle.
• Design patterns for agent responsibilities and scope.

Python Tooling and Agent SDKs

• Utilising LangChain and similar SDKs to initialise agents.
• Async programming, task queues, and subprocess management.
• Packaging, virtual environments, and reproducible development workflows.

Integrating External Tools and APIs

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

Memory, State, and Context Management

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

Orchestration, Planning, and Multi-Step Workflows

• Chaining actions, subagents, and task decomposition.
• Planning algorithms versus heuristic orchestration.
• Handling failures, retries, and compensating actions.

Safety, Testing, and Observability

• Threat models, red-teaming, and input/output sanitisation.
• Unit, integration, and end-to-end testing for agents.
• Logging, metrics, tracing, and alerting for agent behaviour.

Deployment, Scaling, and MLOps for Agents

• Containerisation, CI/CD pipelines, and rollout strategies.
• Cost control, rate limiting, and resource optimisation.
• Monitoring, governance, and operational playbooks.

Summary and Next Steps