Get in Touch

Course Outline

Fundamentals of Agentic AI

  • Understanding autonomous agents: definitions and taxonomy.
  • The agent loop: the perceive, decide, act, observe cycle.
  • Design patterns for defining agent responsibilities and scope.

Python Tooling and Agent SDKs

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

Integrating External Tools and APIs

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

Memory, State, and Context Management

  • Managing short-term context windows and employing prompt engineering techniques.
  • Architecting long-term memory: Redis, vector stores, and retrieval augmentation.
  • Ensuring consistency, optimizing caching strategies, and maintaining memory hygiene.

Orchestration, Planning, and Multi-Step Workflows

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

Safety, Testing, and Observability

  • Developing threat models, conducting red-teaming, and sanitizing input/output.
  • Conducting unit, integration, and end-to-end testing for agents.
  • Implementing logging, metrics, tracing, and alerting for agent behavior.

Deployment, Scaling, and MLOps for Agents

  • Utilizing containerization, CI/CD pipelines, and defining rollout strategies.
  • Managing cost control, rate limiting, and resource optimization.
  • Establishing monitoring, governance, and operational playbooks.

Summary and Next Steps

Requirements

  • Familiarity with Python programming.
  • Experience with REST APIs and asynchronous I/O.
  • Understanding of machine learning concepts and pretrained LLMs.

Audience

  • ML engineers.
  • AI developers.
  • Software engineers.
 21 Hours

Number of participants


Price per participant

Upcoming Courses

Related Categories