Agents

Diagnose AI agents that repeatedly call tools, revisit the same state, or fail to converge on a result.

AI systems that use models, tools, context, and control logic to complete tasks.

Diagnose tool-calling failures caused by schemas, authorization, validation, runtime errors, and ambiguous tool results.

Understand the current distinction between Bedrock Agents Classic and Amazon Bedrock AgentCore when designing agentic applications.

Current Azure AI certification path for 2026, covering AI-901 fundamentals and AI-103 for developing AI apps and agents on Azure.

Core security controls for LLM, RAG, and agentic AI applications.

A design case for tool-using AI agents with bounded execution, authorization, observability, and safe failure handling.