What Are AI Agents?
Understanding AI agents, the autonomy spectrum, key properties, and how agents differ from chatbots, workflows, and pipelines.
Tools and Function Calling
How agents interact with external systems through tool use, function calling APIs, MCP, tool schemas, selection strategies, and error handling.
Model Context Protocol (MCP)
MCP's host-client-server architecture, stateless request flow, protocol eras, primitives, extensions, and security boundaries.
Planning and Reasoning
How AI agents decompose tasks, form plans, reason with chain-of-thought and tree-of-thought, and recover when planning fails.
Memory Systems
Why agents need memory, types of memory (short-term, long-term, episodic, semantic, working), memory architectures, and practical implementation with code.
Context Engineering
Curating exactly what occupies a model's finite context window at each step of an agent's run to maximize signal-to-noise.
Agent Architectures
Single-agent and multi-agent architectures including supervisor, peer-to-peer, hierarchical, and swarm patterns, with guidance on choosing the right one.
Agent Interoperability Protocols (A2A)
How autonomous agents from different teams, frameworks, and vendors discover and delegate work to one another using the A2A protocol, and how it complements MCP.
Guardrails and Safety
Output validation, input filtering, content safety, sandboxing, rate limiting, human oversight, prompt injection defense, and PII handling for agentic AI systems.