AI Agents and Tool Use

86 lessons in AI Fundamentals

• Avoiding Outdated Agent AssumptionsSlides / Video
• Remote MCP Tools in Production APIsSlides / Video
• OpenAI Responses API and Agents SDKSlides / Video
• A2A vs MCP: Two Different LayersSlides / Video
• A2A: Agents Talking to AgentsSlides / Video
• MCP Governance Under AAIFSlides / Video
• MCP Authorization and CIMDSlides / Video
• MCP Feature Lifecycle and ExtensionsSlides / Video
• MCP's Stateless Core DesignSlides / Video
• MCP: Standardizing Model-to-Tool AccessSlides / Video
• Appending Observations to HistoryCode Quiz
• Evaluating and Debugging Agent BehaviorSlides / Video
• Real-World Agent Use CasesSlides / Video
• Cost, Latency, Reliability Trade-offsSlides / Video
• Agent Safety and Permission ScopingSlides / Video
• Human-in-the-Loop and Approval GatesSlides / Video
• Agent Loop Termination ConditionsSlides / Video
• Handling Tool Errors and RetriesSlides / Video
• Multi-Agent Systems and CollaborationSlides / Video
• Common Agent Tool TypesSlides / Video
• Agent Memory: Short-Term vs Long-TermSlides / Video
• Planning and Task Decomposition by AgentsSlides / Video
• Chain-of-Thought Reasoning in AgentsSlides / Video
• ReAct: Reasoning Meets ActingSlides / Video
• Parsing and Executing Tool CallsSlides / Video
• How LLMs Choose a ToolSlides / Video
• Tool Schemas and DescriptionsSlides / Video
• Tools and Function Calling FundamentalsSlides / Video
• The Agent Loop ExplainedSlides / Video
• Agents vs Plain LLM PromptingSlides / Video
• AI Agents: The Sense-Think-Act LoopSlides / Video
• Error Handling and RecoveryQuiz
• Multi-Step Reasoning and Iterative LoopsQuiz
• Short-Term vs Long-Term MemoryQuiz
• Planning and Task DecompositionQuiz
• Parsing and Validating Tool OutputsQuiz
• Tool Schema and Argument DefinitionQuiz
• Autonomy Levels in AgentsQuiz
• Perception-Reasoning-Action LoopQuiz
• Agent vs Plain LLM CallQuiz
• Cost and Latency of Agentic LoopsQuiz
• Real-World Agent ApplicationsQuiz
• Human-in-the-Loop ApprovalQuiz
• Safety Risks of Autonomous AgentsQuiz
• Evaluating Agent PerformanceQuiz
• Retrieval as a ToolQuiz
• Prompt Injection Threats via ToolsQuiz
• Web Browsing and External API AccessQuiz
• Multi-Agent Systems and CollaborationQuiz
• Code Execution and SandboxingQuiz
• Stopping Conditions and Loop TerminationQuiz
• What Defines an AI AgentQuiz
• Tool Use Concept and MotivationQuiz
• Aggregating Tool ResultsCode Quiz
• Loop Detection GuardCode Quiz
• Dangerous Tool Argument GuardrailsCode Quiz
• Sequential Task DecompositionCode Quiz
• Passing Prior Step Output ForwardCode Quiz
• Coercing Tool Arguments to NumbersCode Quiz
• Parsing Action vs Final AnswerCode Quiz
• Routing to the Correct ToolCode Quiz
• Unknown Tool Name HandlingCode Quiz
• Catching Tool ErrorsCode Quiz
• Parsing Tool ArgumentsCode Quiz
• Validating Required ArgsCode Quiz
• Scratchpad State ScopeCode Quiz
• Detecting Final AnswerCode Quiz
• Agent Loop OrderCode Quiz
• Dispatch Tool By NameCode Quiz
• Step Limit GuardCode Quiz
• Real-World Applications of AI AgentsFlashcard
• Cost and Latency of Agentic WorkflowsFlashcard
• Evaluating Agent PerformanceFlashcard
• Code Execution / Code Interpreter AgentsFlashcard
• Parsing and Validating Tool OutputsFlashcard
• Multi-Agent Systems and CollaborationFlashcard
• Planning and Task DecompositionFlashcard
• Agent Memory: Short-term vs Long-termFlashcard
• Agent Orchestration FrameworksFlashcard
• Types of ToolsFlashcard
• Tool Selection and RoutingFlashcard
• Agent vs Standalone LLM CallFlashcard
• Agent Failure Modes and Error RecoveryFlashcard
• Stopping Criteria and Loop TerminationFlashcard
• Reflection and Self-CorrectionFlashcard
• Tool Schema and Function DefinitionsFlashcard