Agent Frameworks - Q&A Review Bank
31 questions across the module, from choosing a framework to the specifics of each. Try each one before revealing the answer.
Learning objectives 45 min
By the end of this page you will be able to:- Recall the core abstraction, state model and human-in-the-loop mechanism of each major framework
- Justify a framework choice for a scenario, including choosing none
- Explain framework behaviour from the underlying agent loop
Prerequisites
- Chapters 1-8 of this module
Choosing a Framework
Check yourself
0 / 6 answered
- What does an agent framework add to a raw model API loop? Name five things.
- What does a framework hide that you need when debugging?
- Place these on the layer map: LangGraph, OpenAI Agents SDK, anthropic SDK, Bedrock AgentCore.
- When is no framework the right choice?
- The same model and tools ran in six frameworks in this module's lab. Where did results differ, and why?
- How do you keep the cost of switching frameworks low?
LangChain and LangGraph
Check yourself
0 / 5 answered
- What replaced AgentExecutor in LangChain 1.x?
- Name four built-in LangChain middleware and what each does.
- What two things does interrupt() need to work?
- Why must side effects come after interrupt() in a node, or be idempotent?
- What is the LangGraph Store for?
OpenAI Agents SDK
Check yourself
0 / 4 answered
- Handoff vs agent.as_tool - what's the difference?
- How is a run requiring approval resumed after a restart?
- What do input guardrails cost and how is latency hidden?
- What do you lose running the Agents SDK on a non-OpenAI model through Chat Completions?
Claude Agent SDK
Check yourself
0 / 4 answered
- How does the Claude Agent SDK differ from the Messages API Tool Runner?
- How are custom tools added, and what name does the model see?
- In what order are permissions decided?
- Which hook would you use to make the agent run tests before finishing?
Google ADK
Check yourself
0 / 4 answered
- What are ADK's three ways to involve another agent?
- What replaced SequentialAgent, ParallelAgent and LoopAgent in ADK 2?
- What happens when before_tool_callback returns a dict?
- What do the state prefixes user:, app: and temp: mean?
CrewAI
Check yourself
0 / 3 answered
- What does a hierarchical crew add over a sequential one?
- In a Flow, what do @start, @listen and @router do?
- Why is a Flow the recommended backbone for production CrewAI apps?
Microsoft Agent Framework and PydanticAI
Check yourself
0 / 5 answered
- What does Microsoft Agent Framework combine?
- Name MAF's five built-in orchestrations.
- How does PydanticAI pass a database connection to tools?
- How does PydanticAI pause for approval?
- How does PydanticAI make runs durable?
Last reviewed: 2026-09