Agents and the Agent SDK

A developer is building a support agent with the Claude Agent SDK. The agent must pause execution, ask a human operator to approve a refund above $500, and resume the exact same session with the operator's decision injected as a new message. Which SDK capability should the developer configure to accomplish this reliably?

A developer is implementing a multi-agent system using the Anthropic SDK where a 'Coordinator' agent delegates tasks to specialized 'Researcher' and 'Writer' agents via tool calls. The Coordinator must maintain a coherent conversation state and avoid redundant work. Which TWO of the following practices are essential for the Coordinator to effectively manage this delegation? (Choose two.)

Refer to the exhibit. Which step should you take first to resolve this tool invocation error?

A developer is designing an agent with the Anthropic SDK that must follow strict brand guidelines when drafting customer emails. The agent should never deviate from these rules regardless of how the user phrases a request. Where should the brand guidelines be placed to have the strongest effect?

Refer to the exhibit. An agent receives this response after attempting to use a 'fetch_url' tool. How will this specific block affect the agent's next reasoning step?

When designing agentic loops with the Anthropic SDK, which TWO practices help prevent infinite tool-use cycles? (Select exactly 2)

A developer's agent calls a weather API tool but Claude keeps emitting the tool call with a misspelled parameter name that the API rejects. The tool definition and the API schema disagree. What is the most likely cause?

What is the primary role of the 'system' role in a message sequence for an agent?

An agent built with the Anthropic SDK is processing a long conversation and begins to exceed the model's context window. The developer wants to preserve recent turns and key facts while reducing token usage. Which approach best matches how the SDK and Claude are designed to handle this?

In the context of the Anthropic Agent SDK, what is the primary role of the 'Orchestrator' component?

When defining a tool for an agent using the Anthropic SDK, which field is required to ensure the model understands the specific schema of the input arguments?

A developer is building an agent that runs shell commands to inspect a repository. They want the agent to iterate autonomously but prevent destructive commands like deleting files outside the project directory. Which combination best enforces this boundary while preserving autonomy?

When deploying an agent that uses the Model Context Protocol (MCP), what is the primary security risk of allowing the agent to dynamically discover and connect to any local MCP server?

In an agentic flow, what is the impact of providing redundant tool descriptions that overlap in functionality?

A developer is building a Claude agent using the Anthropic Agent SDK. The agent must be able to fetch the current stock price for a given ticker symbol. The developer defines a tool named 'get_stock_price' with an input schema that requires a single string parameter 'ticker'. During testing, the agent responds with a final text answer containing a plausible-looking price, but the tool is never invoked. Which is the most likely cause?

A developer writes an agent loop that handles Claude's tool_use blocks by executing each tool and appending a user message containing the tool_result blocks. In production, a request occasionally triggers a 400 error stating that the tool_use ids were not found. Reviewing the code, the developer sees the loop builds each new request by sending only the latest user message and the newest tool_result message, discarding earlier turns to save tokens. Which action resolves the error while preserving the agent's behavior?

Why should you avoid including sensitive personal data (PII) in the tool results returned to an agent?

Which THREE strategies are effective for improving the reliability of an agent in production environments? (Select exactly 3)

An agent using the SDK encounters an error where it generates a tool call for a tool that does not exist in its configuration. Which adjustment to the agent's setup is most likely to resolve this hallucination?

An agent is performing a 'Computer Use' task that requires taking multiple screenshots and moving the cursor. The model generates a tool_use block for 'screenshot' and 'mouse_move' in a single turn. How should the SDK-based orchestrator handle this response to ensure reliable execution?

A developer is implementing a 'Human-in-the-loop' (HITL) pattern for an agent that performs financial transactions. Which TWO strategies are most important for maintaining the security and reliability of this agentic workflow?

A developer is creating an agent that uses the Anthropic SDK to answer customer support questions. The agent has access to a tool that retrieves order status from an internal API. During testing, the developer notices that the agent sometimes provides an order status without calling the tool, resulting in incorrect information. What is the most likely cause of this behavior?

A developer is creating a multi-agent system where a coordinator agent delegates subtasks to specialized agents. Each specialized agent has its own tools and system prompt. The coordinator needs to know when a subtask is complete and what result was produced. Which design best fits the Anthropic SDK's stateless model?

Refer to the exhibit. A developer is configuring an MCP server to provide an agent with database access. What is the primary purpose of the 'args' field in this configuration block?

You are debugging an agent that often fails to format its final response as JSON, despite being instructed in the system prompt. Which technique is most effective for ensuring consistent output structure?

When sharing state between multiple agent turns, why is it recommended to use a managed session object instead of appending everything to a simple list of messages?

An agent developer is building a workflow where an agent must query a private database. To ensure the agent only performs read operations, which component of the Anthropic Agent SDK pattern should be prioritized?

A developer is building a Claude agent with the Anthropic SDK that must look up live order status. The agent has one tool named get_order_status, and its input_schema declares a required string property order_id. During testing, Claude returns a tool_use block with name "get_order_status" and input {"order_id": "A-4471"}. What must the developer's application do next to keep the agent loop running correctly?

A developer is building an agent using the Anthropic Python SDK. The agent's system prompt instructs it to answer questions about a company's internal policies by searching a vector database. The developer wants the agent to autonomously decide when to search and when to answer directly. Which combination of API features should the developer implement to achieve this?

A developer is using the Anthropic SDK to build an agent that can answer questions by calling external APIs. The agent's tool returns a large JSON payload (over 100,000 tokens) as a `tool_result`. The developer notices that subsequent requests to the model fail with a context window error. What is the most effective way to resolve this issue?

When an agent is asked to perform a complex task, which approach minimizes latency while ensuring accuracy?

An agent is designed to manage a user's calendar. During a session, the user asks to 'Schedule a meeting for tomorrow at 2 PM.' The agent must first check for conflicts and then create the event. How should the developer handle the 'observation' phase in the SDK to ensure the agent doesn't double-book?

A developer is building an agent that must decide when to call tools versus when to respond directly to the user. The agent uses the Anthropic SDK with tool definitions supplied in the request. Which TWO behaviors correctly describe how the model handles tool use in this setup? (Choose two.)

A developer is building a customer support agent using the Anthropic SDK. The agent must call a 'get_order_status' tool that requires an order ID. During testing, the agent sometimes invents plausible-looking order IDs instead of asking the user. Which change to the tool definition will most directly reduce this behavior?

Which THREE of the following are essential components of a well-defined tool for an agent? (Select exactly 3)

An agent built with the Claude Agent SDK runs a long research task and repeatedly hits the model's context window limit. The developer wants the agent to keep working without losing critical earlier findings. Which approach best addresses this?

You are designing a multi-agent system where a 'Router' agent directs tasks to a 'Research' agent or a 'Writer' agent. What is the most efficient way to maintain state when the Research agent completes its task and needs to hand back control?

When implementing a 'Computer Use' agent, which THREE capabilities are provided by the standardized Anthropic beta tools 'computer', 'text_editor', and 'bash'?

A developer is designing a subagent architecture with the Claude Agent SDK. The main agent delegates a codebase audit to a specialized subagent to keep the primary conversation focused. Which TWO practices help ensure the delegation works correctly? (Choose two.)

Which of the following is a best practice when providing feedback to an agent after a failed tool call?

Which TWO of the following are essential components of a 'tool_use' block generated by Claude?

Which component is responsible for orchestrating the loop between the model's output and the execution of tools in the Anthropic SDK?