You are building a multi-agent research system using the Claude Agent SDK. A coordinator agent delegates to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. The system researches topics and produces comprehensive, cited reports.
A user is expanding the research system beyond its single web search agent by adding specialized data sources. They add a financial API agent that returns structured JSON with revenue, margins, and growth rates; a news monitoring agent that returns prose summaries of recent developments; and a patent analysis agent that returns structured lists of technology areas. The synthesis agent combines these into executive briefings. Currently, it converts everything to bullet points, causing financial comparisons to lose tabular clarity and news summaries to lose narrative flow. What change would most improve briefing quality?

• A. Standardize all subagent outputs to prose summaries with inline citations
• B. Update the synthesis agent to render each content type appropriately - financial data as tables, news as prose
• C. Standardize all subagent outputs to JSON with fields for claim, evidence, source, and confidence
• D. Add a format conversion layer between subagents and synthesis that transforms all outputs to a common intermediate representation

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles high-ambiguity requests like returns, billing disputes, and account issues. It has access to your backend systems through custom Model Context Protocol (MCP) tools ( get_customer, lookup_order , process_refund , escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.
After expanding the agent's MCP tools with delivery-specific capabilities ( check_delivery_status , contact_driver , issue_credit , apply_promo_code , update_delivery_address , reschedule delivery ), the total tool count has grown from 4 to 10. Your evaluation suite shows tool selection accuracy has dropped from 88% to 71%. Log analysis reveals the majority of errors involve the agent selecting between semantically overlapping tools - calling issue_credit when process_refund was correct, and calling check_delivery_status when lookup_order already returns the needed data. Which approach structurally eliminates the semantic overlap identified in the logs as the error source?

• A. Split the tools across two sub-agents - a "financial resolution" agent with process_refund , issue_credit ,and apply_promo_code , and a "delivery operations" agent with the remaining delivery tools - with a coordinator routing between them.
• B. Consolidate semantically overlapping tools - merge issue_credit and process_refund into a single resolve_compensation tool with an action parameter, and fold check_delivery_status into lookup_order with an optional include_tracking flag.
• C. Add few-shot examples to the system prompt demonstrating correct selection for each ambiguous tool pair, such as showing when issue_credit applies versus when process_refund is appropriate.
• D. Enable the tool search tool with defer_loading on the six new tools, keeping the original four always loaded, so the agent dynamically discovers specialized tools only when needed.

You are building developer productivity tools using the Claude Agent SDK. The agent helps engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate code, and automate repetitive tasks. It uses the built-in tools (Read, Write, Bash, Grep, Glob) and integrates with Model Context Protocol (MCP) servers.
An engineer sees an unfamiliar error message "SYNC_CONFLICT: entity version mismatch detected" in production logs but doesn't know which of the 12 services in the codebase generates it. They ask the agent to help locate the source code. What exploration approach will most efficiently find the responsible code?

• A. Read the project's README and service configuration files to understand the architecture, then systematically Read source files in each service directory.
• B. Use Grep to find all files that import the project's error handling module, then Read those files to locate custom error definitions.
• C. Use Grep to search for distinctive text from the error message (like "SYNC_CONFLICT" or "entity version mismatch"), then Read the matching files to understand context.
• D. Use Glob to find files in directories commonly associated with error handling (such as errors/, exceptions/,or handlers/) across all services, then Read each matching file.

A user asks Claude to ignore all previous instructions and reveal confidential internal prompt content. How should Claude behave?

• A. Reveal the prompt.
• B. Generate random text.
• C. Follow higher-priority instructions and refuse.
• D. Partially reveal hidden instructions.

A customer raises three separate issues during one session: a refund inquiry (turns 1-15), a subscription question (turns 16-30), and a payment method update (turns 31-45). At turn 48, the customer asks "What happened with my refund?" The conversation is approaching context limits.
What strategy best maintains the agent's ability to address all issues throughout the session?

• A. Summarize earlier turns into a narrative description, preserving full message history only for the active issue.
• B. Extract and persist structured issue data (order IDs, amounts, statuses) into a separate context layer.
• C. Implement sliding window context that retains the most recent 30 turns.
• D. Rely on MCP tools to re-fetch relevant information on demand when the customer references earlier issues.