You have configured the system so that all four subagents have access to the complete set of 18 tools. During testing, agents frequently call tools outside their specialization—the synthesis agent attempts web searches, and the report generator tries to analyze documents. What is the primary cause of this poor tool-selection behavior?

Your pipeline runs:

PROMPT= " You are a code reviewer. "

PROMPT= " $PROMPT Analyze the provided diff "

PROMPT= " $PROMPT for bugs, security issues, "

PROMPT= " $PROMPT and style violations. "

claude -p \

--dangerously-skip-permissions \

--system-prompt " $PROMPT " < diff.txt

The reviews complete and return feedback, but Claude comments only on the piped diff—it never reads surrounding files in the checked-out repository to understand broader context, even when the diff modifies a function called by many other modules. Which change to the invocation will cause Claude to read related repository files while still applying your custom review instructions?

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.

The document-analysis agent has a single analyze_document tool that takes a document and a free-text instruction parameter. During evaluation, requests such as “extract the key financial metrics” often return narrative summaries, while “summarize the methodology” sometimes returns raw data tables. The synthesis agent reports that 35% of analysis results require new requests with clarified instructions.

What is the most effective way to improve reliability?

In production, you observe that simple fact-checking queries—for example, “What year was the Paris Climate Agreement signed?”—traverse all four subagents sequentially, consuming more than 40 seconds and significant tokens per query. Complex comparative research benefits from the full pipeline. Your query distribution is diverse and evolving as users discover new applications. What is the most effective approach to optimize for varying query complexity?

You built an LLM-powered code-review tool that analyzes pull requests and returns structured findings. Each finding is a JSON object containing file_path, line_number, issue_category—such as security or style—and description. Developers can dismiss findings they consider unhelpful, and currently 35% of findings are dismissed. You want to analyze these dismissals to understand what the system is getting wrong and improve the prompts accordingly. What change to the output structure would best support this analysis?

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

The automated review consistently flags patterns your team uses intentionally—force-unwrapping optionals in test files, using large coordinator classes that follow your established architecture, and importing internally maintained modules marked as deprecated in the public SDK. Developers dismiss approximately 30% of all findings as project-specific false positives.

Which approach prevents the model from generating these findings in the first place by supplying the project’s conventions as persistent context during every review?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your extraction uses tool use with a JSON schema in which property_type is defined as an enum: house, apartment, condo, or townhouse. After deployment, 8% of extractions fail schema validation. Investigation reveals that listings mention many uncommon property types—“studio,” “loft,” “duplex,” “mobile home,” “tiny house,” and “converted warehouse”—and new types continue appearing regularly.

What is the most effective long-term solution?

After deploying the automated review, you notice high precision but low recall—real bugs are slipping through undetected. Investigation reveals that your review prompt instructs Claude to “only report high-confidence issues you are certain about” and “err on the side of not commenting.” Developers appreciate the low noise, but a race condition that caused a production outage was visible in a reviewed pull request and went unreported. You need to substantially improve bug detection while keeping false-positive rates manageable. What is the most effective approach?

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.

In production, you observe that simple fact-checking queries, such as “In what year was the Paris Climate Agreement signed?”, traverse all four subagents sequentially, consuming more than 40 seconds and significant tokens per query. Complex comparative research benefits from the complete pipeline. Your query distribution is diverse and continues to evolve as users discover new applications.

What is the most effective approach to optimize for varying query complexity?

Production monitoring shows that the research phase takes longer than expected. Analysis reveals that the coordinator invokes the web-search subagent, waits for its response, and then invokes the document-analysis subagent. These tasks are independent; neither requires the other’s output. How should you modify the system to run these subagents concurrently?

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

Your automated reviewer uses a single prompt covering security issues, API design, and business-logic correctness. Your evaluation suite shows strong recall for API-design findings at 82% but poor recall for business-logic edge cases in quiz scoring at 34%. When you add few-shot examples of logic bugs to the prompt, logic recall improves to 41%, but API-design recall drops to 68%.

How should you address this trade-off to improve detection across both categories?

The coordinator agent has AgentDefinition objects configured for all four specialized subagents, each with appropriate descriptions, prompts, and tool restrictions. During testing, you notice that the coordinator correctly reasons about when to delegate—it generates messages such as, “I’ll ask the web-search agent to find sources on this topic”—but no subagent execution occurs. The coordinator then proceeds as if the delegation happened and continues with incomplete information. Logs show no errors. What is the most likely cause?

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 expands the research system beyond its original web-search agent by adding specialized data sources. A financial API agent returns structured JSON containing revenue, margins, and growth rates. A news-monitoring agent returns prose summaries of recent developments. A patent-analysis agent returns structured lists of technology areas. The synthesis agent combines these results into executive briefings. Currently, it converts everything into bullet points, causing financial comparisons to lose tabular clarity and news summaries to lose their narrative flow.

What change would most improve briefing quality?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your extraction system implements automatic retries when validation fails. On each retry, the specific validation error is appended to the prompt. This retry-with-error-feedback approach resolves most failures within 2–3 attempts.

For which failure pattern would additional retries be LEAST effective?

Your pipeline includes a release-notes generation step that classifies and summarizes approximately 200 commits at the end of each weekly release cycle. Each commit is currently sent as a separate Messages API call using a Sonnet-tier Claude model. The release notes are not needed until the following morning, so results have approximately 12 hours of acceptable latency. Your team needs to reduce per-token API cost for this step while keeping the same model and prompts, with no change to the model tier or output quality. Which approach satisfies all these constraints?

Your pipeline reviews approximately 200 database-migration scripts daily using the Message Batches API. Each request includes a shared 8,000-token system prompt containing migration-review guidelines and schema documentation, followed by an individual migration script. You added cache_control breakpoints to the shared system prompt in every request, but monitoring shows cache-hit rates of only 32%, with misses concentrated among requests processed later in the batch window. Which change addresses the root cause without adding sequential-processing latency?

You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution.

A security audit requires updating your authentication library from v2 to v3. The migration guide documents breaking changes: authenticate() now returns a Promise instead of accepting a callback, the User type has restructured fields, and three deprecated methods were removed. Grep shows the library is imported in 45 files across several modules.

What’s the most effective approach?

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 used the agent yesterday to analyze a legacy authentication module, identifying two distinct refactoring approaches: extracting a microservice versus refactoring in-place. Today, they want to explore both approaches in depth—having the agent propose specific code changes for each—before deciding which to implement.

What’s the most effective way to structure this exploration?

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

Your test generation produces unit tests for new code, but reviews show that 55% are low-value: trivial assertions that only verify functions do not throw exceptions, tests duplicating existing coverage, or tests ignoring your team’s fixture conventions.

How do you reduce the rate of low-value tests being generated in the first place?

A customer sends: “This is frustrating. I’ve explained my issue twice and nothing is being resolved. I want to talk to a real person NOW.” The agent has not yet called any tools to investigate the customer’s account. What should the agent do?

Your test-generation process produces unit tests for new code, but reviews show that 55% are low-value: trivial assertions that verify only that functions do not throw exceptions, tests that duplicate existing coverage, or tests that ignore your team’s fixture conventions. How should you reduce the rate of low-value tests being generated in the first place?

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.

Your process_refund tool returns two types of errors: technical errors (“503 Service Unavailable”, “Connection timeout”) that are transient (~5% of calls), and business errors (“Order exceeds 30-day return window”, “Item already refunded”) that are permanent (~12% of calls). Monitoring shows the agent wastes 3–4 turns retrying business errors that can never succeed. Currently, both error types return only a plain text message to Claude.

What’s the most effective way to reduce wasted retries while improving customer-facing response quality?

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 submits two requests:

Request A: “Rename the getUserData function to fetchUserProfile everywhere it’s used.”

Request B: “Improve error handling throughout the data processing module—add try/catch blocks, meaningful error messages, and ensure failures don’t silently corrupt data.”

For which request does specifying an explicit multi-phase workflow (such as analyze → propose → implement with review) most improve outcome quality?

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

Your automated review calls the Claude API for each pull request, using tool_use with a report_findings tool that returns a JSON array of finding objects. Each object contains file_path, line_number, severity, category, and description. During testing on a large pull request touching more than 30 files, the response reaches the max_tokens limit and is truncated in the middle of the JSON, causing your pipeline’s parser to fail.

What is the most effective way to handle this?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your system has been running for 3 weeks and human reviewers have corrected 847 extractions. Analysis reveals a recurring pattern: when recipes use informal measurements like “a handful” or “a splash,” the model either invents specific amounts or leaves fields empty—accounting for 23% of all corrections.

How should you use this feedback to improve extraction accuracy?

The web-search agent has gathered several relevant sources for a research topic. The document-analysis agent now needs to examine those sources. How does information typically flow between these two specialized subagents?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your extraction system uses tool use with a JSON schema containing 12 fields and detailed descriptions, totaling approximately 2,500 tokens for the complete tool definition. Processing documents under 150,000 tokens yields 98% accuracy. For documents between 175,000 and 190,000 tokens, accuracy drops to 71%, with information from the final third consistently missed. The model’s context window is 200,000 tokens.

What is the most likely cause?

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.

Your code review assistant needs to analyze pull requests and provide feedback on three aspects: code style compliance, potential security issues, and documentation completeness. Each aspect requires reading files, running analysis tools, and generating a report section. The review process follows the same three-step workflow for every PR.

Which task decomposition pattern is most appropriate for this workflow?

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.

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?

The automated review consistently flags patterns your team uses intentionally—force-unwrapping optionals in test files, using large coordinator classes that follow your established architecture, and importing internally maintained modules marked as deprecated in the public SDK. Developers are dismissing approximately 30% of all findings as project-specific false positives. Which approach prevents the model from generating these findings in the first place by supplying the project’s conventions as persistent context during every review?

You are using Claude Code to accelerate software development. Your team uses it for code generation, refactoring, debugging, and documentation. You need to integrate it into your development workflow with custom slash commands, CLAUDE.md configurations, and understand when to use plan mode vs direct execution.

Your team has connected a custom MCP server that provides DevOps workflow templates. The server exposes several MCP prompts (such as deploy_checklist and incident_response ) in addition to tools.

How do these MCP prompts become accessible within Claude Code?

Your code-review prompts include both implementation changes and the corresponding test file, but the review comments fail to identify untested code paths. The model correctly flags functions that have no tests at all, but it fails to recognize when conditional branches or error-handling paths within tested functions lack coverage. What is the most effective way to improve branch-level gap detection without overcomplicating the pipeline?

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives.

Your automated code review is missing genuine bugs in pull requests. Investigation reveals that your review prompt includes the instruction: “Only flag critical issues that would definitely cause production failures. Ignore minor concerns and anything you are uncertain about.” Developers confirm that some missed bugs are genuine logic errors that the model investigated but chose not to report. The team requires the review output to remain structured, with each finding tagged with metadata, and actionable.

Which prompt change both removes the cause of the suppressed findings and preserves structured, tagged output for downstream filtering?

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.

The synthesis agent receives summarized findings from the web-search and document-analysis agents, then passes a consolidated summary to the report generator. During testing, you discover that the generated reports make factual claims without proper citations. The report generator cannot attribute statements to their original sources because that metadata was lost during the summarization steps.

What is the most effective approach to ensure proper source attribution in the final reports?

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, and Glob—and integrates with Model Context Protocol (MCP) servers.

You are building a security-scanning workflow.

When engineers need to locate every occurrence of a dangerous function such as eval() across a large codebase, which tool should the agent use for content searching?

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.

The synthesis agent completes its initial pass but flags that three key research questions remain unanswered because the web-search and document-analysis agents did not find relevant information on those specific subtopics. The coordinator currently proceeds directly to report generation, producing reports with incomplete coverage.

What change would most effectively improve research completeness?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your system extracts event metadata (date, location, organizer, attendee_count) from news articles using a JSON schema with all nullable fields. During evaluation, you observe the model frequently generates plausible but incorrect values for fields not mentioned in the article—for example, outputting “500” for attendee_count when the source contains no attendance information.

What’s the most effective way to reduce these false extractions?

During testing, when a customer says, “I need a refund for my recent purchase,” the agent immediately invokes process_refund but populates the required order_id parameter with a plausible-looking fabricated value instead of first calling lookup_order. The refund fails because the invented order identifier does not exist. Which change directly addresses the root cause of the fabricated order_id?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

The system needs to extract candidate information (name, contact details, skills, work experience, education) from uploaded resumes. The extracted data must strictly conform to a predefined JSON schema, as missing required fields or incorrect data types will cause downstream validation failures.

What is the most reliable approach to ensure Claude’s output consistently matches the schema?

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.

Production reviews reveal inconsistent handling of uncertainty in final reports. Sometimes conflicting subagent findings are synthesized into a single confident statement, losing important nuance, while other reports use excessive qualifications and become unhelpful. The web-search agent returns, “Industry analysts estimate a $50 billion market size, although methodologies vary.” The document-analysis agent returns, “A peer-reviewed study estimates $35 billion, with a ±$7 billion 95% confidence interval.” The coordinator either selects one estimate arbitrarily or produces a vague $35–$50 billion range.

What systematic approach best addresses this?

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, and Glob—and integrates with Model Context Protocol (MCP) servers.

After adding an MCP server with specialized code-refactoring tools—extract_function, rename_variable, and inline_function—you notice that the agent still uses basic text manipulation through Write and Bash sed commands for refactoring tasks. The MCP server is connected and healthy. Examining the configuration, you find that each MCP tool has a minimal description such as, “extract_function: Extracts a function from code.”

What is the most effective way to improve adoption of the MCP refactoring tools?

After deploying automated code review, developers report that approximately 35% of flagged findings are false positives falling into consistent patterns: style suggestions contradicting team conventions, security warnings for patterns that are safe in your deployment context, and performance suggestions that would degrade your specific use case. You want to reduce false positives while maintaining the ability to catch genuine issues. Which approach best enables the model to generalize its judgment to novel code patterns it has not seen before?

Your automated code review is missing genuine bugs in pull requests. Investigation reveals that the review prompt includes this instruction: “Only flag critical issues that would definitely cause production failures. Ignore minor concerns and anything you are uncertain about.” Developers confirm that some missed findings are genuine logic errors that the model investigated but chose not to report. The team requires the review output to remain structured, with every finding tagged with metadata, and actionable. Which prompt change both removes the cause of the suppressed findings and preserves structured, tagged output for downstream filtering?

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 used Claude Code yesterday to investigate authentication flows in a legacy monolith, building up significant context over a 2-hour session. Today she wants to continue that specific investigation. She’s worked on three other codebases since then and knows the session was named “auth-deep-dive”.

How should she resume?

You are building a structured data extraction system using Claude. The system extracts information from unstructured documents, validates the output using JSON schemas, and maintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.

Your extraction pipeline occasionally receives responses that cannot be parsed as valid JSON, causing downstream processing failures. The current implementation prompts Claude to return JSON in the response text and then parses it.

What is the most reliable approach to ensure Claude returns valid, schema-compliant structured data?