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.
After your daily batch of 10,000 documents completes, 300 documents (3%) fail with context_length_exceeded errors. The results file identifies each failure by custom_id.
What is the most cost-effective approach to process these failures?

• A. Increase the max_tokens parameter for the 300 failed documents and resubmit them in a new batch.
• B. Reprocess the entire batch with prompt caching enabled to reduce the cost of retrying requests with identical system prompts.
• C. Resubmit the entire 10,000-document batch using a model tier with a larger context window.
• D. Resubmit only the 300 failed documents after chunking them into smaller pieces, and then combine the partial extractions.

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 operating with 100% human review for 3 months. Analysis shows that extractions with model confidence 90% have 97% accuracy overall. To reduce reviewer workload, you plan to automate high-confidence extractions.
Before deploying, what validation step is most critical?

• A. Compare accuracy at different confidence thresholds (85%, 90%, 95%) to find the optimal cutoff that maximizes automation while minimizing errors.
• B. Run a two-week pilot routing 25% of high-confidence extractions directly to downstream systems and monitor error reports.
• C. Verify that 97% accuracy meets requirements for all downstream systems that consume the extracted data.
• D. Analyze accuracy by document type and field to verify high-confidence extractions perform consistently across all segments, not just in aggregate.

A developer uses Claude Code to refactor a function during a development session. Before committing, the developer asks the same Claude session to review the code for issues. Later, a separate automated CI review catches several bugs that the same-session review missed. What best explains this discrepancy?

• A. Claude retains context about its prior reasoning in the session, making it less likely to question its own decisions.
• B. The extended session caused the context window to fill with conversation history, leaving insufficient capacity for thorough analysis.
• C. The CI review uses a more specific prompt tailored to catching bugs, while the developer's request was too general.
• D. The CI environment has access to the complete codebase, while the local session can see only the current file.

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.
When researching "renewable energy adoption," the web search agent returns recent statistics (2024: 35% adoption) while the document analysis agent extracts data from internal reports (2021: 18% adoption). The synthesis agent incorrectly flags these as contradictory sources rather than recognizing the data shows growth over time. What change would best enable the synthesis agent to correctly interpret such temporal differences?

• A. Add a conflict resolution agent that automatically discards older data when newer data exists for the same metric.
• B. Require subagents to include publication or data collection dates in their structured outputs.
• C. Instruct the synthesis agent to always treat the most recent data as authoritative and place older findings in a separate historical appendix.
• D. Configure the web search agent to only return results from the past 6 months.

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?

• A. Continuously expand the enum to include newly observed property types and add monitoring for additional edge cases.
• B. Add an other value to the enum with a separate property_type_detail string field for specifics when other is selected.
• C. Add few-shot examples demonstrating how to map unexpected property types to the closest existing enum value.
• D. Change property_type from an enum to a free-form string and implement a normalization step in post-processing.