Techy Chalkboard in Bits and Pieces
There’s always someone who knows better than Google!
Claude Exam (CCAR-F) Quick Revision 12: Human Review & Provenance
Aggregate Accuracy Trap Overall accuracy = 97% This may still hide poor accuracy for a particular document type or field. Measure Accuracy By Document type. Individual field. Relevant segment. Stratified Random Sampling Do not review only low-confidence results. Sample some high-confidence outputs too. Why? Detect confidently wrong predictions and new failure patterns. Confidence Calibration Field…
Claude Exam (CCAR-F) Quick Revision 11: Advanced Batch & Extraction
Schema Error vs Semantic Error Schema error: Invalid structure/type. Semantic error: Valid structure but wrong meaning/value. Remember: JSON Schema does not guarantee semantic correctness. Self-Validation Fields { “stated_total”: 120, “calculated_total”: 110, “conflict_detected”: true } Expose inconsistencies explicitly. detected_pattern Add fields such as: detected_pattern Use them to analyse which code patterns repeatedly cause false positives. Batch…
Claude Exam (CCAR-F) Quick Revision 10: Iterative Refinement Patterns
Concrete Examples If prose instructions produce inconsistent results: Give 2–3 concrete input/output examples. Interview Pattern Ask Claude to question you before implementation when important requirements may be missing. Useful for discovering: Failure modes. Edge cases. Cache invalidation. Security requirements. Performance constraints. Memory: Unknown design space → interview first. Interacting Problems If fixes affect each other:…
Claude Exam (CCAR-F) Quick Revision 9: Advanced Claude Configuration
@import Use @import to keep CLAUDE.md modular. @import ./standards/testing.md @import ./standards/api.md Use: Reference focused standards instead of creating one huge CLAUDE.md. /memory Shows which memory/instruction files are loaded. Useful for diagnosing inconsistent behaviour. Skill: context: fork context: fork Runs skill in isolated subagent context. Useful for verbose analysis. Useful for brainstorming alternatives. Prevents main-context pollution.…
Claude Exam (CCAR-F) Quick Revision 8: Advanced MCP Design
Split Overly Generic Tools Instead of: analyze_document Prefer: extract_data_points summarize_content verify_claim_against_source Reason: Clear tool boundaries improve selection reliability. Avoid Overlapping Tool Names Bad: analyze_content analyze_document Better: extract_web_results analyze_pdf_document System Prompt Can Bias Tool Selection Tool descriptions may be correct. System-prompt keywords can still create unwanted tool associations. If tool routing remains wrong, inspect both descriptions…
Something went wrong. Please refresh the page and/or try again.
Follow My Blog
Get new content delivered directly to your inbox.
You must be logged in to post a comment.