Atividade_2

Use when implementing or reviewing AV3 candidate-RAG work, including retrieval, Com_RAG candidate answers, context snapshots, candidate prompt rendering, candidate execution, or Sem_RAG vs Com_RAG comparison. Do not use for AV2-only judge pipeline work unless adapting judges to AV3 candidate answers.

Use when implementing or reviewing the AV2 LLM-as-a-Judge execution pipeline. Do not use for generic Python setup, standalone SQL analysis, or rubric design without execution changes.

Use when creating, documenting, or validating PostgreSQL backup and restore artifacts for AV2. Do not use for judge execution, rubric design, or Python project setup.

Use when importing datasets, AV1 answers, prompts, rubrics, or judge outputs into PostgreSQL and validating referential integrity. Do not use for judge prompt design or pure Python project setup.

Use when diagnosing bugs, failing tests, failed pipelines, bad data, or unexpected runtime behavior. Do not use for routine code review or simple formatting tasks.

Use when designing or reviewing LLM-as-a-Judge rubrics and scoring prompts for AV2. Do not use for database imports, backup/restore, or generic Python setup.

Use when creating, reviewing, or standardizing Python project infrastructure. Do not use for domain-specific implementation, business logic, or application feature design.

Use when creating, splitting, reviewing, or refactoring AGENTS.md, PRIMING.md, PLANS.md, or .agents/skills content. Do not use for application feature work.

Use when reviewing code, diffs, or PR changes for correctness, maintainability, tests, performance, and risk. Do not use for initial implementation unless explicitly asked for review.

Use when creating SQL reports, model rankings, disagreement analysis, or Spearman correlation for AV2. Do not use for judge execution or Python project bootstrap.

Use when designing, reviewing, or improving tests, fixtures, mocks, or validation strategy. Do not use for broad implementation unless the main task is testing.