You are integrating AI-assisted tooling into the team's documentation workflow. The team wants generated documentation that stays grounded in the actual code.
Which integration approach best fits this requirement?

• A. Disable all filesystem and code-search tools so the subagents cannot read any repository code, accepting that documentation generation will be entirely disconnected from the actual implementation.
• B. Generate documentation from the model's training-data recall without reading any of the actual repository code, accepting that the output will not reflect the current implementation.
• C. Have the subagents publish generated documentation directly to the public-facing site without passing through the team's normal review workflow or any human approval step.
• D. Configure subagents that read the relevant code files via filesystem and code-search tools, generate the documentation, and emit changes through the team's normal review workflow.

A pilot AI assistant for procurement specialists shows 89 percent first-response acceptance, but follow-up surveys reveal that specialists frequently override the assistant's vendor recommendations after considering criteria the assistant did not evaluate. The pilot owner wants to ship the assistant unchanged because of the strong acceptance rate.
Which two Discernment-competency observations should you raise BEFORE approving the launch? (Select two.)

• A. The pilot duration was probably too short to demonstrate reliability across the full year.
• B. Acceptance does not establish whether recommendations remain correct after specialist review.
• C. The survey response rate may not be statistically representative of all specialists.
• D. The acceptance rate alone proves readiness for general production use.
• E. The unconsidered criteria represent a scope gap in the assistant's input space.

You are identifying the highest-impact optimization for a deployment whose token cost is dominated by a long, repeated system prompt and a large retrieved context per request.
Which optimization most directly targets the dominant cost driver?

• A. Move the long, repeated system prompt into a cacheable prefix and trim retrieved context to the spans relevant to each query.
• B. Switch every request to the heaviest available model to maximize output quality, accepting that higher per-request inference cost compounds rather than addresses the dominant cost driver.
• C. Add additional repeated content to the system prompt to give the model more guidance.
• D. Increase retrieval depth on every request to maximize recall, worsening the dominant cost driver by adding more retrieved tokens per request rather than reducing them.

You are selecting a pattern for a compliance Q & A assistant that must answer policy questions with citations to the authoritative internal source set. Latency, cost, and audit predictability are prioritized.
Which pattern is the best fit?

• A. Augmented LLM with retrieval-augmented generation over the indexed authoritative corpus and citation rendering on each answer.
• B. A pure agent loop with open web-browsing tools to surface the most current policy information, without constraining retrieval to the authoritative internal corpus.
• C. Multi-agent orchestration with a planner, researcher, and writer agent for every query.
• D. A static prompt with the entire policy corpus concatenated into every request.

A Claude architect needs to ensure that a security-hardening flag cannot be disabled by any individual engineer after it is set.
Which configuration scope correctly enforces this requirement?

• A. Project scope (.claude/settings.json) committed to the repository
• B. Environment variable defined in the CI/CD pipeline only
• C. User scope (~/.claude/settings.json) on each engineer's machine
• D. Managed configuration applied centrally and marked as non-overridable