A research summarization assistant has been deployed for six months. A user has flagged that a generated summary contained a fabricated citation. The product team has asked whether the incident requires architectural action or whether it is an isolated case.
Which two Diligence-competency actions should you take? (Select two.)
Each correct answer presents part of the solution.

• A. Communicate to users that the assistant does not fabricate output as a matter of design.
• B. Sample recent summaries to estimate the fabrication frequency across the population.
• C. Review whether citation-grounding controls exist anywhere in the current generation pipeline.
• D. Treat the incident as an anecdotal isolated case and take no further investigative action.
• E. Disable the assistant immediately for all current users without any prior diagnostic analysis.

You are configuring Claude Code for a team that needs every engineer to share the same MCP server set, permission rules, and project context across the engineering monorepo.
Which configuration scope best supports this requirement?

• A. Project scope, with the configuration committed to the repository so every engineer working in the project receives the same MCP servers, permissions, and context.
• B. Local scope configured only on the lead architect's machine, with no configuration present on other engineers' machines and no mechanism to distribute MCP servers or permission rules.
• C. User scope configured individually on each engineer's machine, with no shared configuration committed to the repository and no guarantee of consistency across the team.
• D. User scope, with the MCP server definitions and permission rules placed in each engineer's ~/.claude
  /settings.json and synchronized manually through a shared setup script outside version control.

You are designing a human-in-the-loop validation workflow for a new Claude-based deployment and must complete the design steps before piloting the workflow.
Which two steps must be completed BEFORE piloting the workflow with a representative subset of traffic?
(Select two.)
Each correct answer presents part of the solution.

• A. Define the sampling strategy and the escalation criteria at each oversight point in the pipeline.
• B. Document the workflow with check criteria, escalation paths, and service-level agreements (SLAs) for each step.
• C. Onboard the reviewer pool with role-specific training on the check criteria and escalation procedures.
• D. Iterate the workflow design based on observed pilot findings before broader rollout to production.
• E. Identify the decision points in the pipeline that require human oversight by impact and reversibility.

A technical team is debating whether to implement a new capability for generating regulatory filings from internal data as a Claude Skill or as an MCP server. The capability requires a fixed authoring procedure with embedded examples, does not need to call live external systems, and must be portable across three Claude deployments: claude.ai, an internal API integration, and Claude Code.
Which factor most strongly favors implementing the capability as a Skill?

• A. The capability needs to query a live database for the most recent regulatory filings.
• B. The capability must also be callable from a developer's command-line interface.
• C. The capability requires direct authentication against the corporate identity provider.
• D. The capability is procedural knowledge with no live external-system calls required.

An engineer inadvertently commits an API key to the repository by placing it in .claude/settings.json.
Which configuration design principle was violated?

• A. MCP server definitions must reside in environment variables to prevent scope conflicts.
• B. Project-scope configuration should always override user-scope configuration.
• C. Credentials must be resolved at runtime from a secret store and never stored in version-controlled files.
• D. Managed configuration must be applied before project-scope configuration is read.