You are running a risk assessment on a planned Claude-based deployment and must complete the inventory steps before assessing threats against assets.
Which two steps must be completed BEFORE assessing threats against assets to estimate likelihood and impact? (Select two.) Each correct answer presents part of the solution.

• A. Identify the assets that the deployment touches, along with the sensitivity of each asset.
• B. Recommend mitigations and residual-risk acceptance for risks that remain.
• C. Document the assessment outcome with risks, mitigations, residual risk, and acceptance owners.
• D. Recommend mitigations and residual-risk acceptance for the risks that remain after analysis.
• E. Enumerate the threat actors and attack vectors relevant to the deployment.

During an architectural review, the security team identifies a risk that adversarial content injected into retrieved documents could manipulate the model's behavior.
Which mitigation most directly addresses this threat?

• A. Score outputs against a stable adversarial evaluation set on each model-version change.
• B. Require citations for each claim and constrain responses to source-supported content.
• C. Restrict outbound tool calls to an approved destination allow-list.
• D. Treat all retrieved content as untrusted input and apply input classifiers with output validation.

You are integrating Claude Code into a workflow that runs against a production database.
Which guardrail design most directly preserves safety on data-modifying operations?

• A. Configure the database MCP server with a fully privileged credential that can perform any read or write operation, and allow all operations to proceed without explicit human confirmation.
• B. Disable all logging and auditing on database operations through the MCP server to reduce alert noise, removing the observability needed to detect unintended data modifications.
• C. Configure the database MCP server with a read-only credential by default, restrict the subagent's tool list to read-only operations, and require explicit human confirmation on any operation that would modify data.
• D. Allow Claude Code to write directly to the production database without subagent scoping, read-only credential defaults, or human confirmation gates on data-modifying operations.

A managed agent deployment for claims triage has grown from 6 tools to 34 tools over 18 months as product teams added capabilities. Triage accuracy has declined from 91 percent to 78 percent, and average tool- selection latency has increased by 2.3 seconds. A junior engineer has proposed adding a tool-router agent in front of the current agent to filter the tool list per request.
Which two findings should you present to justify capability decomposition before adding the router? (Select two.) Each correct answer presents part of the solution.

• A. Several tools have not been invoked across the most recent 90 days of traffic.
• B. The router pattern is well documented across publicly available agent literature.
• C. The proposed router introduces an additional model call on every incoming request.
• D. Tool descriptions overlap across multiple claim categories within the agent's tool set.
• E. The 34 tools serve four distinct claim-workflow domains within the triage scope.

You are compiling factors that should drive the choice between Model Context Protocol (MCP), direct API integration, and agent-to-agent handoff.
Which two factors belong on the list? (Select two.)
Each correct answer presents a complete solution.

• A. Whether the vendor publishes detailed reference documentation for each candidate protocol.
• B. Whether the integration must be portable across multiple AI clients in the ecosystem.
• C. Whether the team has prior implementation experience with any of the candidate protocols.
• D. Whether the interaction is stateless and latency-sensitive or stateful and longer-running.
• E. Whether the underlying transport supports encryption in transit between the integrated services.