Free Fortinet NSEI_OTS_AR-7.6 Exam Questions

Question 1

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles highambiguity requests like returns, billing disputes, and account issues. It has access to your backend systemsthrough custom Model Context Protocol (MCP) tools ( get_customer , lookup_order , process_refund ,escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.During testing, you find that when a customer says “I need a refund for my recent purchase,” the agent callsprocess_refund immediately—but populates the required order_id parameter with a plausible-looking butfabricated value instead of first calling lookup_order to retrieve the actual order ID. The refund call failsbecause the fabricated ID doesn’t exist.Which change directly addresses the root cause of the agent fabricating the order_id value?

A : Update the process_refund tool description to explicitly state that order_id must be obtained from a prior lookup_order call and must never be assumed or invented.

B : Switch tool_choice from " auto " to " any " to force the agent to make a tool call on every turn.

C : Add server-side validation that checks whether the order_id exists in your database before executing the refund, returning an error to the agent if not found.

D : Pre-parse incoming customer messages to extract any order IDs mentioned, and inject them into the conversation context before passing to Claude.

Answer: A

Question 2

You are building a structured data extraction system using Claude. The system extracts information fromunstructured documents, validates the output using JavaScript Object Notation (JSON) schemas, andmaintains high accuracy. It must handle edge cases gracefully and integrate with downstream systems.Monitoring shows 12% of extractions fail Pydantic validation with specific errors like “expected float forquantity, got ‘2 to 3’”. Retrying these requests without modification produces identical failures.What’s the most effective approach to recover from these validation failures?

A : Send a follow-up request including the validation error, asking the model to correct its output.

B : Set temperature to 0 to eliminate output variability and ensure consistent formatting.

C : Pre-process source documents to standardize problematic formats before sending them for extraction.

D : Implement a secondary pipeline using a larger model tier to reprocess documents that fail validation.

Answer: A

Question 3

You are building a customer support resolution agent using the Claude Agent SDK. The agent handles highambiguity requests like returns, billing disputes, and account issues. It has access to your backend systemsthrough custom Model Context Protocol (MCP) tools ( get_customer , lookup_order , process_refund ,escalate_to_human ). Your target is 80%+ first-contact resolution while knowing when to escalate.Your process_refund tool returns two types of errors: technical errors (“503 Service Unavailable”,“Connection timeout”) that are transient (~5% of calls), and business errors (“Order exceeds 30-day returnwindow”, “Item already refunded”) that are permanent (~12% of calls). Monitoring shows the agent wastes 3–4 turns retrying business errors that can never succeed. Currently, both error types return only a plain textmessage to Claude.What’s the most effective way to reduce wasted retries while improving customer-facing response quality?

A : Implement automatic retry logic at the tool layer for technical errors only, passing business errors to Claude without retries.

B : Add few-shot examples showing how to distinguish retriable from non-retriable errors by parsing error message text.

C : Add a check_refund_eligibility tool that must be called before process_refund to prevent business rule violations.

D : Return structured error responses with " retriable " : false for business errors and a customer-friendly explanation for Claude to use.

Answer: D

Question 4

You are integrating Claude Code into your Continuous Integration/Continuous Deployment (CI/CD) pipeline. The system runs automated code reviews, generates test cases, and provides feedback on pull requests. You need to design prompts that provide actionable feedback and minimize false positives. Your automated reviewer uses a single prompt covering security issues, API design, and business-logic correctness. Your evaluation suite shows strong recall for API-design findings at 82% but poor recall for business-logic edge cases in quiz scoring at 34%. When you add few-shot examples of logic bugs to the prompt, logic recall improves to 41%, but API-design recall drops to 68%. How should you address this trade-off to improve detection across both categories?

A : Split the review into separate focused prompts—one for security and API design and another for business logic—each with dedicated examples, and then consolidate the findings before posting.

B : Replace the few-shot examples with a detailed checklist of specific logic edge cases to verify, such as division by zero in score calculations and boundary conditions in grading thresholds.

C : Upgrade to a more capable model tier because its stronger reasoning will handle both concern types in one prompt and eliminate the recall trade-off.

D : Provide the full repository as context instead of only the changed files and surrounding code, giving the model deeper visibility into business-logic patterns.

Answer: A

Question 5

You are building a structured data extraction system using Claude. The system extracts information fromunstructured documents, validates the output using JSON schemas, and maintains high accuracy. It musthandle edge cases gracefully and integrate with downstream systems.Your extraction system uses tool use with a JSON schema containing 12 fields and detailed descriptions,totaling approximately 2,500 tokens for the complete tool definition. Processing documents under 150,000tokens yields 98% accuracy. For documents between 175,000 and 190,000 tokens, accuracy drops to 71%,with information from the final third consistently missed. The model’s context window is 200,000 tokens.What is the most likely cause?

A : Schemas exceeding eight to ten fields increase decision complexity during parameter generation, reducing extraction accuracy independently of document length.

B : The model distributes attention proportionally across the input length, causing fields mentioned only once near the document’s end to receive insufficient processing focus.

C : Very long documents exceed the model’s effective attention span regardless of context limits, causing accuracy degradation for content farther from the prompt instructions.

D : Tool definitions consume input-context tokens. Combined with system prompts and document content, the total approaches the context limit, degrading end-of-document processing.

Answer: D