Anthropic CCAR-F - Claude Certified Architect – Foundations

A schema-defined tool provides a structured interface between Claude and the application. The tool’s input_schema can declare required properties, nested work-experience and education objects, arrays of skills, and exact data types. Claude then supplies the extracted resume information as tool-call arguments, which the application can read directly from the tool_use response.

Anthropic’s tool documentation specifies that a custom tool definition includes a JSON Schema object describing its expected parameters. Current strict tool use can additionally enforce that generated tool arguments match the declared schema exactly. This removes the need to locate JSON inside free-form text or depend on post-generation repair. ( https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/implement-tool-use )

Option A is fragile because regular expressions do not provide a robust parser for arbitrary nested JSON and cannot correct missing properties or incorrect types. Option B improves formatting behavior but remains probabilistic. Option C doubles latency and creates two opportunities for information loss: first during extraction and again during reformatting.

In a production design, fields that may genuinely be absent from a resume should be optional or nullable rather than forcing invented values. The tool schema should also use strict: true where supported. Among the available choices, D provides the strongest structural guarantee and the cleanest downstream integration.

Official references/topics: Tool Use Responses, Input Schemas, Strict Tool Use, Nested Structured Extraction.

The checklist is a reusable, task-specific procedure that should load only when a pull-request review is being performed. A /review command provides an explicit invocation mechanism, prevents repeated copy-and-paste, and keeps the checklist out of unrelated coding, debugging, and documentation sessions.

In current Claude Code terminology, custom commands have been consolidated into skills. A .claude/skills/review/SKILL.md file creates a /review command, while the legacy .claude/commands/review.md format remains supported. Anthropic recommends skills when users repeatedly supply the same checklist or multi-step procedure; unlike CLAUDE.md content, the skill body is loaded only when invoked or determined relevant. ( https://code.claude.com/docs/en/skills )

Option B introduces an isolated agent context when the requirement is primarily to inject a repeatable review procedure. A subagent could be useful for independent verification, but it is not necessary merely to avoid repasting the checklist. Option C bloats every session with instructions that apply only to code review. Option D controls editing permissions and planning behavior; it does not encode review criteria.

The review skill can also pre-authorize read-only tools and accept a pull-request identifier or branch as an argument.

Official references/topics: Claude Code Skills; Custom Slash Commands; On-Demand Instructions; Reusable Review Workflows.

Option D preserves the evidence instead of manufacturing certainty. The two estimates are not directly interchangeable: one is an industry estimate with unspecified methodology, while the other is a peer-reviewed estimate with an explicit confidence interval. Converting both into model-generated confidence scores and calculating a weighted average would create a new figure that neither source reported and that may have no statistical validity. Anthropic’s hallucination-reduction guidance recommends making claims auditable through quotations, citations, and supporting evidence rather than presenting unsupported synthesis as fact. Its Citations documentation similarly emphasizes retaining the exact source passages supporting individual claims. Filtering uncertain findings, option B, would remove decision-relevant information. Requiring two-source corroboration, option C, could also discard credible evidence concerning emerging or specialized subjects. The synthesis agent should report the estimates separately, explain their methodological differences, identify which findings are strongly supported or disputed, and state what evidence would resolve the disagreement. This produces calibrated, useful reporting without arbitrary selection, excessive hedging, or false precision.

================

Option C directly searches source-file contents for imports of @company/auth . Anthropic’s Claude Code tools reference states that Grep locates patterns within files, while Glob matches filenames and paths. The search can account for the repository’s supported module syntaxes, including static imports, require() calls, dynamic imports, and re-exports. It can also restrict results by file type or directory when appropriate. Option A identifies packages that declare the dependency but does not prove which source files import or invoke it; workspace-level dependency declarations may cover many packages. Option B finds authentication-related filenames, which are unrelated to whether a file imports the package. Option D searches directory names and therefore has the same limitation. After Grep returns the matching files and line numbers, the agent can read the surrounding code to determine whether each import supports middleware registration, token verification, authorization checks, or re-exporting. This produces an accurate usage inventory while minimizing context consumption and unnecessary file reads.

================

Option A establishes a clear destination without forcing the subagent to follow a brittle route. The prompt should define the research question, boundaries, expected deliverable, acceptable source types, recency requirements, coverage expectations, and verification criteria. The subagent can then broaden, narrow, reformulate, or follow emerging leads according to observed search results.

Anthropic’s research-agent guidance emphasizes giving each subagent an objective, output format, source guidance, and clear task boundaries. It also describes research as dynamic and path-dependent, requiring agents to adapt their strategy as new information emerges.

Option B removes too much structure and may cause duplicated work, incomplete coverage, or inconsistent output. Option C handles only one known failure condition and still restricts the agent to a predetermined procedure. Option D adds classification complexity and creates an artificial boundary between topic types that may change during investigation. Objective-based delegation retains accountability because results can be evaluated against explicit quality criteria, while preserving the agent’s ability to discover alternative terminology, unexpected sources, and useful adjacent evidence. This is controlled autonomy rather than either procedural micromanagement or unrestricted exploration.

================

Option A matches the standard coordinator-managed subagent model. The coordinator invokes the web-search agent, receives its final result, selects the useful URLs or source records, and then supplies them explicitly when invoking the document-analysis agent. This keeps task ownership, provenance, and execution order visible to the coordinator.

The Claude Agent SDK subagent documentation states that a subagent begins with a fresh context window and does not inherit the parent’s conversation history or previous tool results. The information passed through the Agent tool’s prompt is the primary parent-to-subagent context channel. Consequently, the analysis prompt must include the source URLs, documents, retrieval notes, and any questions the analyzer must answer.

Option B requires nested delegation that is neither stated nor necessary and reduces centralized observability. Options C and D describe valid custom architectures only if the application has deliberately implemented a queue or shared memory system; neither is automatic Agent SDK behavior. Coordinator-mediated handoff is therefore the expected approach. For reliability, the handoff should use structured source records rather than an informal prose statement, ensuring that the analyzer receives identifiers, provenance, relevant excerpts, and analysis objectives.

================

Option D directly addresses cache entries expiring before later batch requests are processed. Anthropic’s batch-processing documentation specifically notes that Message Batches can take longer than five minutes and recommends the one-hour prompt-cache duration for batches containing shared context. The prompt-caching documentation confirms that the default TTL is five minutes and that " ttl " : " 1h " creates an extended entry.

Option A may improve cache locality, but it introduces the sequential-processing latency explicitly prohibited by the requirement. Option B seeds the cache initially, but the prewarmed entry still expires after five minutes unless the TTL is extended; it therefore does not solve misses among requests scheduled later. Option C places the breakpoint on request-specific content, defeating reuse of the stable 8,000-token prefix and attempting to cache scripts that are not byte-for-byte identical.

The system should retain the breakpoint at the end of the shared system content and apply the one-hour TTL there. Cache-usage fields should then be monitored to confirm that cache_read_input_tokens rises and later batch requests reuse the intended prefix.

================

Option A identifies the direct configuration contradiction. Each system prompt defines a specialized responsibility, but the corresponding tool allowlist presents unrelated actions as available capabilities. The synthesis agent may therefore interpret web searching as an acceptable way to fill evidence gaps, while the report generator may perform document analysis instead of limiting itself to report production.

Anthropic’s subagent documentation defines subagents as focused workers with their own prompts and specific tool access. Its tool-definition guidance also recommends reducing selection ambiguity by presenting clear, relevant tools. The appropriate correction is least-capability configuration: expose search tools to the search agent, document tools to the analyzer, synthesis utilities to the synthesizer, and formatting or output tools to the report generator.

Option B may affect token efficiency but does not explain the role-specific misuse pattern. Option C concerns delegation, whereas the improper calls occur after successful delegation. Option D is tempting, but Anthropic does not define four or five tools as a universal reliability threshold; 18 tools alone does not prove threshold failure. The decisive defect is misalignment between declared roles and permitted capabilities.

================

The reference to generic rendering patterns indicates that the current context has become saturated or that important earlier details are no longer receiving sufficient attention. Anthropic documents that performance can degrade as a Claude Code context window fills with conversation history, file contents, and command output; symptoms include forgetting earlier instructions and making less precise responses. ( https://code.claude.com/docs/en/best-practices )

Option C preserves the high-value rendering discoveries while isolating the physics investigation. The summary should identify the relevant rendering classes, synchronization boundaries, debug-overlay interfaces, and unresolved integration questions. A physics-focused subagent can then inspect collision and simulation code in its own context without adding dozens of additional files to the already crowded main conversation.

This explicit summary matters because an ordinary named subagent starts with a fresh, isolated context and does not automatically receive the parent’s full conversation history or previously read files. Claude constructs a delegation message containing the task context, so the essential rendering findings must be supplied deliberately. ( https://docs.anthropic.com/en/docs/claude-code/sub-agents )

Option A omits the integration context needed to guide the physics search. Option B destroys useful prior analysis. Option D keeps expanding an already degraded context and treats the symptom rather than controlling context growth.

Official references/topics: Context-Window Management; Subagent Isolation; Delegation Summaries; Codebase Exploration.