# CCDV-F Practice: Agents and workflows | Your AI Department > 9 free CCDV-F practice questions on agents and workflows (14.7% of the exam), with study notes and explanations. Source: https://youraidept.com/network/ccdv-f-practice-questions/agents-and-workflows CCDV-F domain drill # CCDV-F practice questions: Agents and workflows. 9 original questions on Agents and workflows, which carries 14.7% of the Claude Certified Developer – Foundations exam per the published guide. Study notes first, then the questions with an explanation for each. When this domain feels solid, take [the timed CCDV-F practice exam](https://youraidept.com/network/ccdv-f-practice-exam) and check the domain breakdown. ## What to know about Agents and workflows - Implementing the agent loop in code: send messages, detect tool_use blocks, execute, append tool_result blocks, repeat until end_turn. - Workflow patterns from Anthropic's guidance (chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer) and how to pick one. - The Claude Agent SDK: what it handles for you (the loop, tools, permissions, hooks, subagents) versus a hand-rolled loop. - Stop conditions, max turns, and human approval steps. ## Agents and workflows questions All domains (9) Agents and workflows (9) Agents and workflows Which loop correctly implements a tool-using agent? - Call the model once with tool_choice any and return the first tool_use arguments - Call the model; on tool_use run the tool, append the result, call again; stop on end_turn or a turn cap - Call the model repeatedly until its text no longer mentions any tool by name - Run every declared tool up front with default arguments, then pass all of the results to the model in a single call Check answer ### Show answer Answer: Call the model; on tool_use run the tool, append the result, call again; stop on end_turn or a turn cap. The agent loop alternates model turns and tool execution until the model ends its turn or a safety limit stops it. Running tools up front skips the model's decision about which tool to call and with what arguments. Agents and workflows What does the Claude Agent SDK handle for you that a hand-rolled loop does not? - Automatic retries, rate-limit backoff, and typed request and response objects - Fine-tuning the model on your repository before the first run - The agent loop, tool execution, permission checks, hooks, and subagents - Server-side tool execution so your code does not have to handle tool_use blocks Check answer ### Show answer Answer: The agent loop, tool execution, permission checks, hooks, and subagents. The Agent SDK packages the agent loop with tools, permission checks, hooks, and subagent support so you do not rebuild them. Retries and typed objects come from the plain client SDK, which still leaves the loop to you. Agents and workflows In a hand-rolled agent loop, what must happen before calling the model again after a tool call? - Remove the tool_use block from history so the model does not call it again - Change tool_choice to none so the model must answer in text - Append a tool_result block whose tool_use_id matches the tool_use block - Reset the conversation and resend the system prompt with the tool output Check answer ### Show answer Answer: Append a tool_result block whose tool_use_id matches the tool_use block. Tool results must be returned with the matching id, and the tool_use block stays in history so the pairing is valid. Agents and workflows Which pattern fits 'translate, then have a second call grade the translation, then revise until it passes'? - Routing by input type - Orchestrator-workers - Parallel sectioning - Evaluator-optimizer loop Check answer ### Show answer Answer: Evaluator-optimizer loop. Generate, evaluate, refine. Orchestrator-workers splits a task across workers; it does not grade and revise. Agents and workflows What should limit an agent loop besides end_turn? - A maximum number of iterations plus a time or cost budget - The context window, which ends the loop once it fills up - A stop sequence that fires when the model writes the word done - A max_tokens value low enough to stop long-running turns Check answer ### Show answer Answer: A maximum number of iterations plus a time or cost budget. Hard caps prevent runaway loops. Letting the context window fill is a crash, not a limit. Agents and workflows The Claude Agent SDK's hooks are useful for: - Switching the model mid-run when a task turns out to need more capability than expected - Rewriting the system prompt between turns based on the user's tone - Injecting API credentials into the environment before each tool runs - Running deterministic checks around tool calls, such as blocking a dangerous command Check answer ### Show answer Answer: Running deterministic checks around tool calls, such as blocking a dangerous command. Hooks wrap tool calls with your own logic, such as blocking or transforming a call. Model switching and prompt rewriting are not what hooks are for. Agents and workflows A workflow has a step that sometimes needs human input. How should the code model it? - A default value so the step completes and the human reviews afterwards - A pause state that persists progress and resumes when the input arrives - A blocking loop that polls for the input every few seconds until it appears - A retry policy that restarts the workflow from the top once input exists Check answer ### Show answer Answer: A pause state that persists progress and resumes when the input arrives. Human-in-the-loop steps need durable pause and resume. Polling holds resources open, and restarting repeats work already done. Agents and workflows Which is true about subagents in the SDK? - They must use the same system prompt and model as the parent - They run with their own context and return a result to the parent - They share the parent's full conversation so nothing needs restating - They run tools only through the parent, which executes on their behalf Check answer ### Show answer Answer: They run with their own context and return a result to the parent. Subagents isolate context; the parent gets back a result, not the subagent's transcript. Agents and workflows Why give each workflow step one responsibility? - Each step becomes testable on its own and failures are easier to localize - It lets every step share one system prompt across the whole workflow, which keeps behavior consistent - Smaller steps use fewer tokens per run, which lowers cost - The API rejects steps that combine more than one tool Check answer ### Show answer Answer: Each step becomes testable on its own and failures are easier to localize. Single-purpose steps are debuggable. Token savings are not guaranteed, and the API has no such rule. ## Next - [Timed CCDV-F practice exam](https://youraidept.com/network/ccdv-f-practice-exam): 53 questions in 120 minutes, scored against the 720 pass mark. - [All CCDV-F practice questions](https://youraidept.com/network/ccdv-f-practice-questions) with a domain filter. - [The CCDV-F exam page](https://youraidept.com/network/ccdv-f): format, weights, registration, study path. ### Other CCDV-F domains - [Applications and integration (20 questions)](https://youraidept.com/network/ccdv-f-practice-questions/applications-and-integration) - [Model selection and optimization (10 questions)](https://youraidept.com/network/ccdv-f-practice-questions/model-selection-and-optimization) - [Prompt and context engineering (7 questions)](https://youraidept.com/network/ccdv-f-practice-questions/prompt-and-context-engineering) - [Tools and MCPs (6 questions)](https://youraidept.com/network/ccdv-f-practice-questions/tools-and-mcps) ## FAQ ### How much of the CCDV-F exam is agents and workflows? + 14.7% of the marks, per the published CCDV-F exam guide. The full domain list with weights is on the CCDV-F exam page. ### Are these real CCDV-F exam questions? + No. They are 9 original scenario questions written from the blueprint for this domain. Reproducing exam content would violate the candidate agreement. ### How should I study agents and workflows for CCDV-F? + Read the domain notes on this page, answer the questions with explanations hidden, then take the timed CCDV-F practice exam and check the per-domain breakdown for this domain. ## Who wrote this ### [Matei Olaru](https://youraidept.com/about/matei-olaru) CEO, Your AI Department Former public-company CEO, corporate attorney, and World Bank consultant. Runs the YAID Network and the partner relationship with Anthropic. ### [Michael Greenberg](https://youraidept.com/about/michael-greenberg) AI Product Lead, Your AI Department AI at Google, Meta, and Samsung. Six patents. Leads member support and the certification prep guidance. Your AI Department is a registered Claude Partner Network company. Our members sit these exams under our partner standing. Facts on this page were last checked on October 15, 2026. ## Ready to sit CCDV-F for real? Registration needs a Claude Partner Network organization. [YAID Network](https://youraidept.com/network) members register under our partner standing. $149 per quarter, exam fee separate. [Apply to join YAID ↗](https://youraidept.com/network/apply?ref=drill)[How registration works →](https://youraidept.com/network/register-for-claude-certification)