CCDV-F practice questions
Anthropic · CCDV-F · 200 questions
Original practice questions for the Anthropic Claude Certified Developer – Foundations (CCDV-F) exam, covering agents and workflows, applications and integration with the Claude API, Claude Code, eval and debugging, model selection and optimization, prompt and context engineering, security and safety, and tools and MCPs — framed in civic and municipal scenarios such as city AI pilots, public-health records, permitting chatbots, 311 assistants, courts / clerk workflows, and transit / utilities operations.
This course contains the use of artificial intelligence.
About the CCDV-F exam
- Exam fee
- $125 USD
- Time allowed
- 2 hours
- Passing score
- 720 (scaled)
- Languages
- English
- Format
- Closed book, multiple choice and scenario-based multiple response, delivered through Pearson VUE online proctored (OnVUE) or at a test centre; allow about 135 minutes of seat time including check-in, instructions and a post-exam survey
Schedule this exam The certification this earns
Exam details published by the vendor, checked 18 October 2026. Vendors change fees and formats without notice — confirm on the vendor's own page before you book.
Practice Quizzes
Test your knowledge with standard 20-question practice sets.
Quiz 1
Quiz 2
Quiz 3
Quiz 4
Quiz 5
Quiz 6
Quiz 7
Quiz 8
Quiz 9
Quiz 10
Browse by Domain
Study specific topics at your own pace.
Agents and Workflows · 30 questions
- A city permitting office needs ordinance FAQ triage where every ticket must follow the same fixed multi-step approval checklist before a reply is sent. When should the team prefer a deterministic workflow over a free-roaming Claude agent?
- A county 311 program wants one Claude manager agent to delegate streetlight outages to one specialist and pothole reports to another. What architecture pattern best fits this design?
- A transit authority splits schedule lookups and fare-policy answers into separate Claude subagents. What is the primary benefit of that isolation?
- A water utility compares a scripted SCADA alert chain to a Claude agent that invents investigation steps at runtime. Which choice best fits high-predictability, safety-critical utility operations?
- A housing authority clerk needs Claude to apply a fixed eligibility checklist and must not invent new criteria mid-call. Which approach best enforces that constraint?
- An emergency-management desk designs a Claude supervisor that should escalate only after field-status subagents return structured reports. What design element makes that gate reliable?
- A library IT team compares one monolithic Claude agent to separate research and catalog-update subagents for staff assistants. When is subagent decomposition the better tradeoff?
- A school-district helpdesk wants an orchestrator that sends password resets to IT tools and curriculum questions to a read-only knowledge agent. What routing principle should it apply?
- A parks department requires inspection photos to be posted before Claude drafts a trail closure notice. Which pattern best enforces that mandatory preceding step?
- A city developer needs Claude to poll the permit database between model turns while building a permitting agent. Which construction approach best supports that custom loop?
- A county IT lead must choose Anthropic-hosted managed agents versus self-hosting the agent runtime inside the county VPC. Which factor most strongly favors self-hosting?
- A court clerk project must prevent Claude from calling a file-delete tool until an archive action is confirmed. Which Agent SDK mechanism provides that deterministic guardrail?
- A 311 engineering team wants tool failures to retry with backoff before control returns to Claude. Where should that retry logic live?
- A transit app team wants riders to see intermediate status while an agent calls arrival-prediction tools. What construction practice supports that experience?
- A public-health portal needs Claude agents that can call department tools for clinic hours and vaccine inventory. What Agent SDK step enables those capabilities?
- A water-utility engineer must ensure Claude cannot open a valve-control API without dual human approval. Which mechanism best enforces that rule?
- A housing-authority team must keep case notes inside the authority's approved hosting boundary. Which agent hosting choice best matches that constraint?
- A municipal open-data portal agent must avoid runaway tool calling against public endpoints. What harness control best bounds fair use per resident query?
- A city CIO wants civic Claude agents that are operable and auditable rather than ad-hoc chat scripts. Which construction preference supports that goal?
- An emergency ops agent must write a structured JSON status update into the incident log after every tool turn. How should that side effect be enforced?
- A permitting agent must look up a parcel, check zoning, then draft conditions from the returned records. Which agent pattern describes that sequence?
- A 311 agent needs the open ticket ID across clarification turns without stuffing the entire chat history each time. What pattern best addresses that need?
- A transit research agent receives long trip-planner tool dumps that risk overflowing the next Claude turn. What should the agent pattern do before continuing?
- A library team must choose between a LangGraph-style graph and a simple Claude tool loop for multi-step catalog repair. What should drive that framework choice?
- A school-district agent retrieves grading policy in one path and must not expose student PII tools on that path. Which pattern best enforces least-privilege isolation?
- A parks maintenance agent must recall prior trail closures across shifts without re-querying the closure API every turn. Which pattern best fits?
- A county clerk agent must keep typed filing steps between tool calls so each stage has validated fields. Which approach best supports that?
- A public-works flood-complaint desk needs inspect, prioritize, and notify workers coordinated as one multi-step job. What should the team use?
- A housing waitlist agent receives huge eligibility-tool JSON that crowds the next deliberation turn. What should developers do?
- A municipal legal-research assistant must search case law without polluting the parent drafting thread. Which design is best?
Applications and Integration · 66 questions
- A city product owner is starting a permitting FAQ on Claude. What should happen before API design begins?
- A county health clinic requires kiosks that still guide residents when the WAN drops. How should that shape Claude integration?
- A transit authority wants overnight ridership analytics summarized and cares more about cost than sub-second answers. What should developers prioritize?
- A court clerk requires that Claude never invent docket numbers missing from the case system. Which requirement class does that encode?
- A housing authority scopes a Claude chat assistant for applicants. Besides the model backend, what must the requirements include?
- A water utility mandates that Claude applications run only in the utility's approved cloud region. How should developers treat that?
- A school district needs Claude to summarize IEPs with different visibility for teachers versus admins. What must requirements capture?
- A city IT PMO is placing a Claude 311 bot under the municipal SDLC. Which life-cycle thinking is appropriate?
- A county must promote a new Claude prompt version from staging to production. What gate should apply?
- A transit team is about to launch a Claude rider assistant that replaces a legacy FAQ bot. What life-cycle step should they plan?
- A public-health app team wants to stay safe across Claude model releases. Which life-cycle practice fits?
- A parks department wants CLAUDE.md and tool schemas managed like other IT assets. How should they classify them?
- A court IT board will allow production Claude access to sealed case metadata only after which gate?
- A 311 backend must show progressive reply text while tools fetch ticket status. Which Messages API capability fits?
- A permitting app needs Claude to read uploaded site-plan images for checklist hints. Which API capability should be enabled?
- A county analytics job must summarize 8000 inspection reports overnight with cost as the main driver. Which API approach fits?
- A transit agent must reason through complex multi-agency detour planning before answering. Which Messages API feature helps?
- A library catalog assistant repeats a large static collection-policy preamble on almost every call. How should developers optimize?
- A housing portal must call Claude through an approved third-party cloud marketplace endpoint. What does that imply for developers?
- A water-utility agent calls a tool and must continue the Claude conversation with that result. Where do tool results go?
- A school-district bot must detect when Claude truncates IEP summaries. Which API handling practice fits?
- A city open-data chatbot must answer questions about large municipal datasets. How should Claude reach the data?
- An emergency dashboard needs Claude to draft live briefings during an active incident. Which API mode fits?
- A clerk app must keep court-assistant instructions and conversation turns correctly structured for Claude. What practice fits?
- A parks mobile app wants Claude to flag hazard indicators in trail photos from field staff. Which capability is required?
- A municipal finance bot reuses the same chart-of-accounts instructions across departments. Which caching practice fits?
- A county GIS assistant must show progressive map-description text while tools fetch parcel attributes. Which approach fits?
- A city team is changing Claude tool schemas for a civic integration. What engineering practice should they apply?
- A 311 service backend calls Claude over REST and must keep request threads responsive. Which practice fits?
- A permitting API returns JSON that Claude tools must consume. What engineering practice fits?
- A transit squad's Claude prompt helper has grown into one untestable file. What should they do?
- A water-utility team deploys Claude tool-argument builders. What should the CI pipeline do before release?
- A housing team must operate Claude beside a case-management API. How should they document failures?
- A school-district engineer is wiring production calls to Claude's REST API. Which client approach fits?
- A library IT review finds a PR that hard-codes secrets into Claude client constructors. What should happen?
- A court app mixes Claude orchestration logic inside UI controllers. What design change improves ownership?
- A parks team wants to introduce a new Claude tool to field staff carefully. Which delivery practice fits?
- A county open-data project will expose internal services for Claude to call. What contract practice fits?
- A public-health backend hits transient Claude HTTP 429 responses. Which resilience practice fits?
- A city devops group wants reproducible Claude client behavior across deploys. What dependency practice fits?
- A housing microservice needs operations visibility into Claude traffic. Which practice fits?
- A transit team's prompts are embedded inside UI code. What large-scale refactor fits?
- A city compares the same permitting instructions in Claude Code versus a Messages API app. What design insight matters?
- A 311 product must keep the resident assistant from advising on criminal complaints. What design control fits?
- A court filing assistant must fill party and case fields for downstream systems. Which output design fits?
- A housing counseling chat runs long and context grows stale. What session-hygiene design fits?
- A library Desktop Claude workspace needs local catalog plugins that a public web FAQ bot should not load. What design choice fits?
- A school district drafts curriculum in a Claude.ai project space but needs a production grading helper with audit trails. Which surface choice fits?
- A water utility SCADA-adjacent assistant must not invent free-text plant control commands. What schema design fits?
- A parks app must keep system trail policy separate from volunteer-uploaded trail notes. What content design fits?
- A county clerk wants the same tool names and descriptions on Desktop Claude bots and API bots. What design practice fits?
- A transit rider app must avoid inventing arrival times beyond published GTFS. What content-boundary design fits?
- A public-health intake bot must feed symptom checklist fields into an EHR API. Which output design fits?
- Municipal grant writers on Claude Desktop need local folder draft plugins managed carefully. What practice fits?
- A housing caseworker finishes eligibility chat and starts a payment-dispute chat with the same resident. What session design fits?
- A city legal-aide chatbot drafts plain-language answers residents might treat as official counsel. What content-boundary design fits?
- An emergency PIO assistant must produce press-release fields under time pressure. What output design fits?
- A county open-data team writes ETL scripts in Claude Code and serves the public with a separate API bot. What design separation fits?
- A parks volunteer scheduler gets JSON slot suggestions from Claude before committing shifts. What closing design step fits?
- A city repo must stop silent default model upgrades from changing permitting answers. What configuration practice fits?
- A 311 team must control production CLAUDE.md edits that change system prompts. What change-control practice fits?
- A transit monorepo needs shared Claude guidance plus service-specific rules. What configuration approach fits?
- A water utility wants approved Claude Code plugins tracked like other software. What configuration practice fits?
- A school district student-data assistant must allow only org-approved tools. Where should that constraint live?
- A housing authority needs to roll back bad eligibility-rule prompt deploys. What configuration practice fits?
- A court IT team must audit model pins, prompts, and plugins together. What configuration discipline fits?
Claude Code · 6 questions
- A city engineering team starts Claude Code in a permit-service repo and needs coding standards loaded. What first practice fits?
- A county developer wants Claude Code to run city lint and security-scan scripts on demand. What Claude Code feature fits?
- A transit squad wants Claude Code to propose GTFS parser test stubs inside CI without an interactive IDE. What operating mode fits?
- A water-utility engineer wants Claude Code to retain plant coding conventions across sessions. Which configuration approach fits?
- A school-district settings.json must constrain Claude Code for student-project sessions. Which configuration goal fits?
- A housing IT lead needs nested CLAUDE.md files to specialize guidance for a case-management microservice. What hierarchy behavior should they explain?
Eval, Testing, and Debugging · 5 questions
- A 311 on-call engineer sees repeated tool-schema validation errors before Claude replies. How should the fault be classified?
- A permitting bot returns fluent but wrong zone codes even though traces show correct tool data returned. What failure type fits?
- A transit agent hits Claude API rate limits during a rush-hour outage FAQ surge. Which recovery strategy fits first?
- A court assistant debug session must find why Claude never saw a filing-status tool reply. What analysis step fits?
- A public-health eval harness flags rising hallucination rates after a prompt edit. What recovery action fits?
Model Selection and Optimization · 34 questions
- A city FAQ team must size a large ordinance corpus for Claude. Which LLM fundamental should guide the plan?
- A 311 lead notices the same complaint summary wording differs across identical retries. What LLM behavior explains this?
- A transit planner needs deeper deliberation for complex multi-leg detour narratives. Which model capability choice fits?
- A housing bot answers simple office-hours questions and nuanced eligibility edge cases. How should prompting intensity differ?
- A water utility must set Claude effort for routine meter FAQs versus regulatory interpretation drafts. What matching rule fits?
- Teachers expect Claude to guarantee identical lesson plans on every regenerate. What should the school district explain?
- A parks app needs quick trail-status rewrites under heavy weekend load. Which latency-oriented choice fits?
- A court clerk sees docket summary wording change across identical Claude requests. What concept explains the change?
- A county open-data agent faces queries that range from trivial field lookups to multi-dataset joins. Which thinking approach fits?
- A public-health team must call Claude on long encounter notes without overflowing capacity. What budgeting step fits?
- A library FAQ must steer Claude toward a preferred citation style. Which prompting technique fits?
- A city backend must call Claude Messages reliably from production services. Which technical approach fits?
- A 311 streaming UI must show Claude tokens as they arrive for resident chat. Which client pattern fits?
- A transit service must authenticate Claude calls without hard-coding credentials. What practice fits?
- A water SCADA historian bridge must send tool arguments through the Claude SDK. What serialization step fits?
- A housing microservice receives Claude SDK failures that must surface cleanly in the case UI. What mapping practice fits?
- A school district needs multiple campus apps to share consistent Claude client behavior. Which SDK design fits?
- A court integration must summarize long filings without blocking clerk workstations. Which SDK usage fits?
- A parks mobile app must send queued Claude requests after trail crews regain signal. Which client pattern fits?
- A county GIS tool must call Claude-related REST endpoints securely from the field. What validation step fits?
- A public-health Python service must keep Claude SDK behavior reproducible across clinic deploys. Which practice fits?
- A library catalog agent receives huge tool result sets that must feed Claude carefully. Which engineering practice fits?
- A municipal finance bot must keep Claude client waits aligned with gateway SLOs. What configuration fits?
- A city routes high-volume 311 intent labels and nuanced ordinance drafts to Claude. Which model split fits?
- A transit cost review evaluates Claude for simple stop-code lookups that Haiku already meets. What decision fits?
- A housing team sees eligibility edge cases shift after a Claude model release. What response fits?
- A court summarizer must compare Claude models for adaptive thinking support. What selection check fits?
- A water utility drafts regulatory nuance where quality outweighs per-call cost. Which model tradeoff fits?
- A county FinOps dashboard must attribute Claude spend across departments. Which practice fits?
- A 311 bot reuses a large static policy block on every Claude call. Which cost optimization fits?
- A transit analytics job must avoid runaway overnight Claude spend on long reports. What budgeting technique fits?
- A library runs multiple Claude skills that share a common catalog ontology preamble. Which caching approach fits?
- A school district must control cost spikes on student homework helpers. Which output control fits?
- A housing authority must estimate Claude spend under projected case volume before go-live. What planning step fits?
Prompt and Context Engineering · 22 questions
- A permitting agent receives verbose GIS tool dumps that threaten the next reasoning turn. What context step fits?
- A 311 session nears the context-window limit during a long resident chat. What management step fits?
- A court research workflow must keep search noise from drifting into drafting context. Which isolation pattern fits?
- A transit trip planner refreshes arrival predictions but old values remain in context. What hygiene step fits?
- A housing case bot must keep working memory lean across eligibility turns. Which selection practice fits?
- A public-health assistant faces multi-page lab PDFs before Claude deliberates. Which compaction strategy fits?
- A parks multi-step agent moves from inspect to notify and carries noisy tool residue. What context practice fits?
- A school-district agent must handle student PII and curriculum-policy text carefully. Which context design fits?
- A city needs Claude to cite ordinance sections instead of vague paraphrases. Which prompt engineering step fits?
- A 311 team must keep immutable city policy separate from free-text resident messages in the prompt. Which placement practice fits?
- A transit team needs rider-alert messages to keep a stable tone and length. Which prompt engineering technique fits?
- A court clerk task should list only missing filing fields, nothing else. Which prompt constraint fits?
- A housing eligibility prompt confuses income thresholds on eval. What refinement practice fits?
- A water utility builds prompts from free-text resident messages. Which assembly step fits?
- A library wants catalog-note style rules to stick when Claude writes output. Which placement approach fits?
- A school IEP helper must avoid unauthorized medical diagnosis wording. Which prompt rule fits?
- Emergency PIO staff say Claude boilerplate is too long. Which prompt practice fits?
- A permitting API receives a Claude JSON checklist destined for the case file. Which output handling step fits?
- A 311 parser gets confident but malformed ticket JSON from Claude. What defensive handling fits?
- A transit integrator needs ETA fields that downstream systems can parse. Which output approach fits?
- A housing UI must not show Claude dollar amounts that fail numeric checks. Which gate fits?
- A court export job consumes Claude summaries for legal clerks. Which defensive parse step fits?
Security and Safety · 16 questions
- A 311 agent receives pasted webpage text that might hide instructions. How should the team treat that input?
- A permitting pipeline must reduce injection risk from uploaded PDFs before Claude reads them. Which mitigation fits?
- A housing bot stores Claude transcripts in logs. Which privacy control fits?
- A school assistant can call student-record tools. Which access control fits?
- A court research agent is asked to ignore sealing rules via a jailbreak-style prompt. What defense fits?
- A public-health chatbot handles sensitive encounter details with Claude. Which confidentiality practice fits?
- A city wants safer resident chat around toxic content with Claude. Which guardrail design fits?
- A transit ops Claude tool connects to GTFS data. Which privilege model fits?
- A water utility connects Claude near plant systems. Which secure-by-design tool policy fits?
- A housing team wants to enable case-note summarization with Claude. Which go-live gate fits?
- A library public kiosk runs Claude for visitors. Which tool control fits?
- A court Claude app must stop unsupervised case-file deletes. Which hooks control fits?
- A 311 harness must stop Claude from running shell-exec during ticket triage. Which hooks control fits?
- A city must manage Claude API keys for production apps. Which secrets practice fits?
- A school district runs sandbox and production Claude apps. Which key separation fits?
- A housing ops team needs visibility into Claude-calling identities. Which monitoring practice fits?
Tools and MCPs · 21 questions
- A permitting app needs Claude to look up parcels reliably. Which tool design fits?
- A 311 client-side tool can create work orders. Which approval pattern fits?
- A transit harness needs live vehicle positions for Claude. Which dispatch pattern fits?
- A water utility exposes Claude tools near plant operations. Which tool-set construction fits?
- A housing case tool cannot find a case ID. Which error signaling fits?
- A court filing tool updates dockets via Claude. Which description quality fits?
- A school roster tool must fetch attendance every turn. Which tool-use configuration fits?
- A parks inspection tool attaches photos to closure notices. Which validation fits?
- A library catalog agent looks up many ISBNs with Claude. Which efficiency pattern fits?
- A county wants GIS parcel tools reused by permitting and assessor Claude apps. Which MCP approach fits?
- A transit MCP server supports Claude Code with route docs and live ETAs. Which MCP design fits?
- A housing IT team shares case APIs across chatbots. Which MCP deployment fits?
- A school-district MCP provides a networked student-info tool gateway. Which transport choice fits?
- A city needs local file edits in Claude Code and shared permit-database access. Which tooling split fits?
- A 311 team needs reusable tone-of-voice standards across Claude surfaces. Which customization fits?
- A court agent needs current docket state for Claude. Which approach fits?
- A water utility needs a one-off plant report inside a single Claude app. Which customization fits?
- A housing consortium wants eligibility services shared by partner cities. Which MCP pattern fits?
- A library needs citation style guidance and live ILS search for Claude. Which matching fits?
- A transit on-call engineers with Claude Code against logs and GTFS. Which combination fits?
- A school district evaluates a new gradebook capability for Claude. Which decision approach fits?
These questions are original practice material and are NOT actual exam questions or brain-dump content. All vendor marks are trademarks of their respective owners. This site is not affiliated with, endorsed by, or sponsored by Anthropic.