Claude Certified Developer – Foundations: Independent Exam Prep

Finish the series by connecting model guidance, authorization, hooks, isolation and evidence-based release decisions. Work through original Maple Room scenarios and a cumulative teach-back covering context, tool contracts, identity, approval and uncertain outcomes. Independent exam preparation, not endorsed by Anthropic.

Source links:

https://code.claude.com/docs/en/security

https://code.claude.com/docs/en/hooks

https://code.claude.com/docs/en/hooks-guide

https://code.claude.com/docs/en/agent-sdk/permissions

https://code.claude.com/docs/en/sandboxing

https://code.claude.com/docs/en/agent-sdk/secure-deployment

https://platform.claude.com/docs/en/test-and-evaluate/develop-tests

Why external content is not authority, authentication is not blanket permission, and secrets are capabilities. Follow Noor at fictional Maple Room through an injected repair document, cross-building access controls, MCP token boundaries, and a leaked credential. Includes three original practice questions with explained answers. Independent exam preparation, not endorsed by Anthropic; no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks

https://platform.claude.com/docs/en/managed-agents/secure-deployment-risks

https://cheatsheetseries.owasp.org/cheatsheets/LLM_Prompt_Injection_Prevention_Cheat_Sheet.html

https://cheatsheetseries.owasp.org/cheatsheets/Authorization_Cheat_Sheet.html

https://cheatsheetseries.owasp.org/cheatsheets/Insecure_Direct_Object_Reference_Prevention_Cheat_Sheet.html

https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization

https://modelcontextprotocol.io/specification/2026-07-28/basic/authorization/security-considerations

https://cheatsheetseries.owasp.org/cheatsheets/Secrets_Management_Cheat_Sheet.html

Use trace evidence to isolate integration, model-output, and display failures, then choose recovery without blind retries or duplicate actions. Follow an original Maple Room repair case through API-version changes, rate and spend limits, streaming errors, and an uncertain ticket request. Includes three original practice questions with explained answers. Independent exam preparation, not endorsed by Anthropic; no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/api/errors

https://platform.claude.com/docs/en/api/rate-limits

https://platform.claude.com/docs/en/api/migration-2026-10-21

https://code.claude.com/docs/en/monitoring-usage

https://opentelemetry.io/docs/concepts/signals/traces/

https://opentelemetry.io/docs/concepts/signals/logs/

https://opentelemetry.io/docs/concepts/signals/metrics/

Choose Claude Code components, inspect loaded project guidance, resume sessions carefully, and distinguish output modes from permission and isolation controls.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://code.claude.com/docs/en/features-overview

https://code.claude.com/docs/en/skills

https://code.claude.com/docs/en/memory

https://code.claude.com/docs/en/sessions

https://code.claude.com/docs/en/permission-modes

https://code.claude.com/docs/en/permissions

https://code.claude.com/docs/en/headless

https://code.claude.com/docs/en/settings

Personal views only; no employer affiliation or endorsement.

Build Maple Room's handover workflow by matching existing operations, a custom repair integration, reusable Skill guidance, an MCP connection, and optional plugin packaging. Learn why these components can compose, how execution and permissions differ by surface, and which maintenance responsibilities each introduces.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview

https://code.claude.com/docs/en/agent-sdk/overview

https://code.claude.com/docs/en/agent-sdk/custom-tools

https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview

https://code.claude.com/docs/en/skills

https://code.claude.com/docs/en/agent-sdk/skills

https://code.claude.com/docs/en/plugins

https://modelcontextprotocol.io/specification/2026-07-28

Personal views only; no employer affiliation or endorsement.

A compact MCP lesson: identify host, client, and server; distinguish resources, prompts, and tools; select compatible protocol and transport behavior; and test clear errors and denied access. Current2026-07-28 request semantics are explicitly separated from older initialization-based revisions.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://modelcontextprotocol.io/specification/2026-07-28

https://modelcontextprotocol.io/specification/2026-07-28/server/tools

https://modelcontextprotocol.io/specification/2026-07-28/server/resources

https://modelcontextprotocol.io/specification/2026-07-28/basic/versioning

https://modelcontextprotocol.io/specification/2026-07-28/basic/transports

https://modelcontextprotocol.io/specification/2026-07-28/basic/transports/stdio

https://modelcontextprotocol.io/specification/2026-07-28/basic/transports/streamable-http

Personal views only; no employer affiliation or endorsement.

Follow a proposed repair-note operation through schema design, registered dispatch, business validation, access checks, approval, execution, and matched results. Original questions cover forbidden but well-formed inputs, parallel lookup results, and recovery after a write timeout.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview

https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools

https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use

https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls

https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use

https://code.claude.com/docs/en/agent-sdk/user-input

https://code.claude.com/docs/en/agent-sdk/permissions

https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/

Personal views only; no employer affiliation or endorsement.

Compare a custom Messages API loop, a process-operated Claude Agent SDK harness, and Claude Managed Agents. Follow Maple Room through execution ownership, conversation and working state, self-hosted tool sandboxes, hooks, and recovery after an uncertain write. Includes original retrieval questions and an ownership teach-back.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://code.claude.com/docs/en/agent-sdk/overview

https://code.claude.com/docs/en/agent-sdk/agent-loop

https://code.claude.com/docs/en/agent-sdk/hosting

https://code.claude.com/docs/en/agent-sdk/sessions

https://code.claude.com/docs/en/agent-sdk/hooks

https://code.claude.com/docs/en/agent-sdk/permissions

https://platform.claude.com/docs/en/managed-agents/overview

https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes

https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/

Personal views only; no employer affiliation or endorsement.

Trace a tool-use loop, distinguish active context, checkpoints, and long-term memory, and compare framework abstractions. Use original scenarios to reason about denied tools, scoped preferences, durable review pauses, and recovery evidence.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://strandsagents.com/latest/documentation/docs/user-guide/concepts/agents/agent-loop/

https://docs.langchain.com/oss/python/langgraph/overview

https://docs.langchain.com/oss/python/langgraph/persistence

https://pydantic.dev/docs/ai/overview/

https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool

https://code.claude.com/docs/en/sub-agents

https://www.anthropic.com/research/building-effective-agents

https://docs.langchain.com/oss/python/langchain/multi-agent

Personal views only; no employer affiliation or endorsement.

Design a predictable packing workflow and an adaptive investigation for a fictional museum. Choose routing, parallel checks, single-agent investigation, or supervised delegation, and define concrete completion, limits, and human handoffs.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://www.anthropic.com/research/building-effective-agents

https://code.claude.com/docs/en/sub-agents

https://docs.langchain.com/oss/python/langgraph/workflows-agents

https://docs.langchain.com/oss/python/langchain/multi-agent

Personal views only; no employer affiliation or endorsement.

Compare model configurations by acceptable-result quality, end-to-end latency, compatibility, and total cost. Use fictional token prices to calculate retries and cache reuse, then connect configuration, prompting, context, and output handling in a cumulative checkpoint.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/models/overview

https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions

https://platform.claude.com/docs/en/api/migration-2026-10-21

https://platform.claude.com/docs/en/build-with-claude/context-windows

https://platform.claude.com/docs/en/build-with-claude/token-counting

https://platform.claude.com/docs/en/build-with-claude/prompt-caching

Personal views only; no employer affiliation or endorsement.

Follow an invented delivery record through completion, parsing, structural checks, evidence validation, and authorization. Practice three original decisions about missing fields, truncation, and permission checks.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/build-with-claude/structured-outputs

https://json-schema.org/understanding-json-schema/reference/object

Personal views only; no employer affiliation or endorsement.

Preserve decisive evidence and valid state while using targeted retrieval, pruning, compaction, and isolated investigations. Includes three original questions.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/build-with-claude/context-windows

https://platform.claude.com/docs/en/build-with-claude/context-editing

https://platform.claude.com/docs/en/build-with-claude/compaction

https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand

https://platform.claude.com/docs/en/build-with-claude/compaction-thinking-blocks

https://platform.claude.com/docs/en/build-with-claude/compaction-threshold

https://code.claude.com/docs/en/sub-agents

https://www.anthropic.com/research/effective-context-engineering-for-ai-agents

Personal views only; no employer affiliation or endorsement.

Improve a failing prompt through observable requirements, correct placement, diverse examples, usable constraints, and separate evaluation cases. Includes three original questions.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview

https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices

https://platform.claude.com/docs/en/build-with-claude/working-with-messages

https://platform.claude.com/docs/en/test-and-evaluate/develop-tests

https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-hallucinations

https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks

https://platform.claude.com/docs/en/build-with-claude/structured-outputs

https://code.claude.com/docs/en/sub-agents

Personal views only; no employer affiliation or endorsement.

Trace effective configuration across model identifiers, API and SDK versions, prompts, settings, and resolved dependencies. Includes three original decision questions.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/about-claude/models/model-ids-and-versions

https://platform.claude.com/docs/en/api/versioning

https://platform.claude.com/docs/en/api/migration-2026-10-21

https://platform.claude.com/docs/en/cli-sdks-libraries/overview

https://code.claude.com/docs/en/settings

https://code.claude.com/docs/en/memory

https://code.claude.com/docs/en/plugin-dependencies

https://docs.npmjs.com/cli/v11/configuring-npm/package-lock-json/

Personal views only; no employer affiliation or endorsement.

Design schema contracts, keep repair-case sessions separate, and choose a maintainable plugin boundary. Includes three original retrieval questions.

Independent exam preparation, not endorsed by Anthropic; original questions, no actual exam items or pass guarantee.

Source links:

https://platform.claude.com/docs/en/build-with-claude/structured-outputs

https://json-schema.org/understanding-json-schema/reference/object

https://code.claude.com/docs/en/sessions

https://code.claude.com/docs/en/memory

https://code.claude.com/docs/en/plugins

https://code.claude.com/docs/en/plugins/create

Personal views only; no employer affiliation or endorsement.

Why does the same request behave differently in a Claude project, Claude Code and an API application? Follow a fictional repair cooperative across interfaces to inspect instruction scope, loaded context, reference material and action controls. Learn where project guidance, system prompts, repository files and Agent SDK settings belong, and why instructions do not replace permissions. Original practice questions test missing guidance, untrusted retrieved content and evidence that a migration preserves the intended behavior.

Independent Exam Prep with original scenarios and questions. No Anthropic affiliation or endorsement. Personal views only; no employer affiliation or endorsement.

Source credits: Claude Certified Developer – Foundations Exam Guide, version 1.0, effective July 2026; Anthropic's official personalization, project, Messages, tool-use, Claude Code memory, Agent SDK and security documentation. Technical references checked October 20, 2026.

References:
https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features
https://support.claude.com/en/articles/9519177-how-can-i-create-and-manage-projects
https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork
https://platform.claude.com/docs/en/api/messages/create
https://platform.claude.com/docs/en/build-with-claude/working-with-messages
https://code.claude.com/docs/en/memory
https://code.claude.com/docs/en/agent-sdk/modifying-system-prompts
https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls
https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
https://platform.claude.com/docs/en/managed-agents/secure-deployment-risks

A pull request promises a little cleanup, but its diff changes a formatter, a prompt and an access check. Follow a fictional repair-desk patch through the working tree, staging area, commit, pull request and merge. Learn to review the exact revision, resolve conflicts against intended behavior, and distinguish a behavior-preserving refactor from a feature or permission change. Original practice questions connect version control, independent review, preservation checks and the limits of reverting source code.

Independent Exam Prep with original scenarios and questions. No Anthropic affiliation or endorsement. Personal views only; no employer affiliation or endorsement.

Source credits: Claude Certified Developer – Foundations Exam Guide, version 1.0, effective July 2026; Git's official documentation, GitHub Docs, Google's code-review guidance, and Martin Fowler's refactoring definition. Technical references checked October 20, 2026.

References:

https://git-scm.com/docs/git-add

https://git-scm.com/docs/git-commit

https://git-scm.com/docs/git-diff

https://git-scm.com/book/en/v2/Git-Basics-Recording-Changes-to-the-Repository

https://git-scm.com/book/en/v2/Git-Branching-Branches-in-a-Nutshell

https://git-scm.com/docs/git-push

https://git-scm.com/book/en/v2/Git-Branching-Basic-Branching-and-Merging

https://docs.github.com/en/pull-requests/reference/pull-requests

https://google.github.io/eng-practices/review/developer/small-cls.html

https://google.github.io/eng-practices/review/reviewer/looking-for.html

https://martinfowler.com/bliki/DefinitionOfRefactoring.html

https://git-scm.com/docs/git-revert

What happens when a request is accepted but the work is unfinished, or a notification is sent but its acknowledgement never arrives? A fictional repair-desk application brings HTTP contracts, JSON validation and asynchronous scheduling into focus. You'll examine dependent and concurrent work, bounded queues, deadlines, cancellation and retries, then use delivery evidence to resolve an uncertain outcome before repeating a side effect. Practice questions help connect the code's behavior to the result the application can safely claim.

Independent Exam Prep with original scenarios and questions. No Anthropic affiliation or endorsement. Personal views only; no employer affiliation or endorsement.

Source credits: Claude Certified Developer – Foundations Exam Guide, version 1.0, effective July 2026; Anthropic's API documentation; HTTP, PATCH and JSON standards; Python documentation; and Amazon's retry guidance. Technical references checked October 13, 2026.

Live repair assistance and overnight analysis need different ways of working. Follow both workloads to learn how to track streamed content, recognize completion and recover from interrupted responses. Then work through batch identifiers, out-of-order results and item-by-item recovery. The lesson connects those choices to model providers, authentication and deployment configuration, and explains why prompt caching depends on an eligible matching prefix rather than simply reusing the same words somewhere in a request.

Independent Exam Prep with original scenarios and questions. No Anthropic affiliation or endorsement. Personal views only; no employer affiliation or endorsement.

Source credits: Claude Certified Developer – Foundations Exam Guide, version 1.0, effective July 2026; Anthropic's official API documentation and Microsoft Learn's Claude deployment guidance. Technical references checked October 13, 2026.