Source: raw/claude-cookbooks-main/ — see also multi-agent research pattern deep-dive and chief-of-staff agent template deep-dive (2026-05-23 batch) and the agentic-search evals section below. 2026-07-24 ecosystem-watch batch: seven anthropics/claude-cookbooks commit stubs — 6c63a145/85016cac (crop→zoom rewrite, PR #793), c39be3a2/995c3c88 (subagent live-streaming, PR #792), 849918c6/1f932a8c/90b3ebd6 (Fraud Review Agent + MongoDB Atlas, PR #759) — folded into the dated sections below.
The official Anthropic cookbook repository containing Jupyter notebooks and Python examples for building with the Claude API. Repo renamed 2026-06-30: github.com/anthropics/anthropic-cookbook → github.com/anthropics/claude-cookbooks (old URL redirects; 46,364 stars as of 2026-07-02). This article catalogs the cookbooks as a CCA-F study resource, organizing them by exam domain relevance. Each notebook provides hands-on code you can run to internalize the patterns tested on the exam.
Repository Overview
- Language: Python (Jupyter notebooks)
- License: MIT
- Key directories:
tool_use/,capabilities/,misc/,multimodal/,patterns/agents/,claude_agent_sdk/,managed_agents/,skills/,extended_thinking/,evals/(new 2026-06-30 — see below) - Prerequisites: Anthropic API key, Python 3.10+,
uvfor dependency management - Setup:
uv sync --all-extras, thencp .env.example .envand add yourANTHROPIC_API_KEY
Cookbooks by Exam Domain
Domain 1: Agentic Architecture & Orchestration (27%)
These notebooks demonstrate the agentic loop lifecycle, coordinator-subagent patterns, and multi-agent orchestration:
| Notebook | Path | What it teaches |
|---|---|---|
| Customer Service Agent | tool_use/customer_service_agent.ipynb | Full agentic loop: tool calls, stop_reason checking, conversation management. Directly maps to Task 1.1 |
| Orchestrator Workers | patterns/agents/orchestrator_workers.ipynb | Coordinator-subagent pattern with parallel workers. Maps to Tasks 1.2, 1.3 |
| Basic Workflows | patterns/agents/basic_workflows.ipynb | Prompt chaining, routing, parallelization patterns. Maps to Task 1.6 |
| Evaluator Optimizer | patterns/agents/evaluator_optimizer.ipynb | Iterative refinement loops where evaluator guides optimizer. Maps to Task 1.6 |
| Sub-Agents | multimodal/using_sub_agents.ipynb | Spawning sub-agents for parallel processing. Maps to Task 1.3 |
| One-Liner Research Agent | claude_agent_sdk/00_The_one_liner_research_agent.ipynb | Minimal Agent SDK setup. Maps to Tasks 1.1, 1.3 |
| Chief of Staff Agent | claude_agent_sdk/01_The_chief_of_staff_agent.ipynb | Multi-agent delegation with coordinator. Maps to Tasks 1.2, 1.3 |
| Session Browser | claude_agent_sdk/05_Building_a_session_browser.ipynb | Session management and state inspection. Maps to Task 1.7 |
Managed Agents cookbooks (advanced agentic patterns):
CMA_orchestrate_issue_to_pr.ipynb— end-to-end orchestration from GitHub issue to PRCMA_iterate_fix_failing_tests.ipynb— iterative test-fixing loopsCMA_gate_human_in_the_loop.ipynb— human-in-the-loop gating patternsCMA_operate_in_production.ipynb— production operation patternsCMA_explore_unfamiliar_codebase.ipynb— codebase exploration strategiesroadtrip_planner— Next.js chat on a Managed Agent session (PR #750, merged 2026-06-30); see Managed Agents- Subagent live-streaming (PR #792, merged 2026-07-22) — streams a coordinator and its subagents in real time; per-thread event deltas,
initial_events, per-agent modeleffort, versionless agent updates. See the 2026-07-22 refresh below. - Fraud Review Agent with MongoDB Atlas (PR #759, merged 2026-07-23) — partner-contributed from
mongodb-partners. See the 2026-07-23 partner-cookbook section below.
Domain 2: Tool Design & MCP Integration (18%)
These notebooks cover tool definition, structured errors, tool choice configuration, and tool search patterns:
| Notebook | Path | What it teaches |
|---|---|---|
| Calculator Tool | tool_use/calculator_tool.ipynb | Basic tool definition with JSON schema. Maps to Task 2.1 |
| Parallel Tools | tool_use/parallel_tools.ipynb | Parallel tool execution patterns. Maps to Task 2.3 |
| Tool Choice | tool_use/tool_choice.ipynb | auto, any, and forced tool selection. Maps to Task 2.3 |
| Tool Search (Embeddings) | tool_use/tool_search_with_embeddings.ipynb | Semantic tool search for large tool sets. Maps to Task 2.3 |
| Tool Search (Alternate) | tool_use/tool_search_alternate_approaches.ipynb | Alternative approaches to tool discovery. Maps to Task 2.3 |
| Programmatic Tool Calling | tool_use/programmatic_tool_calling_ptc.ipynb | Programmatic (non-LLM) tool execution. Maps to Tasks 2.1, 2.3 |
| Context Engineering Tools | tool_use/context_engineering/context_engineering_tools.ipynb | Context-aware tool design. Maps to Tasks 2.1, 2.4 |
| Memory Cookbook | tool_use/memory_cookbook.ipynb | Persistent memory tools. Maps to Task 2.4 |
| Automatic Context Compaction | tool_use/automatic-context-compaction.ipynb | Automatic context management. Maps to Tasks 2.4, 5.4 |
| Tool Use with Pydantic | tool_use/tool_use_with_pydantic.ipynb | Schema validation with Pydantic. Maps to Task 2.1 |
| Tool Evaluation | tool_evaluation/tool_evaluation.ipynb | Evaluating tool use quality. Maps to Task 2.1 |
| Threat Intel Agent | tool_use/threat_intel_enrichment_agent.ipynb | Multi-tool agent for security. Maps to Tasks 2.1, 2.3 |
Domain 3: Claude Code Configuration & Workflows (20%)
The cookbooks repo itself demonstrates Claude Code configuration patterns:
| Resource | Path | What it teaches |
|---|---|---|
| Root CLAUDE.md | CLAUDE.md | Project-level configuration with coding standards, model aliases, git workflow. Maps to Task 3.1 |
| Slash Commands | .claude/commands/ | Project-scoped commands (notebook-review, review-pr, link-review, model-check). Maps to Task 3.2 |
| Skills | .claude/skills/cookbook-audit/SKILL.md | Skill with style guide reference, demonstrating SKILL.md frontmatter. Maps to Task 3.2 |
| Code Reviewer Agent | .claude/agents/code-reviewer.md | Agent definition for automated code review. Maps to Task 3.6 |
| Skills Notebooks | skills/notebooks/01_skills_introduction.ipynb | Introduction to skills system. Maps to Task 3.2 |
| Skills Custom Dev | skills/notebooks/03_skills_custom_development.ipynb | Building custom skills. Maps to Task 3.2 |
Domain 4: Prompt Engineering & Structured Output (20%)
These notebooks demonstrate structured output, few-shot prompting, batch processing, and validation patterns:
| Notebook | Path | What it teaches |
|---|---|---|
| Extracting Structured JSON | tool_use/extracting_structured_json.ipynb | JSON extraction via tool_use. Maps to Task 4.3 |
| Enable JSON Mode | misc/how_to_enable_json_mode.ipynb | Reliable JSON output. Maps to Task 4.3 |
| Batch Processing | misc/batch_processing.ipynb | Message Batches API usage, custom_id correlation. Maps to Task 4.5 |
| Building Evals | misc/building_evals.ipynb | Automated evaluation patterns. Maps to Tasks 4.4, 4.6 |
| Generate Test Cases | misc/generate_test_cases.ipynb | Test case generation. Maps to Task 3.5 |
| Moderation Filter | misc/building_moderation_filter.ipynb | Content classification with structured output. Maps to Task 4.1 |
| Using Citations | misc/using_citations.ipynb | Citation tracking in output. Maps to Task 5.6 |
| Classification Guide | capabilities/classification/guide.ipynb | Classification patterns with explicit criteria. Maps to Task 4.1 |
| Summarization Guide | capabilities/summarization/guide.ipynb | Summarization with structured output. Maps to Task 4.3 |
| RAG Guide | capabilities/retrieval_augmented_generation/guide.ipynb | Retrieval-augmented generation. Maps to Tasks 4.2, 5.1 |
| Vision with Tools | tool_use/vision_with_tools.ipynb | Multimodal structured extraction. Maps to Task 4.3 |
| Zoom / Crop Tool | multimodal/crop_tool.ipynb | Pixel-coordinate zoom tool for fine image detail; visual-token budgeting, 1:1 coordinate mapping, pause_turn handling. Maps to Tasks 2.1, 4.3. Deep-dive: Giving Claude a Zoom Tool for Fine Image Detail |
| Metaprompt | misc/metaprompt.ipynb | Prompt generation and refinement. Maps to Task 4.1 |
Domain 5: Context Management & Reliability (15%)
These notebooks address context window management, prompt caching, session memory, and long-document handling:
| Notebook | Path | What it teaches |
|---|---|---|
| Prompt Caching | misc/prompt_caching.ipynb | Cache-aware prompt design, cost reduction. Maps to Task 5.1 |
| Speculative Caching | misc/speculative_prompt_caching.ipynb | Advanced caching strategies. Maps to Task 5.1 |
| Session Memory Compaction | misc/session_memory_compaction.ipynb | Compacting long conversation history. Maps to Tasks 5.1, 5.4 |
| Automatic Context Compaction | tool_use/automatic-context-compaction.ipynb | Automated context management. Maps to Task 5.4 |
| PDF Upload Summarization | misc/pdf_upload_summarization.ipynb | Handling long documents. Maps to Task 5.1 |
| Sampling Past Max Tokens | misc/sampling_past_max_tokens.ipynb | Working beyond token limits. Maps to Task 5.1 |
| Observability Agent | claude_agent_sdk/02_The_observability_agent.ipynb | Agent monitoring and observability. Maps to Task 5.3 |
| SRE Agent | claude_agent_sdk/03_The_site_reliability_agent.ipynb | Reliability patterns in practice. Maps to Task 5.3 |
| Prompt Versioning & Rollback | managed_agents/CMA_prompt_versioning_and_rollback.ipynb | Managing prompt versions for reliability. Maps to Task 5.3 |
Extended Thinking (Cross-Domain)
| Notebook | Path | What it teaches |
|---|---|---|
| Extended Thinking | extended_thinking/extended_thinking.ipynb | Chain-of-thought reasoning patterns. Relevant to Tasks 4.1, 4.6 |
| Extended Thinking + Tools | extended_thinking/extended_thinking_with_tool_use.ipynb | Combining reasoning with tool use. Relevant to Tasks 1.1, 4.3 |
Recommended Study Path
Work through the notebooks in this order to build knowledge progressively:
- Week 1 — Tool Foundations:
calculator_tool->tool_choice->parallel_tools->extracting_structured_json - Week 2 — Agentic Patterns:
customer_service_agent->basic_workflows->orchestrator_workers->evaluator_optimizer - Week 3 — Production Concerns:
batch_processing->prompt_caching->session_memory_compaction->building_evals - Week 4 — Advanced Agents: Agent SDK notebooks (00-05) -> Managed Agents notebooks ->
context_engineering_tools
Key Takeaways
- The cookbooks repository provides runnable code for nearly every CCA-F task statement — use it as your hands-on lab
- Domain 1 (Agentic Architecture) has the richest notebook coverage: the
patterns/agents/,claude_agent_sdk/, andmanaged_agents/directories together cover all 7 task statements - Domain 2 (Tool Design) is well covered by the
tool_use/directory — especiallytool_choice.ipynbandprogrammatic_tool_calling_ptc.ipynb - Domain 3 (Claude Code Config) is best studied by examining the repo’s own
.claude/directory structure rather than running notebooks - The
misc/batch_processing.ipynbnotebook is essential for Task 4.5 (batch strategies) — one of the most concrete exam topics - Domain 5 (Context & Reliability) content is spread across
misc/(caching, compaction) and the Agent SDK (observability, SRE patterns)
Related
- CCA-F Official Exam Guide
- CCA-F Technical Reference
- CCA-F Practice Exam (60 Questions)
- The Architect’s Playbook
- CCA-F Study Guide
- CCA-F Practice Questions by Domain
- The Complete Guide to Building Skills for Claude
- Claude Code Subagents
- Essential MCP Servers for 2026
- Cookbook — Multi-Agent Research Pattern (Lead + Subagent + Citations Prompts)
- Cookbook — Chief of Staff Agent (SDK Coordinator Template)
- Cookbook — Managed Agents Multi-Agent Outcomes
- Cookbook — Giving Claude a Zoom Tool for Fine Image Detail — the
multimodal/crop_tool.ipynbdeep-dive; visual-token budgeting, 1:1 pixel-coordinate mapping, and the Chartography benchmark.
2026-05-23 batch refresh
Recompiled against the local raw/claude-cookbooks-main/ tree dump. Two new deep-dive articles split out from this overview to capture reusable artifacts the table-of-notebooks doesn’t carry full detail on:
- anthropic-cookbook-research-agent-prompts — distills the three-role multi-agent research pattern (lead + parallel subagents + citations agent) shipped in
patterns/agents/prompts/. Load-bearing rules: lead’s depth-first/breadth-first/straightforward classifier, subagent’s 5-15-tool-call OODA budget withweb_fetch-after-web_searchmandate, citations agent’s whitespace-exact no-rewrite contract. - anthropic-cookbook-chief-of-staff-agent — documents the Claude Agent SDK coordinator template (TechStart SaaS):
CLAUDE.mdbusiness state + two domain subagents (financial-analyst + recruiter) + three commands (/budget-impact,/strategic-brief,/talent-scan) + two output styles (executive, technical). Re-use checklist for swapping in a different 2-domain coordinator.
The rest of the 2026-05-23 raw dump (.claude/agents/, .claude/commands/, .github/, capabilities/*/README.md, managed_agents/example_data/*, skills/custom_skills/*, third_party/*) is recorded in .manifest.json but stays linked through the tables above rather than each getting its own article — most are README pointers or sample data, not new technique surface.
2026-05-24 infra refresh — Workload Identity Federation for claude-code-action
Source: raw/anthropic-watch-anthropic-cookbook-commit-3c30b020594de29a7f24ee579c511ac3ac45fb6a.md (commit 3c30b020, PR #662, author zenexer-ant, merged 2026-05-24T21:44:59Z).
Anthropic migrated the cookbook repo’s six claude-code-action-invoking workflows from the static ANTHROPIC_API_KEY repo secret to Workload Identity Federation — the GitHub Actions job exchanges its OIDC token for a short-lived access token at run time. The federation rule is repository_id-pinned, so the trust scope is the specific repository, not the whole GitHub org. Reusable pattern for anyone running claude-code-action in their own repos:
- Drop the long-lived
ANTHROPIC_API_KEYsecret. The static-secret model leaks if the repo is compromised or the secret is shared with a contributor; WIF tokens are scoped to one job run. - Add
permissions: id-token: writeto every workflow that invokesclaude-code-action(all six in the cookbook repo lacked it pre-migration). This is the GitHub side of the OIDC handshake. - Pin
claude-code-actionto v1.0.132 or later. The WIF inputs landed in v1.0.130;@v1is a moving tag and silently rolls forward. anthropic_workspace_idis optional. Anthropic’s default workspace already matches the federation rule for org-default cases. Provide it explicitly only when targeting a non-default workspace.- Two notebook-execution steps still on static keys.
notebook-quality.ymlandnotebook-tests.ymlpassANTHROPIC_API_KEYas an env var intonbconvert/pytest— those need a separate inline OIDC exchange (TODO comments in the commit). Both gracefully degrade when the secret is absent (notebook-testshas an explicit skip-guard;notebook-qualitycatches per-notebook failures), so the partial migration doesn’t break the repo while the inline-OIDC pattern is being worked out.
Operator takeaway. If you’re using claude-code-action in your own repo with a stored API key, this commit is the reference template for moving off it. Read the diff alongside Anthropic’s WIF docs to wire the federation rule on your side (one-time setup per repo). Doesn’t apply to notebook execution paths yet — keep those on managed secrets until Anthropic publishes the inline-OIDC pattern.
2026-07-03 evals refresh — agentic-search benchmark harness
Source: PR #749 (8231472d, Mengting Li / mengtingli-ant, Anthropic, merged 2026-06-30) — the repo’s first evals/ top-level directory, added the same day as the anthropic-cookbook → claude-cookbooks rename.
What it adds: evals/agentic_search/reproduce_agentic_search_benchmarks.ipynb (788 lines) + evals/agentic_search/utils/agentic_search.py (246 lines) — a reference-grade Messages-API harness that reproduces Claude’s DeepSearchQA and BrowseComp agentic-search benchmark scores. As of 2026-07-02 this is still the only notebook in evals/.
Architecture:
- Programmatic tool calling (PTC). Only
code_executionis directly callable;web_search/web_fetchare markedallowed_callers: ["code_execution_20260521"]withresponse_inclusion: "excluded"— Claude writes Python that calls search/fetch from inside the sandbox, and only printed summaries return to the conversation. Keeps context clean on questions needing 50+ fetches. Builds on programmatic_tool_calling_ptc.ipynb` (already in the Domain 2 table above). - Four request-level config params:
thinking: {"type": "adaptive"};output_config.effort: "max";output_config.task_budget= 3,000,000 cumulative output tokens (paces the agent across turns/compactions);context_managementwith acompact_20260112edit triggered at 200K input tokens. Builds ontool_use/automatic-context-compaction.ipynb(Domain 2/5 table above). - The single biggest lever: custom compaction
instructionsthat force the post-compaction summary to restate the original question verbatim (inside<original_question>tags) plus the<result>-tag output format. Without this, a compacted agent forgets what it was asked and often scores zero by asking the user to restate the question. - Round-trip loop. Server-side tools mean one API call can run many tool iterations internally, returning
stop_reason="pause_turn"as a checkpoint; the client appends content and calls again untilend_turn. Uses streaming,cache_control: ephemeralprompt caching across turns, a persistedcode_executioncontainer id, and atruncate_to_last_compaction()helper (resending pre-compaction history the server already discarded risks the 32MB request-body limit). - Two graders. DeepSearchQA-style model-as-judge F1 (fixed grader model
claude-opus-4-6regardless of model under test, grades only the extracted<result>tag, precision/recall/F1 plus an excessive-answers penalty); BrowseComp-style single-letter judge (A=correct/B=wrong/C=abstain, accuracy = fraction “A”). Swapping benchmarks is “a dataset, a few config lines, and a grader” — the loop itself doesn’t change. - Real datasets: BrowseComp = 1,266 questions (Wei et al. 2025, OpenAI); DeepSearchQA = 900 questions (arXiv:2601.20975). The notebook’s 3 demo questions are illustrative only, not drawn from the real 900. Scaling guidance:
ThreadPoolExecutorat concurrency 50 → full DeepSearchQA-900 run in ~2 hours, “a few hundred dollars.”
Operator takeaway. This is the concrete recipe for reproducing (or adapting to your own eval set) the agentic-search numbers Anthropic cites in model announcements — useful as a template if you want a defensible, model-as-judge-graded benchmark for your own long-horizon search agent rather than relying on vibes. The compaction-instructions trick generalizes beyond search evals to any long-running agentic task that might compact mid-run.
2026-07-24 multimodal refresh — crop_tool.ipynb rewritten as a benchmarked zoom tool
Source: ai-research/anthropic-cookbook-crop-tool-zoom-2026-07-24.md (upstream multimodal/crop_tool.ipynb, fetched 2026-07-24), compared against the vault’s 2026-04-10 corpus copy. Upstream commit provenance (added same day from the ecosystem-watch feed): commit 6c63a145 — “Rewrite the crop-tool cookbook around a measured zoom tool”, cj-ant, 2026-07-23T17:31:03Z on branch cj-ant/crop-tool-zoom — merged as **PR 793 in 85016cac (2026-07-23T17:32:40Z). raw/anthropic-watch-anthropic-cookbook-commit-6c63a145b7136a610092dbd2c3ef412b055e003b.md, raw/anthropic-watch-anthropic-cookbook-commit-85016cacf5b7923aa62aa2b514399325e9d159e9.md. The commit message confirms the rewrite inventory below in Anthropic’s own words, so it is no longer inferred from the diff — and dates the rewrite to 2026-07-23, one day before the fetch.
The notebook the tables above inherited from the April tree dump has been substantially rewritten, and the rewrite changes the correctness of the pattern rather than just its presentation:
- April (22 cells): “Giving Claude a Crop Tool for Better Image Analysis” — a hand-rolled loop around a simple crop, framed as a useful trick.
- Now (24 cells): “Giving Claude a Zoom Tool for Reading Fine Image Detail” — the same idea plus a measured result on Surge AI’s Chartography benchmark (
claude-fable-529% → 73%,claude-sonnet-513% → 44%), theresized_size()pre-resize discipline that makes Claude’s pixel coordinates map 1:1 onto the image you hold,tool_runner+pause_turnhandling, and the production notes (JPEG crops against the 32 MB request limit,subsampling=0, transparency compositing).
Split out as its own deep-dive — Cookbook — Giving Claude a Zoom Tool for Fine Image Detail — following the same pattern as the 2026-05-23 research-agent and chief-of-staff splits, since the reusable artifact (a self-contained tool cell plus a benchmark) is more than a table row carries.
Corpus-drift note. This is the first confirmed case of a raw/claude-cookbooks-main/ notebook diverging materially from upstream since the April dump. The corpus tree is a point-in-time snapshot, not a live mirror — treat any notebook-level claim sourced only from it as dated April 2026 unless re-fetched.
2026-07-22 managed_agents refresh — subagent live-streaming cookbook
Sources: raw/anthropic-watch-anthropic-cookbook-commit-c39be3a2e64d2cff678045233d7c56065b94f93e.md (commit c39be3a2, cj-ant, 2026-07-22T15:00:32Z) + raw/anthropic-watch-anthropic-cookbook-commit-995c3c880a6e0cf7a2e137ac6a373d53c87a9c8a.md (**PR 792, branch cj-ant/watch-subagents-live, merged 2026-07-22T18:00:42Z).
A new managed_agents/ notebook that streams a coordinator and its subagents in real time. It is the reference implementation for the Managed Agents July launch wave — exercising per-thread event deltas, initial_events on session create, per-agent model effort, and versionless agent updates in one worked example. Ships with a registry entry, an authors entry, and a README row. Full feature semantics (including the “effort in a per-session override is silently ignored” trap) are documented at Managed Agents § July launch wave; SDK floor is Python v0.118.0 / TS sdk-v0.113.0 (SDK Releases).
Adds to the Managed Agents cookbook list in the Domain 1 section above.
2026-07-23 partner cookbook — Fraud Review Agent with MongoDB Atlas
Sources: raw/anthropic-watch-anthropic-cookbook-commit-849918c65cdea068c144b481027dd18bcedb2c2c.md (commit 849918c6, author mohammaddaoudfarooqi, 2026-07-23T04:37:01Z), raw/anthropic-watch-anthropic-cookbook-commit-1f932a8c7c74b1e2d40041e684a5eedf2cb5474c.md (review-fix commit, same author/timestamp), raw/anthropic-watch-anthropic-cookbook-commit-90b3ebd6791cd3d2334b334061875d3dcea10dcc.md (**PR 759 from mongodb-partners/cma_with_mongodb, merged by cj-ant 2026-07-23T13:39:40Z).
The first third-party partner-contributed Managed Agents cookbook the vault has recorded.^[inferred — no earlier partner-authored managed_agents/ cookbook appears in prior wiki coverage] A Fraud Review Agent built on Managed Agents with MongoDB Atlas as the data layer, contributed from the mongodb-partners org rather than by Anthropic staff, and merged by an Anthropic maintainer.
- Why it matters structurally: the
managed_agents/directory has been Anthropic-authored to date (CMA_orchestrate_issue_to_pr,CMA_iterate_fix_failing_tests,CMA_gate_human_in_the_loop,CMA_operate_in_production,CMA_explore_unfamiliar_codebase, plus theroadtrip_plannerand subagent-streaming additions). A partner-org PR landing in the same directory suggests the cookbook repo is becoming an integration-showcase surface, not only a first-party teaching repo. - The review pass is the useful part for contributors. Follow-up commit
1f932a8c— “fix(managed_agents): address review — Anthropic auth, Atlas setup link, rename outcome var” — names the three things Anthropic’s review asked a partner contribution to fix: auth handled the Anthropic-idiomatic way, a linked Atlas setup path rather than assumed setup, and anoutcomevariable rename (the Outcomes API surface has naming conventions worth matching). A reasonable checklist if you plan to submit an integration cookbook. - Not yet read at the notebook level. The ecosystem-watch stubs carry commit titles only — no cell content, no schema, no cost figures. See Open Questions.
Try It
- Clone the repo:
git clone https://github.com/anthropics/anthropic-cookbook.gitand set up your API key - Run
customer_service_agent.ipynbfirst — it is the single most exam-relevant notebook, covering the agentic loop, tool use, and conversation management in one example - Modify the examples — after running each notebook, change something (add a tool, modify the schema, break something intentionally) to see what happens
- Build your own cookbook — create a notebook that combines patterns from at least 3 different cookbooks into one integrated system
- Use the cookbooks as flashcards — for each notebook, write down which exam task statement it maps to without looking at this article
Open Questions
- Fraud Review Agent notebook contents unread. PR #759 is recorded from commit titles only (
anthropic-ecosystem-watchstubs). Unknown: the notebook filename and path, which Managed Agents primitives it uses (Outcomes is implied by the “rename outcome var” review fix, but not confirmed), how MongoDB Atlas is reached (vault credential? MCP server? direct driver in the sandbox?), and whether it carries cost or accuracy figures. Needs a direct fetch of the notebook. - Subagent live-streaming notebook contents unread. Same limitation — PR #792 is known from its commit message, not its cells. The feature list is confirmed; the code is not.
- Is the Fraud Review Agent really the first partner-contributed cookbook? Marked
^[inferred]above — established from the absence of prior partner-authoredmanaged_agents/cookbooks in wiki coverage, not from a repo-wide contributor audit.