Browse the reference ⌄
Decision Guide published

Choose and Contract Claude Deployment Routes

Decide, per use-case class, which route carries Claude into production (Anthropic API, Claude Platform on AWS, Bedrock, Google Cloud, Microsoft Foundry, plus the Microsoft 365 Copilot surface); record who operates, bills and processes; size the diligence to the processor; check residency, zero data retention and HIPAA per feature; sign a contracting matrix row; and run Agent SDK or hosted agents with the controls the product does not supply. Provider-specific and dated.

Version
0.1.0
Owner
DEIXEI
Last reviewed
Reading time
50 min

For Cto · Ai Architect · Platform Engineer · Security Engineer · Procurement · Dpo · Risk And Assurance · Internal Audit

Sources and details
Source works
Book 3 · Research Series
Source chapters
4, 7, 9, 10
Source appendices
04:A, 04:C, 04:D, 04:H, 04:I, 04:J
Refresh trigger
vendor release

Full source list ↓ Source index →

There is no single answer to “how do we run Claude?”. There are several commercial routes to the same model family, and each one assigns the operator, billing, data-processor and contracting roles differently. Each also offers a different residency posture, feature set and retention arrangement. Book 3 Ch 4 puts the decision in one line: choose a route per class of workload, not per institution. Most regulated firms will end up running two or three routes. This page turns that decision into a sequence you can follow, a matrix row both procurement and the second line can sign, and the run-time controls an embedded Claude agent needs whichever route carries it.

This page is provider-specific and dated. Every product statement carries its date. Three dates recur:

  • Book 3 state (May to August 2026). Appendix A was drafted on 14 May 2026, and its Foundry entries were revised on 3 August 2026 after Foundry went GA on 29 June 2026. Chapters 4 and 9 are dated 3 August 2026.
  • Research Paper 3 state (10 November 2026). Claude Code route facts checked against vendor documentation.
  • Vendor documentation read for this page (15 November 2026). Anthropic’s pages on API data retention, data residency, Foundry, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), and Agent SDK hosting, session storage and permissions. Wherever these pages contradict the books, this page reports both and follows the vendor text, flagged as a correction.

Anything not checked against vendor documentation carries a [FACT-CHECK: …] marker. Documentation is not the contract: the signed order form, DPA and addenda govern. Bank A and Asset Manager X are composite institutions from Book 3, not real firms. Statements about what DORA, GDPR, the Swiss FADP or the EU AI Act require, and every regulatory date, are on the regulatory map and the regulatory calendar. This page gives design consequences only. It is not legal advice.

Decisions this page supports

DecisionDecided byRecorded inSection
Which route serves each use-case classHead of platform with lead architect; co-signed by procurement and second lineContracting matrix rowDecision sequence
Who is the data processor, and therefore whose diligenceProcurement lead with legal and second lineContracting matrix block 2; Register of Information rowWho operates, bills and processes
Whether the route meets the class’s residency ruleDPO with data officeMatrix block 3; transfer recordResidency
Which API features an agent may use without leaving ZDR or HIPAA coverWrangler with privacy officeAgent envelope (Means, Memory); ZDR configuration recordZDR and HIPAA
Whether a hosted agent service is an outsourcing arrangementThird-party risk owner with second lineOutsourcing register; matrixHosted agents
How a self-hosted SDK agent is isolated, bounded and evidencedPlatform engineering owner of the SDK runtime; SOCRuntime profile; detection rulesAgent SDK
When a route decision is reopenedRoute-portfolio ownerRoute-decision register; quarterly minutesQuarterly review

The owners are drawn from Book 3 Ch 4 PR-2 (responsible roles) and Ch 9 PR-1. Align them with your own RACI.

Treat the route as a portfolio decision

Book 3 Ch 4 §5 names four factors. No route is best on all four.

FactorThe questionWhat moves it
Data residencyWhere is the prompt processed, and where is data stored at rest?The route’s inference-location and storage-location controls (two separate settings on most routes)
Contractual postureWho is the data processor, and is that processor a designated critical ICT third-party provider (CTPP)?The route’s operator, not its biller
Region and model availabilityDoes this route serve the model version you need in the location you need, today?Per-route model catalogues and regional endpoints; aliases resolve differently per route
Feature parityAre the features the workload depends on (Files, Batch, Agent Skills, Compliance API, MCP connector, code execution) available on this route and this hosting option?Per-route and per-hosting-option exclusion lists

Three rules follow (Book 3 Ch 4 §3, §8):

  1. One matrix row per use-case class. “Engineering productivity”, “employee assistance” and “regulated workflow agents” are separate rows, and they can land on separate routes.
  2. The row expires. Re-derive block 2 (processor, biller, DPA) from current vendor text at every quarterly review, at every model release and at every vendor terms change. Do not copy it forward. In the Bank A composite, Foundry’s GA statement moved the processor from Microsoft to Anthropic. The route on two rows stayed the same, but their TPRM target, DPA reference and register entry all changed (Ch 4 §6).
  3. Pin model versions on every route. Use exact deployment, inference-profile or model IDs in configuration under change control. An alias is a laptop convenience, not a production control (Ch 4 §5; see model gateway: pin models).

Book 3’s reference architecture is Azure-first. It uses Foundry plus the direct Anthropic API behind an Azure API Management gateway, with Bedrock as the route for the residency-strict slice (Ch 4 §3, §8). AWS-first firms swap in Bedrock plus the direct API behind Amazon API Gateway. GCP-first firms swap in Google Cloud plus the direct API behind Apigee (Ch 4 §4.8). The method is the same in all three. That is the author’s position for an Azure estate, not a market finding.

Record who operates, bills and processes

The most expensive mistake in Book 3 Ch 4 §7 is to assume that the marketplace you buy through is the processor of your data. The table below separates the four roles. It combines Book 3 Appendix A §2 (Foundry column revised 3 August 2026) with the vendor documentation read on 15 November 2026.

RouteOperator of inferenceBillerData processorContracting entity (EU customers, per App A)
Anthropic API (api.anthropic.com)AnthropicAnthropicAnthropic PBCAnthropic PBC, San Francisco; no EU establishment named
Claude Platform on AWSAnthropic, on Anthropic-managed infrastructureAWS Marketplace (Claude Consumption Units, billed in arrears on the AWS bill)Anthropic for inference inputs and outputs; AWS processes billing and identity metadata (vendor docs, 15 Nov 2026)AWS Marketplace terms layered over Anthropic Commercial Terms and DPA: two layers
Amazon BedrockAWSAWSAWS (App A: AWS EMEA SARL)AWS EMEA SARL, Luxembourg; no separate Anthropic agreement
Claude on Google Cloud, Google managed (Google Cloud’s Agent Platform, formerly Vertex AI; Ch 4 §4.5, Paper 3 §4.3)GoogleGoogleGoogle (App A: Google Ireland Ltd)Google Ireland Ltd
Claude Models on Google Cloud, Anthropic managed (not in Book 3)AnthropicGoogle Cloud MarketplaceAnthropic; some supporting services, including Anthropic’s trust and safety systems, process data outside Google Cloud (vendor docs, 15 Nov 2026)[FACT-CHECK: contracting layers for the Anthropic-managed Google Cloud offering]
Microsoft FoundryAnthropic, on Azure infrastructure (“hosted on Azure”) or on Anthropic infrastructure (“hosted on Anthropic”)Microsoft (Azure Marketplace; CCUs on the Azure bill)Anthropic: Anthropic’s Foundry documentation says it “acts as an independent processor for Microsoft” (15 Nov 2026)Microsoft (App A: Microsoft Ireland Operations Ltd under MOSPA). MOSPA covers the commercial wrapper only, not the Anthropic processing leg
Microsoft 365 Copilot (Anthropic models): arrives through an admin toggle, not procurementAnthropicMicrosoft (M365 licensing)Anthropic listed as a Microsoft sub-processor for select Copilot experiences (App A §3.2 sidebar, verified by the author 14 May 2026)Microsoft 365 terms, not Foundry terms

Read the table with these points in mind:

  • On four of the seven rows, the biller is not the processor. On Claude Platform on AWS, the Anthropic-managed Google offering and Foundry, a cloud provider bills and authenticates while Anthropic processes. Book 3 Ch 4 §7 gives the test. If your TPRM register names only the cloud provider for one of these routes, or the DPA column says “MOSPA” on a Foundry row, the row is wrong. Re-derive the processor from the vendor’s current published text. Do not take it from the invoice, the login screen or last quarter’s diagram.
  • Foundry hosting option is a per-deployment choice, and it changes the data path. For “hosted on Azure”, Anthropic’s documentation says prompts and completions stay within Azure, and only usage metadata and content flagged by Anthropic’s safety systems leave for Anthropic. “Hosted on Anthropic” runs on Anthropic infrastructure outside Azure (vendor docs, 15 Nov 2026; consistent with Research Paper 3 §4.1). In both cases Anthropic is the processor. Record the hosting option on the matrix row.
  • Claude Platform on AWS and the Anthropic-managed Google offering each provision a new Anthropic organisation. It is separate from any existing Anthropic or Claude Enterprise organisation. Keys, workspaces, console settings and ZDR enablement do not carry over (vendor docs, 15 Nov 2026; Ch 4 §4.4). Add each organisation to the identity inventory and the access review.
  • Draw the data-flow diagram for every route with the second line, the DPO and TPRM in one workshop. Date it and include it in the next supervisory pack (Ch 4 §7).

Source difference: who processes on Foundry

The books disagree, and this page follows the newer sources.

SourceSays the Foundry processor is
Book 3 App A (revised 3 Aug 2026), Ch 4 §4.2 and §7Anthropic, per the GA statement of 29 June 2026, not qualified by hosting option
Book 3 App H §3.2 (per-route summary and second observation)Treats Foundry as “cloud-processed”, with Anthropic as a sub-processor under MOSPA and a Microsoft CTPP lead-overseer relationship
Book 3 Glossary (“Azure AI Foundry”) and Ch 10 §5.2Microsoft is the data processor, or the cloud provider is processor (preview-era wording)
Research Paper 3 §4.1 (10 Nov 2026)Anthropic is the seller and operator and acts as an independent data processor on both hosting options
Anthropic Foundry and data-retention documentation (15 Nov 2026)Anthropic is the data processor; “independent processor for Microsoft”

This page follows App A, Ch 4, Paper 3 and the vendor text: Anthropic is the processor on Foundry. App H’s Foundry row and the Glossary entry predate the GA revision. Do not use them to fill block 2 of the matrix. Apply the same check to exit sequencing: on Foundry, exit planning has to cover the Anthropic processing relationship as well as the Microsoft commercial one.

Size the diligence to the processor

Per Book 3 App A §1 and App I §3, Anthropic was not on the ESAs’ list of designated CTPPs, while AWS, Microsoft Azure and Google Cloud were. The list date, the relevant DORA articles and any later designation round are on the regulatory map and regulatory calendar. [FACT-CHECK: re-confirm Anthropic’s designation status against the current ESAs CTPP list before relying on this row.]

For the institution, the design consequence is that the diligence load follows the processor, not the biller:

RouteProcessor is a designated CTPP?What third-party risk must do
Anthropic APINoThe full third-party diligence, register entry, contractual-clause check and exit strategy for Anthropic is the institution’s own work. No lead-overseer output exists to rely on (App I §3)
Claude Platform on AWSNo for the processing layer. AWS’s designation covers the Marketplace procurement layer only (App H §3.2)As for the Anthropic API. Draw the AWS/Anthropic split explicitly in the Register of Information
Anthropic-managed Google CloudNo (Anthropic)As for the Anthropic API [FACT-CHECK: how this offering is papered]
Microsoft FoundryNo. The processor is Anthropic, even though Microsoft is designated (App A §3.2)As for the Anthropic API, plus the Microsoft wrapper. Bank A’s July re-run added a second Anthropic row to the register and re-ran second-line sign-off for the two Foundry rows (Ch 4 §6, composite)
BedrockYes (AWS)Existing AWS TPRM workstream and register entry extend to the route; the designated-provider regime applies
Google-managed Google CloudYes (Google)Existing Google TPRM workstream extends
M365 Copilot (Anthropic)Anthropic as a Microsoft sub-processorA separate register row and owner from Foundry (App A §3.2 sidebar). See the Copilot surface

Three supporting facts belong in the TPRM file:

  • Mandatory contract clauses apply on any route that supports a critical or important function (CIF), whatever the CTPP status (Ch 4 §5). The CIF flag is decided at intake and kept separate from the risk tier (App I §3). Article references are on the regulatory map.
  • Sub-processor notice differs by route. Anthropic publishes its sub-processor changes at trust.anthropic.com/updates with 15 days’ notice. The AWS list carries 30 days’ notice (App A §5). [FACT-CHECK: current notice periods in the executed DPAs.] Subscribe the TPRM mailbox to each list the matrix depends on.
  • WorkOS is a sub-processor on the Anthropic SSO path. Console and Claude Enterprise SAML SSO is brokered through WorkOS, so IdP metadata and certificate exchange pass through it rather than going directly between your IdP and Anthropic (App A §3.1; Glossary). Record WorkOS in the sub-processor register for the Anthropic API and Claude Platform on AWS rows. An Anthropic exit ends the WorkOS relationship without touching your own IdP (App H §3.2). [FACT-CHECK: whether WorkOS still mediates SSO, and for which plans.]

Exit cleavage points (contracting entity, notice, termination for cause, data return, sub-processor exit, suspension versus termination, CTPP implication, register-row implication) are covered in vendor concentration and exit.

Check residency route by route

Residency has two independent parts: where inference runs and where data is stored at rest (vendor docs, data residency, 15 Nov 2026; Paper 9 §6.2). Record both per deployment.

RouteBook 3 state (App A §2, Ch 4 §4; May–Aug 2026)Vendor documentation, 15 Nov 2026Consequence
Anthropic APIWorkspace us only; inference us or global; no EU geoSame. inference_geo accepts only "global" (default) and "us"; workspace geo is "us" only and cannot be changed after creation. Workspace settings allowed_inference_geos and default_inference_geo restrict and default the geoNo EU inference or storage. The EU-to-US transfer happens on every call and is carried by transfer instruments, not avoided
Claude Platform on AWSIn-region EU inference in Dublin, London, Frankfurt, Milan, Zurich, Paris and StockholmCorrection. A workspace is bound to one AWS region, but that region “does not pin where model inference runs”. Inference geos are US or Global only. Workspace geo is not configurable. Workspaces created before 18 September 2026 may have requests processed and data stored outside AWSDo not treat this route as an EU-resident route. The App A §4 step 3 outcome no longer holds (see the decision sequence)
Anthropic-managed Google CloudNot coveredEvery workspace allows all inference geos and defaults to global; workspace geo us; set inference_geo: "us" per request for US-onlyNo EU inference or storage
Microsoft FoundryUS data zone only at GA; no EU data zoneGlobal Standard and US Data Zone Standard. The data zone is available only on the “hosted on Azure” option; inference_geo does not applyNo EU data zone. Paper 3 §4.1 notes data at rest stays in the chosen Azure geography while processing is global. Whether that satisfies your classification rules is your decision
BedrockIn-region inference in eu-central-1, eu-west-1, eu-south-1, eu-north-1; AWS processorAnthropic documents that on Bedrock the inference region is set by the endpoint or inference profile; Paper 3 §4.3 records eu.-prefixed cross-region profilesThe cleanest EU in-region option in the sources [FACT-CHECK: Claude model availability per EU region and the EU cross-region profile scope, from AWS documentation]
Google-managed Google Cloudeurope-west1 and the eu multi-regionInference region set by endpoint URL (vendor docs)EU in-region available [FACT-CHECK: per-model availability on europe-west1 and eu; a 404 usually means the model is served only on global or a multi-region (Ch 4 §4.5)]

Regional premiums. As of 15 November 2026, US-only inference (inference_geo: "us") costs 1.1 times the standard rate for Claude 4.6 and later models. This applies on the Anthropic API, Claude Platform on AWS and the Anthropic-managed Google offering, and the same multiplier applies to Foundry’s US Data Zone deployments (vendor docs). Book 3 reports a 10% premium on Bedrock regional endpoints over global (from Claude 4.5) and on Google’s europe-west1 or eu locations (App A §2) [FACT-CHECK: current Bedrock and Google regional pricing]. Put the premium in the matrix row so finance sees the cost of residency rather than discovering it.

Treat the absence of an EU sovereign offering as a design constraint, not a dependency. Book 3 Ch 4 §4.7 compares the US government package (a named authorisation level, a written inference boundary, direct contracting) with the lack of any EU equivalent as of July 2026. The author’s advice is to design around the gap rather than put “awaiting EU sovereignty” on a roadmap as though it had a date. The author also notes that billing follows the assurance boundary. Where a route’s billing is most convenient, ask what assurance was traded away to get it. [FACT-CHECK: whether Anthropic has since published an EU sovereign or EU-resident offering.]

Record the transfer basis for every Anthropic-processed route

Zero data retention reduces copies. It does not legitimise a transfer (Ch 10 §5.2). Each Anthropic-processed row needs a transfer record, co-owned by the DPO and the procurement lead (App I §6.1):

  1. Check DPF certification. Verify Anthropic’s EU–US Data Privacy Framework status on the official DPF list, and re-verify at least annually. Track the status of legal challenges to the DPF (App I §6.1; Ch 10 §5.2).
  2. Fallback: SCCs plus a TIA. Where the DPF is unavailable or not relied on, use Standard Contractual Clauses Module 2 (controller to processor), which the Anthropic DPA carries with UK and Swiss adapters (App A §3.1), plus a documented Transfer Impact Assessment on file. Book 3’s composite firms run SCCs plus a TIA on every direct-API row (Ch 4 §6; Ch 9 §8).
  3. Swiss entities. Verify Anthropic’s Swiss–US DPF status and record it separately (App I §6.1).
  4. Record per row: mechanism relied on, verification date, TIA reference, owner and next check date.

The legal instruments, their dates and their litigation status are on the regulatory map. The data classes and lanes page decides which classes may take a cross-border lane at all.

Check zero data retention and HIPAA per feature, not per route

“ZDR applies” is a claim about one organisation, one route and one set of features. It is never a claim about a vendor (data classes: ZDR as recorded configuration).

ZDR by route (vendor docs, 15 Nov 2026)

RouteZDR
Anthropic APIAvailable on request, enabled per organisation by the account team. Enablement does not extend to other organisations under the same account. ZDR organisations cannot call the API from a browser (CORS requests are rejected)
Claude CodeClaude Code with Commercial-organisation API keys is covered by the API arrangement. Claude Code on Claude Enterprise has a separate ZDR offering for qualified accounts. If Claude Code metrics logging is on, productivity data is exempt from ZDR
Claude Platform on AWSAvailable on request; otherwise the first-party retention policy applies
Anthropic-managed Google CloudAvailable on request. A ZDR arrangement on another Anthropic organisation does not carry over
Foundry, Bedrock, Google-managed Google CloudAnthropic’s ZDR does not carry. The cloud provider’s retention terms and settings govern (Ch 10 §5.2; App A §3). Paper 3 §4.1 found no ZDR option for Foundry on the Microsoft pages

Features that leave ZDR

Book 3 (Ch 4 §4.1, Ch 10 §5.1, Glossary) lists the surfaces outside ZDR as Console, Workbench, Managed Agents, the Files API, the Batch API, Code Execution, Agent Skills, the MCP connector and Claude for Excel. Anthropic’s eligibility table on 15 November 2026 confirms that list and makes it more precise:

Not ZDR-eligible (vendor table, 15 Nov 2026)Endpoint or parameterRetention note from the table
Files API/v1/filesRetained until deleted or until a configured expiration
Batch processing/v1/messages/batches29-day retention
MCP connector/v1/messages with mcp_serversStandard policy
MCP tunnels (research preview)/v1/tunnelsNot eligible
Code execution tool, and programmatic tool calling built on it/v1/messages with code_executionContainer data up to 30 days
Agent Skills/v1/skills, /v1/messages with skillsStandard policy
Message threads/v1/messages with threadNot eligible
Claude Managed Agents/v1/agents, /v1/sessions, /v1/environmentsNot eligible except self-hosted Managed Agents
User profiles/v1/user_profilesNot eligible
Console (incl. playground), Claude for Excel, Teams/Enterprise product interfaces (apart from the separate Claude Code offering)—Not covered

Four further rules from the vendor page:

  • Using a non-eligible feature is not blocked under ZDR. The API accepts the call, and the feature’s own retention applies to that data. Only HIPAA readiness blocks non-eligible features, with a 400; the exception is client-side tools the table marks as not blocked, which are accepted but stay outside HIPAA cover. Under ZDR the control therefore has to sit with you, at the gateway and in the envelope.
  • Certain model families require 30-day retention. Anthropic calls them “Covered Models”, and they are not available under ZDR unless Anthropic expressly authorises it. Book 3 Ch 10 §5.1 makes the same point about one model. The retention posture limits model choice, so put it in the envelope.
  • Flagged content and legal holds. Even under ZDR, Anthropic may retain data where the law requires it, and may keep inputs and outputs of flagged sessions for up to two years. Name both in the DPIA and the records schedule (Ch 10 §5.1).
  • Book 3’s “computer use” note has aged. Ch 9 §4.2 calls computer use a beta capability that is not HIPAA-eligible. The 15 November 2026 table lists the computer-use tool as ZDR-eligible and HIPAA-eligible because it is a client-side tool. Book 3’s operational advice still stands: VM isolation, snapshot rollback, and admission only after an Agent Control Board review.

Controls that make ZDR checkable

ControlWhereOwner
The gateway refuses non-eligible features on ZDR-dependent routes. It strips or blocks mcp_servers, /v1/files, /v1/messages/batches, code_execution, skills and thread on requests whose envelope states a ZDR postureModel gatewayPlatform
Envelope flag. persistent_storage: files_api_on is a deliberate non-ZDR choice. The registry flags the envelope for second-line review and records the posture (App D §2.3). Do the same for a Batch or MCP-connector dependencyBounded agentWrangler; second line
Pin the authenticated organisation. Coverage follows the organisation, not the device, so set forceLoginMethod and forceLoginOrgUUID on workstations (Ch 10 §5.1; Paper 3 §4.2)Coding-agent workstationEndpoint engineering
ZDR configuration record per deployment: route, organisation ID, enablement evidence, surfaces in and out, carve-outs, verification test, last verified dateData classes and lanesPrivacy office

The MCP connector: wire format only, broker decides

The Messages API mcp_servers parameter lets an embedded agent bind MCP tools directly. That has two consequences (Ch 7 §4.1; Ch 9 §4.3; App C §5 item 17):

  1. It takes the call out of ZDR. The vendor table (15 Nov 2026) confirms this. A ZDR-dependent workload either routes tool calls through the SDK’s own loop to registered servers, or records the exception in the envelope and the MCP register entry.
  2. It must not become a parallel tool surface. Embedded agents may name only servers from the connector broker’s signed manifest of approved servers. The runtime reads that manifest at instantiation, just as Claude Code reads managed-mcp.json, and refuses any server that is not also on the envelope’s Means list. The mcp_servers parameter is the wire format. The MCP and connector broker is the authority.

MCP parity differs by route. Book 3 Ch 7 §4.1 (verified May 2026) reports: same-day parity on Claude Platform on AWS; Bedrock lagging beta features by about one release; Vertex with MCP tool search off by default; and Foundry carrying MCP through a separate Foundry MCP Server in public preview. Claude Platform on AWS now reaches public-internet MCP servers only, because MCP tunnels are not supported there (vendor docs, 15 Nov 2026). [FACT-CHECK: current MCP support per route.]

HIPAA by route

Book 3 states that HIPAA-ready cover is available only on the direct Anthropic API (App A §2; Ch 4 §4.1; Glossary). The vendor documentation of 15 November 2026 differs:

  • Claude API: HIPAA readiness with a signed BAA and a HIPAA-enabled organisation, for eligible features only. Once enabled it is permanent, enforced per organisation, and the API returns 400 for non-eligible features. Run HIPAA and general-purpose work in separate organisations.
  • Foundry: eligible on both hosting options, with a BAA with Anthropic plus the HIPAA configuration enabled on the Azure subscription.
  • Claude Platform on AWS: not available. The AWS-specific page points HIPAA, FedRAMP High, IL4 and IL5 workloads to Bedrock.
  • Bedrock and Google-managed Google Cloud: outside Anthropic’s programme. Refer to the provider’s compliance documentation.
  • Claude Code: not covered by HIPAA readiness. This contradicts Ch 10 §5.2’s statement that a BAA extends to Claude Code where ZDR is active. Follow the vendor text and confirm in your BAA.

Walk the seven-step route decision

Book 3 App A §4 gives a walkable sequence: start at step 1 with the use case in hand, and the first fit is the recommendation. Below is the sequence with each output recorded in the contracting matrix, annotated where the 15 November 2026 vendor documentation changes the outcome. The annotations are this page’s correction. They are not in the book.

  1. Classify the workload. Record its AI Act class (prohibited / high-risk under Annex III / transparency / minimal), CIF yes or no, data class (the book’s Tier 0–4, or the C1–C4 classes on data classes and lanes), and personal and special-category data flags. If the use is prohibited, stop. Classification rules are on risk tiers and the regulatory map.
  2. Is in-EU inference mandatory? It is mandatory for high-risk workloads on EU residents, for CIFs, and wherever firm policy or the supervisor requires it (App A names BaFin, CSSF, FINMA, ACPR, DNB and CBI guidance as possible sources). Yes → step 3. No → step 5.
  3. Mandatory residency: which processor do you prefer?
    • Book 3: Anthropic as processor → Claude Platform on AWS in a named EU region, accepting no HIPAA and the full non-CTPP diligence.
    • Correction (15 Nov 2026): the vendor documentation offers only US or Global inference on Claude Platform on AWS and says the workspace region does not pin inference. No Anthropic-processed route currently offers EU in-region inference. If residency is mandatory, the answer is a cloud-processed route → step 4. Book 3 ties the Anthropic preference to Anthropic-native features (Compliance API, Activity Feed, ISO/IEC 42001 lineage, day-zero parity). If those features are essential, the workload has to be re-scoped, for example by tokenising so the residency rule no longer binds, or the residency requirement has to be formally relaxed by its owner. Neither is a route choice.
  4. Mandatory residency, cloud-processed route: which is your primary cloud?
    • AWS → Bedrock in an EU region. Accept: no Compliance API, no Agent Skills, no Claude for Excel (App A §3.3); WebSearch unavailable on Bedrock (Ch 4 §4.3; Paper 3 §4.3).
    • GCP → Google-managed Google Cloud on europe-west1 or eu. Accept the regional premium, no Compliance API, and verify each model on the chosen endpoint.
    • Azure → not Foundry for this workload. There is no EU data zone, and the processor is Anthropic, not Microsoft, so Foundry delivers neither residency nor a cloud-provider processor. Use Bedrock (Book 3’s choice), and defer Foundry for this class until an EU data zone is published. [FACT-CHECK: whether Foundry has since published an EU data zone.]
  5. Residency flexible: do you need MACC drawdown, with a residency-flexible workload (Book 3’s Tier 0–1, no customer personal data, no high-risk decisioning)?
    • Yes → Foundry. Record the processor as Anthropic, record the hosting option, use Entra ID, document the EU data-zone gap as a watch item with a named owner and a quarterly date. Vendor docs (15 Nov 2026) describe Foundry billing as CCUs through the Azure Marketplace. Paper 3 §4.1 says spend counts against a Microsoft Azure Consumption Commitment and that Cloud Solution Provider subscriptions are not supported. [FACT-CHECK: MACC eligibility in your current SOW.]
    • No → step 6.
  6. Does the workload process PHI that needs a BAA?
    • Book 3: yes → direct Anthropic API only.
    • Correction (15 Nov 2026): the Claude API or Foundry, each with an Anthropic BAA; or Bedrock under AWS’s own programme, per the Claude Platform on AWS page. Not Claude Platform on AWS. Not Claude Code. No → step 7.
  7. Does it depend on a feature available only on Anthropic-operated surfaces (Claude for Excel, Agent Skills, Compliance API, Activity Feed and similar)?
    • Yes, residency flexible → Anthropic API (or Claude Platform on AWS where AWS Marketplace procurement is preferred: vendor docs list Agent Skills, code execution, Batch, the Files API, the Compliance API and Managed Agents there, but no HIPAA). Workspace us; transfer record per the section above.
    • Yes, residency mandatory → Book 3 sends you back to step 3. After the correction there is no route that does both, so escalate the conflict to the use-case owner and the second line.
    • No → choose between the Anthropic API (fastest feature parity) and Foundry (MACC, Entra ID) on procurement preference. On Foundry, check the exclusion lists: no Admin API, Advisor tool, Managed Agents, Compliance API, Models API, Message Batches API, server-side fallback or user-profile endpoints. “Hosted on Azure” additionally excludes code execution, Agent Skills, programmatic tool calling, the Files API and newer web search/fetch tool versions, and returns 400 for them (vendor docs, 15 Nov 2026).

Output: one route per use-case class, written into the contracting matrix, signed by procurement and the second line. The same row feeds the Register of Information submission (App A §4).

The Azure-first shortcut (a second layer, not a replacement)

Book 3 Ch 4 PR-1 gives a shorter top-down tree for an Azure estate. Use it after the seven steps as a consistency check, not instead of them:

OrderIf…Book 3 routeNote as of 15 Nov 2026
1Tier 0–1, internal, no customer data, no CIF adjacencyFoundry with Entra ID (DefaultAzureCredential, Azure AI User or Cognitive Services User; the vendor page now names Foundry User or Cognitive Services User)Processor is Anthropic; EU data-zone gap is a watch item
2Depends on Anthropic-native featuresAnthropic API behind APIM; SCCs plus TIA; ZDR on the Messages APICheck each feature against the ZDR table above
3High-risk or CIF and in-region EU inference non-negotiableBedrock eu-central-1 or eu-west-1Add a “revisit when an EU commitment is published” trigger
4Anthropic as processor, EU residency, AWS Marketplace preferredClaude Platform on AWSDoes not hold for residency as of 15 Nov 2026 (see step 3)
5GCP primary, or the clearest documented EU region story neededGoogle-managed Google Cloud on europe-west1 or euVerify per model

Ch 9 PR-1 applies the same split to API agents. Tier 0–1 internal agents go to Foundry. Tier 2 and above needing Anthropic-native features go to the direct API behind APIM. Tier 3 and above with non-negotiable EU inference go to Bedrock. Book 3 reports this hybrid as where most peer banks have landed (Ch 9 §7). That is the author’s observation, not a survey.

Configure each route’s identity and client binding

Client and SDK configuration is where a route decision silently fails. The variable names below are from Book 3 App A §3 (May–Aug 2026) and Ch 4 PR-3, cross-checked where marked.

RouteClient routing and auth (Claude Code / Agent SDK)Grant neededTraps
Anthropic APIANTHROPIC_API_KEY (sent as X-Api-Key), ANTHROPIC_AUTH_TOKEN (bearer for a gateway), ANTHROPIC_BASE_URL (gateway endpoint)Workspace-scoped key held in the secret store or gateway named values; separate “Claude Code” and “Developer” console key rolesA Console organisation is separate from a claude.ai Team or Enterprise organisation; settings and audit in one do not reach the other (Paper 3 §4.2 rule 5)
BedrockCLAUDE_CODE_USE_BEDROCK=1, AWS_REGION=<EU region>, AWS credential chain (role, Identity Center, environment)bedrock:InvokeModel; Paper 3 §4.3 adds bedrock:InvokeModelWithResponseStream, bedrock:ListInferenceProfiles, bedrock:GetInferenceProfileModel access is enabled per account per region before first use; prompt caching may not be available in every region; Claude Code uses the Invoke API rather than Converse (Ch 4 §4.3)
Google-managed Google CloudCLAUDE_CODE_USE_VERTEX=1, ANTHROPIC_VERTEX_PROJECT_ID, CLOUD_ML_REGION=europe-west1 (or eu), ADC or a service accountaiplatform.endpoints.predict (App A); Paper 3 §4.3 names roles/aiplatform.userModel IDs are date-namespaced; not every model is on every regional endpoint
FoundryCLAUDE_CODE_USE_FOUNDRY=1, ANTHROPIC_FOUNDRY_RESOURCE=<resource>; Entra bearer, resource key or the Azure default credential chain. SDK variables per vendor docs: ANTHROPIC_FOUNDRY_API_KEY, ANTHROPIC_FOUNDRY_RESOURCE or ANTHROPIC_FOUNDRY_BASE_URL (mutually exclusive)Foundry User or Cognitive Services User (vendor docs, 15 Nov 2026)Deployment names are administrator-chosen and immutable, and the model parameter takes the deployment name, so keep a deployment-name-to-model map. Book 3 reports no startup model check (failures occur at request time) and an opus alias resolving to an older default than on other routes (Aug 2026) [FACT-CHECK: current alias resolution]. Foundry omits Anthropic’s rate-limit headers, so watch limits through Azure Monitor. Keep both request-id and apim-request-id for support cases
Claude Platform on AWSBook 3 Ch 4 PR-2’s matrix lists a _ANTHROPIC_AWS routing flag alongside CLAUDE_CODE_USE_BEDROCK (implying CLAUDE_CODE_USE_ANTHROPIC_AWS) [FACT-CHECK: Claude Code variable name]. SDK variables per vendor docs: ANTHROPIC_AWS_API_KEY (a key from the AWS console; standard Console keys do not work), ANTHROPIC_AWS_WORKSPACE_ID (wrkspc_ prefix), AWS_REGION, optional ANTHROPIC_AWS_BASE_URL, or SigV4 credentialsIAM service prefix aws-external-anthropic (e.g. aws-external-anthropic:CreateInference); enable outbound web identity federation once per account; sts:GetWebIdentityToken and sts:TagGetWebIdentityTokenA Bedrock-scoped role does not authorise this route (Ch 4 §4.4). Expect a permissions failure, and an access-review gap if nobody adds the new organisation to the inventory

Auth precedence. Book 3 App A §3.1 gives the order Claude Code and the Agent SDK use: cloud-provider flags (Bedrock, Vertex, Foundry) → ANTHROPIC_AUTH_TOKEN → ANTHROPIC_API_KEY → apiKeyHelper script → CLAUDE_CODE_OAUTH_TOKEN → subscription OAuth. [FACT-CHECK: current precedence in the Claude Code authentication documentation.] Practical rules:

  • Bind the route in the managed-settings env block, not in a shell profile, so a developer’s export cannot override ANTHROPIC_BASE_URL (Ch 4 PR-3). On a gateway, Bedrock, Google Cloud or Foundry route, Claude Code skips the server-managed settings fetch, so device-delivered policy is the policy (Paper 3 §4.2 rule 6). Use the managed key allowedProviders to refuse sessions configured for any other provider (Paper 3 §4.2 rule 2; version-gated). Workstation detail is on coding-agent workstation.
  • Gateway in front of a cloud route. Point the client at the gateway with ANTHROPIC_BEDROCK_BASE_URL or ANTHROPIC_VERTEX_BASE_URL, and set CLAUDE_CODE_SKIP_BEDROCK_AUTH=1 or CLAUDE_CODE_SKIP_VERTEX_AUTH=1 so the gateway, not the laptop, holds the cloud credential (App A §3.3, §3.5).
  • No team-shared keys, no raw keys on endpoints. Use workload identity per agent (Ch 9 PR-1 step 2). See identity and secrets.
  • Set every model-tier default explicitly (for example ANTHROPIC_DEFAULT_HAIKU_MODEL) so background tasks do not fall back to the most expensive primary model (Ch 4 §6, Bank A composite).

Govern the Microsoft 365 Copilot surface as a separate route

Book 3 calls this “the sixth route, the one nobody procured” (Ch 4 §4.6). Per App A §3.2 (verified by the author against Microsoft Learn on 14 May 2026):

  • Anthropic has been listed as a Microsoft sub-processor for select Copilot experiences since January 2026. The experiences named are Microsoft 365 Copilot (web, desktop, mobile), Researcher, Copilot Studio, Power Platform, Agent Mode in Excel, and the Word, Excel and PowerPoint agents.
  • Those Anthropic models are excluded from the Microsoft EU Data Boundary, are not available in government or sovereign clouds, and are opt-in (off by default) for EU/EFTA and UK tenants.
  • They are governed by Microsoft 365 terms, not Foundry terms.

[FACT-CHECK: current list of Copilot experiences using Anthropic models, their EU Data Boundary status, and whether they now run on Foundry-hosted capacity.]

Controls (Ch 4 §6–7):

  1. Separate register row and separate procurement and audit decision. Foundry Claude and Copilot Claude get two rows in the Register of Information.
  2. One shared owner who reads both the landing-zone configuration and the productivity-tenant configuration every quarter. In the Bank A composite, the DPO’s office owns the Copilot row.
  3. Bind AI-model enablement toggles to change control. That covers the M365 admin centre, Copilot Studio and every SaaS admin console with an AI sub-processor switch, all under the same change process as a Foundry deployment. Book 3’s test question for the architecture forum is: who can switch on an AI sub-processor here without raising a change? If the answer takes longer than ten seconds, you have found the gap.
  4. Withdraw the EU-residency assumption for any Copilot rollout that included Claude-served experiences.

Fill the contracting matrix

The contracting matrix is the decision’s evidence. Book 3 Ch 4 PR-2 defines one row per use-case class in four blocks, co-signed by procurement and the second line. The template below keeps the book’s fields. Fields marked † are this page’s additions, drawn from App A §5, App H §3 and the vendor corrections above.

Block 1: Scope

FieldValues / notes
Use-case classe.g. engineering productivity; employee assistance; regulated workflow agents
Risk tier / CIF flag / AI Act classTier per risk tiers; CIF yes/no; prohibited / high-risk / limited / minimal
Deployment routeOne of the routes above. M365 Copilot needs its own row
Hosting option (Foundry only)Hosted on Azure / hosted on Anthropic

Block 2: Contracting and processing. This block expires. Re-derive it every quarter.

FieldValues / notes
Data processorAnthropic / Microsoft / AWS / Google, re-derived from vendor text this quarter, with the source and its date
Billing partyState it even when it equals the processor
CTPP-designated processorYes / No (Anthropic: No, per App A, subject to the FACT-CHECK above)
DPA referenceAnthropic DPA / AWS DPA / Google Cloud DPA. Never MOSPA alone on a Foundry row
DORA mandatory contractual clauses confirmedYes / No (article reference on the regulatory map)
Register of Information row IDOne row per processor relationship; Copilot separate
Transfer mechanism †DPF (verified date) / SCCs Module 2 + TIA reference / Swiss–US DPF
Sub-processors in scope †e.g. WorkOS on Anthropic SSO paths; sandbox providers for hosted agents

Block 3: Technical configuration. The gateway and change register enforce these fields.

FieldValues / notes
Region and inference residencye.g. eu-central-1, in-region; Foundry, Global or US Data Zone; Anthropic API, inference_geo and workspace geo
Models authorised, pinned versionExact deployment, inference-profile or model ID. No aliases
Client routing flagCLAUDE_CODE_USE_BEDROCK / _VERTEX / _FOUNDRY / _ANTHROPIC_AWS / none
ZDR / HIPAAPer route and organisation, with the ZDR configuration record reference † and the list of non-eligible features the class may use †
Expected consumption †e.g. expected CCUs per workload on Claude Platform on AWS (App A §5); regional premium

Block 4: Governance and review

FieldValues / notes
Exit strategy referenceVendor concentration and exit
Responsible rolesNamed procurement lead, legal counsel, second-line reviewer, DPO, InfoSec architect
Second-line sign-offDate and named reviewer
Review cadenceQuarterly minimum; re-review at every model release and every vendor terms change
Open watch items †e.g. Foundry EU data zone; owner and next date

Acceptance for a row: every block-2 cell cites a vendor source dated within the current quarter. The processor and biller are stated separately. The model ID is pinned. Every non-ZDR feature the class uses is named. Both signatures are present. The Register of Information row ID resolves.

Run the per-route procurement checklist

Book 3 App A §5 gives a per-route cheat-sheet for the procurement lead and contract lawyer. Verify every item against the order form on the contracting date.

RouteCheck at contracting
Anthropic APIAnthropic Commercial Terms (incorporating the DPA, Usage Policy and Privacy Policy), or an Enterprise MSA and PO. DPA with SCCs Module 2 plus UK and Swiss adapters; importer Anthropic PBC. ZDR addendum via the Enterprise account manager. BAA if needed, scoped to eligible features. Sub-processor feed subscribed. SLA: Book 3 cites a 99.99% Enterprise figure from third-party reporting only [FACT-CHECK: SLA in the executed MSA]
FoundryMOSPA and Product Terms for the wrapper. Separately confirm DPA cover for the Anthropic processing leg and put that relationship on the register [FACT-CHECK: how the Anthropic leg is papered]. Hosting option chosen per deployment. Subscription tagged for cost allocation. RBAC role assigned. A written question to Microsoft on the EU data zone, with the answer filed. Private network: the vendor page now documents adding the resource to an Azure Virtual Network (Book 3 found no such guidance in August 2026)
BedrockAWS Customer Agreement or EA, AWS DPA and Service Terms; no separate Anthropic agreement. Customer-managed KMS key recommended for Book 3’s Tier 1 and above. PrivateLink endpoint per region, with the endpoint policy and IAM scoped to Bedrock invoke actions. Bedrock SLA version in force. AWS sub-processor list. Configure Bedrock retention and invocation-logging settings, and opt out of improvement programmes (Ch 10 §5.2)
Claude Platform on AWSTwo contractual layers (Marketplace order plus Anthropic Commercial Terms and DPA): verify both, and lock the DPA version referenced in the order form. ZDR scope in the addendum. No HIPAA. Confirm in writing that data is processed by Anthropic outside the AWS security boundary and draw it on the data-processor diagram. CMEK is available with AWS KMS keys per vendor docs (15 Nov 2026; Book 3 reported BYOK as “announced”)
Google-managed Google CloudGoogle Cloud Master Agreement, DPA and service-specific terms covering partner models. CMEK keyring in the endpoint’s region with a rotation policy. VPC Service Controls perimeter including Vertex AI. Private Service Connect. Access Transparency logs. Cloud Audit Logs
Anthropic-managed Google CloudNot in Book 3. Treat it as an Anthropic-processed route: Anthropic DPA, transfer record, new organisation in the identity inventory, ZDR enabled separately [FACT-CHECK: contract structure]

Every contracting decision is logged in the Register of Information. The row template is in Book 3 App I §2, and the obligation is on the regulatory map.

Treat hosted managed agents as outsourcing

Book 3 Ch 9 §4.4 states its position plainly. Claude Managed Agents is an Anthropic-managed harness that provides state, memory, permissions, scheduling, sandboxing and tool execution. It is an ICT third-party service supporting whatever function the agent supports, not a deployment option you operate. As of 3 August 2026 the book reports it in public beta at token rates plus $0.08 per session-hour [FACT-CHECK: current status and pricing].

What follows for a regulated firm (Ch 9 §4.4, §9):

PointConsequence
If the supported function is critical or important, the third-party obligations attach (register entry, exit strategy, audit access)Register it as an outsourcing arrangement before the first production session
Self-hosted sandboxes narrow the exposure but do not remove it. Tool execution moves to your infrastructure, but Book 3 notes the orchestration loop stays on Anthropic’s. Vendor docs (15 Nov 2026) add that attached memory stores remain stored by Anthropic and are copied to your sandbox for the sessionPrompts, tool arguments and results still transit Anthropic: keep the transfer record and DPA cover
Third-party sandbox providers are fourth parties. Book 3 names Cloudflare, Daytona, Modal and Vercel [FACT-CHECK: current list]Register the sub-outsourcing chain
No CIF on a beta service. The author’s position: Tier 0–1 workloads are a reasonable way to learn the surface; nothing supporting a CIF goes there until GA and a contract with SLAs, exit terms and audit accessGate admission by tier in the envelope registry
ZDR: Managed Agents is not ZDR-eligible except self-hosted Managed Agents (vendor table, 15 Nov 2026)Record the retention posture in the envelope
Residency: inference_geo can be pinned per agent and overridden per session; on Claude Platform on AWS, sessions run with workspace geo us (vendor docs, 15 Nov 2026)Same EU constraint as the parent route
Vaults keep credentials at the network boundary, so the agent never holds the real secret. But an injected agent can still use the credential against an allow-listed domain, and revoking a credential does not end a running sessionLeast-privilege scoping stays yours. Treat revocation as a session-termination event
Dreaming (scheduled memory curation) rewrites tomorrow’s memoryManual review mandatory for a regulated function
Scheduled deployments are standing changesThe schedule needs approval, not only the agent

Run Agent SDK agents as processes, not services

Choose the SDK or the raw API deliberately

Book 3 Ch 9 §5.5 treats this as a craft decision, governed by the same envelope either way:

  • Agent SDK: multi-step reasoning with tool use, such as research synthesis, incident summarisation, regulatory-change diffing and evidence preparation. These need the hook model and subagents.
  • Raw Messages API: a single-turn answer grounded in Citations, batched analysis through the Batch API (accepting that Batch is not ZDR), and tight latency budgets the SDK loop overhead cannot absorb.
  • Subagents give you context isolation, tool scoping and parallelism. Spawn each with a tighter tool allow-list, a separate context and an explicit return contract. Subagents inherit the parent’s identity unless re-scoped at spawn (Ch 9 §5.1). Permission modes also inherit. Vendor docs (15 Nov 2026) say a subagent inherits plan, acceptEdits, auto or bypassPermissions from the main session, and runs its own mode only under a default or dontAsk parent. Bound each subagent with maxTurns in its AgentDefinition. The vendor page states there is no per-subagent wall-clock deadline.

Know what you are deploying: the subprocess model

Book 3 Ch 9 §5.2 matches the vendor hosting page (15 Nov 2026). Calling query() spawns a separate claude CLI subprocess that talks over stdio and owns a shell, a working directory and session files on disk. One session is one subprocess.

PropertyValue / behaviourControl
Starting capacity per agent1 GiB RAM, 5 GiB disk, 1 CPU. The vendor page calls this a floor, not the ceilingSize hosts as (host RAM − overhead) ÷ measured peak per-session RSS
State on local diskTranscripts (~/.claude/projects/ or under CLAUDE_CONFIG_DIR), CLAUDE.md memory files, working-directory artefacts; none survive a restartSession store for transcripts; separate storage for memory and artefacts
Session timeoutNone at the top levelmaxTurns / max_turns plus an orchestrator-level pod deadline; recycle subprocesses to cap memory growth
Kill semanticsKilling the pod kills the shell and every child it spawnedThat is your suspension mechanism. Make sure an autoscaler cannot trigger it by accident
RoutingLong-running sessions pin to one containerConsistent hashing on sessionId behind the load balancer (Ch 9 PR-1 step 7)
VersionThe SDK bundles a CLI binary pinned to the SDK package versionUpdating the SDK is how you update the CLI, so put SDK bumps under change control

The SDK does not supply the envelope, the policy decision point, the evidence pipeline or the isolation posture (Ch 9 §5.6). Those come from the bounded-agent pattern, the model gateway, audit evidence and your platform team. The runtime must refuse to instantiate without a valid envelope ID, and the gateway must refuse traffic without one (Ch 9 §9).

Treat session-store mirroring as best-effort

The SessionStore adapter mirrors transcripts into storage you govern, and the vendor lists compliance and audit among its purposes. Book 3 Ch 9 §5.2 warns that it is a mirror, not a guarantee. The vendor page (15 Nov 2026) gives the detail:

  • Retries: a rejected append() is retried up to two more times (three attempts in total) with short backoff. A timed-out call is not retried. After that the SDK logs the error, emits { type: "system", subtype: "mirror_error" }, drops the batch and continues. The agent does not stop.
  • Which copy is durable depends on how the run started. For a fresh session, the local transcript outlives the run and the store holds a copy. For a run resumed from the store, the local copy is deleted at run end, so the store holds the only durable copy, and a dropped batch on such a run has no surviving copy anywhere. Book 3’s statement that “the local file stays authoritative” is true only for the first case.
  • Duplicates: retries can re-deliver entries. Deduplicate by entry.uuid in append(), and keep entries with no uuid.
  • Audit retrieval: getSessionMessages returns the post-compaction chain the agent would see on resume. For the full record, call store.load(key) (Book 3 Ch 9 PR-1 step 7 gives the same advice).
  • Retention: the SDK never deletes from your store. Lifecycle rules are the adapter’s job. Local transcripts are swept separately by cleanupPeriodDays.
  • Conflicts: persistSession: false (TypeScript) and file checkpointing both throw at startup when combined with a store.
  • Scope: only transcripts are mirrored, not CLAUDE.md or working-directory artefacts.

Controls. (1) A SOC detection rule on every mirror_error, with an owner. (2) For fresh sessions, reconcile the local JSONL against the store before container teardown. (3) For store-resumed sessions, treat a mirror_error as an evidence gap to record and report. (4) Do not assert transcript completeness to a supervisor without (1) to (3) in place (Ch 9 §9).

Put mandatory checks where the permission pipeline cannot skip them

Book 3 Ch 9 §5.3 and the vendor permissions page (15 Nov 2026) give the same six-step order. Assign an owner to each step:

StepEvaluatedBehaviour that mattersOwner (Book 3)
1. HooksFirstA hook deny holds in every mode, including bypassPermissions. A hook allow does not skip steps 2–3Platform security
2. Deny rulesdisallowedTools plus loaded settingsDeny even in bypassPermissions and even after a hook allowCentral policy
3. Ask rulessettings askFalls through to canUseTool, even in bypassPermissions; denied in dontAskCentral policy
4. Permission modeActive modebypassPermissions approves what reaches it; default and dontAsk move on to allow rulesPlatform (mode is set in code; review it)
5. Allow rulesallowedTools plus settingsApproved here never reaches canUseToolApplication team, within the envelope’s Means
6. canUseTool callbackLastSkipped and denied in dontAskApplication team (user experience, not control)

Book 3 calls the two documented warnings pre-written post-mortems:

  • A compliance check in canUseTool is silently bypassed for every call approved earlier by an allow rule, acceptEdits or bypassPermissions. Mandatory checks belong in a PreToolUse hook. The TypeScript SDK now emits a CLAUDE_SDK_CAN_USE_TOOL_SHADOWED process warning when the configuration shadows the callback (vendor docs, 15 Nov 2026). Make that warning fail the build.
  • allowedTools does not constrain bypassPermissions. Unlisted tools are still approved. For unattended agents, use the documented locked-down pattern of allowedTools plus permissionMode: "dontAsk": listed tools run, every call that would prompt is denied, and there is no prompt path. In an unattended agent, behaviour must not depend on an absent human.

CI and unattended runs (Ch 9 §5.3, PR-1 step 8; version-gated to Claude Code v2.1.x, August 2026): claude -p --bare --allowedTools "<explicit set>" --permission-mode dontAsk --output-format json. Keep each run’s session_id and total_cost_usd as evidence, and fail the job whenever the system/init event carries a non-empty mcp_server_errors or plugin_errors array. [FACT-CHECK: flags and event fields against the current headless documentation.]

Harden the runtime: a bank-grade profile

Book 3 Ch 9 §5.4 collapses Anthropic’s secure-deployment menu into one profile for Tier 2 and above. The author derived it from the vendor page but it is not quoted from it. [FACT-CHECK: isolation figures and the proxy caveat against the current secure-deployment page.]

#ControlSettingAcceptance check
1Isolation by zoneDevelopment zone: hardened Docker. Untrusted external content or multi-tenant: gVisor (--runtime=runsc) or a Firecracker microVM (Book 3 cites under 125 ms boot, under 5 MiB overhead)Runtime class recorded per envelope; untrusted-content agents never on plain containers
2Egress through a proxy, always--network none; the only way out is a Unix socket mounted from the host, behind which a proxy enforces the destination allow-list, adds credentials and records each requestA direct outbound connection from the container fails; the proxy log shows every call
3Credentials outside the boundaryAn MCP or custom tool relays to an authenticated service, or a TLS-terminating proxy injects the header (Book 3 names Envoy’s credential_injector). Book 3 prefers the custom-tool route for banks: no certificate estate, and each call is logged against the agent’s identity. Do not rely on sandbox-runtime’s built-in proxy: it allow-lists by client-supplied hostname without TLS inspection, so domain fronting bypasses itNo secret readable inside the container; egress enforced at the network
4Container flags--cap-drop ALL, --security-opt no-new-privileges, --read-only with a noexec,nosuid tmpfs, memory/CPU/PID limits, non-root user, read-only code volumeImage scan and admission policy enforce the flags
5No credential files in any mount, read-only included.env, ~/.git-credentials, ~/.aws/credentials, ~/.azure/, ~/.kube/config, ~/.docker/config.json, .npmrc, *.pem, *.keyMount manifest test fails on any match
6Multi-tenant isolationSee belowCross-tenant canary test

In the Asset Manager X composite (Ch 9 §8), the research agent ingests external research, so it runs on gVisor with --network none and a Unix socket to the egress proxy that holds the APIM bearer token. The direct API behind APIM is itself the proxy-based credential-injection pattern (Ch 9 §7).

Isolate tenants with four controls that travel together

One tenant’s CLAUDE.md or auto-memory appearing in another tenant’s prompt is a data-segregation breach, not a quality bug (Ch 9 §5.4 item 6). The vendor hosting page (15 Nov 2026) confirms the set. Apply all four on every query():

  1. settingSources: [] (Python setting_sources=[]), so no user, project or local settings load.
  2. CLAUDE_CODE_DISABLE_AUTO_MEMORY=1 in env. Auto memory loads into the system prompt regardless of settingSources.
  3. CLAUDE_CONFIG_DIR pointed at a per-tenant directory, so tenants do not share the global config. Build the path so no other tenant can read it.
  4. A per-tenant cwd, passed explicitly on every call.

Then add per-tenant egress rules at the proxy (distinct outbound identity, credentials or domain allow-lists), so a compromised tenant cannot exfiltrate through another tenant’s policy. One implementation trap from the vendor page: in TypeScript, env replaces the subprocess environment, so spread process.env deliberately. In Python, env merges. Note too that setting settingSources: [] also drops project .claude/settings.json permission rules, so supply those rules in code.

Acceptance test: plant a unique canary string in tenant A’s CLAUDE.md, auto-memory and working directory. Run tenant B’s session and assert that the canary is absent from the prompt, the transcript and all outbound traffic.

Re-run the portfolio every quarter

Book 3 App A §6 reviews route choices against six axes every quarter. The output is a row update in the route-decision register and an addendum to the next Register of Information submission. The review is a deliverable for the management body and a working artefact for the second line and internal audit.

AxisCheckSource of truth
1. Model lifecycleNew models per route, deprecations and exposed workloads, and the next two quarters’ retirement calendar. Deprecation schedules can differ by route. Vendor docs (15 Nov 2026) state Foundry follows the Claude API lifecycle; Bedrock and Google follow their own policiesAnthropic model-deprecations page; each cloud’s policy
2. RegulatoryChanges to the CTPP list, AI Act timing, supervisory guidance, incident-reporting templatesRegulatory map, calendar
3. AnthropicTrust Center updates, certifications, sub-processor changes, the policy versions in forcetrust.anthropic.com
4. Cloud providerFoundry EU data-zone status; re-derive the Foundry processor statement; new Bedrock and Google regions and model IDs; Claude Platform on AWS feature and region changes (re-check the inference-geo position); provider sub-processor listsVendor documentation, dated
5. Workload portfolioNew use cases and their routes; classifications that moved (Book 3’s typical case is a Tier 1 internal assistant becoming a Tier 2 customer-facing one); CIF flags added or removed; changed data-flow diagramsUse-case registry
6. Cost and concentrationSpend per route; concentration per provider as a share of the AI estate against limits; exit-rehearsal readiness per routeVendor concentration and exit; running the factory

Also reopen a row outside the quarterly cycle at every model release and every vendor terms change (Ch 4 PR-2). Bank A’s July re-run took eleven days, and Book 3 attributes that to a vendor fact changing, not a wrong choice. Its model-risk lead put it as choosing on facts that later expired (Ch 4 §6, composite).

Failure modes and recovery

Book 3 Ch 4 §7 and Ch 9 §9 name these patterns. The recognition signals and recoveries are condensed from them.

FailureRecognise byRecover
One route for everything”We’ll just put everything on Foundry”, with no mapping to use-case classesPush each class through the matrix against the four factors
Marketplace wrapper mistaken for processorTPRM register names only the cloud provider on an Anthropic-processed route; “MOSPA” in a Foundry DPA cellRe-derive the processor from current vendor text and add the Anthropic register row
An admin toggle opens a routeCopilot or SaaS AI features enabled with no change recordPut toggles under change control and name one owner across tenants
No data-flow diagramSecond line, DPO and TPRM describe the flow differentlyOne workshop; dated diagrams in the supervisory pack
Pilots leaked across routesThe AI inventory shows the same model on three routes with three evidence setsDraw a freeze line on new pilots and consolidate within the next two release windows. Book 3 accepts the cost in goodwill; the alternative costs a year
Residency assumed from a region name (this page’s addition)Claude Platform on AWS or Foundry recorded as “EU” because the workspace or resource sits in an EU regionRecord inference geo and storage geo separately; the region does not pin inference on these routes
ZDR assumed for a whole agentEnvelope says ZDR while the agent uses Files, Batch, the MCP connector, Skills or code executionGateway refusal on non-eligible features; envelope flag for second-line review
No envelope, no productionA successful Claude call with no envelope referenceRuntime refuses without an envelope ID; gateway refuses forwarding; SOC rule on envelope-less calls
Silent evidence lossTranscript gaps with no failed request anywhereAlert on mirror_error; reconcile before teardown
Compliance check in canUseToolAllow-listed tools bypass the checkMove it to a PreToolUse hook; fail the build on the shadowing warning
Credential revocation that does not stop the agentA revoked credential still produces successful callsTreat revocation as session termination

Ownership

Artefact or controlAccountableConsulted
Route-decision register and quarterly reviewHead of platform (route-portfolio owner)Lead architect, procurement, second line
Contracting matrix rowProcurement lead and second-line reviewer (co-sign)Legal, DPO, InfoSec architect
Register of Information rows, including CopilotProcurement leadSecond line, DPO
Transfer record (DPF / SCCs + TIA / Swiss DPF)DPO with procurement leadLegal
ZDR configuration record; non-eligible-feature exceptionsPrivacy office; wrangler per envelopePlatform
Client route binding (managed env, allowedProviders)Endpoint engineeringPlatform security
SDK runtime profile, tenant isolation, session storePlatform engineering owner of the SDK runtimeSecurity engineering
Detection rules (mirror_error, envelope-less calls, token spikes, recursion depth)SOC engineering leadWrangler
Managed Agents admissionThird-party risk owner and Agent Control BoardSecond line

Acceptance checks

  1. Every production use-case class has one signed matrix row. Block 2 cites vendor text dated within the current quarter, and processor and biller are stated separately.
  2. Every Foundry row names Anthropic as processor, records the hosting option, and has its own Anthropic register entry and DPA reference.
  3. Every Anthropic-processed row has a transfer record with a verification date, and a TIA reference where SCCs are relied on.
  4. No row claims EU in-region inference for the Anthropic API, Claude Platform on AWS, the Anthropic-managed Google offering or Foundry unless current vendor text supports it.
  5. Microsoft 365 Copilot’s Anthropic experiences have a separate register row, a named owner, and toggles under change control.
  6. Each organisation provisioned through a marketplace (Claude Platform on AWS, Anthropic-managed Google) is in the identity inventory and the access review.
  7. For every ZDR-dependent envelope, a synthetic request using mcp_servers, /v1/files or /v1/messages/batches is refused at the gateway.
  8. Model IDs are pinned on every route; a configuration scan finds no aliases in production settings.
  9. Managed Agents are absent from CIF-supporting envelopes; any Tier 0–1 use is in the outsourcing register with its fourth parties.
  10. SDK runtimes pass the hardening checks above, a mirror_error test fires the SOC rule, and the cross-tenant canary test passes.
  11. No mandatory check lives only in canUseTool, and unattended agents run with dontAsk and an explicit allowedTools.
  12. The quarterly review minutes cover all six axes, and the Register of Information addendum is filed.

Source status and differences

TopicDifferencePage follows
Foundry processorApp A (Aug 2026), Ch 4, Paper 3 and vendor docs say Anthropic; App H §3.2, the Glossary and Ch 10 §5.2 say Microsoft or the cloud providerAnthropic
Claude Platform on AWS residencyApp A and Ch 4 list EU regions with in-region inference; vendor docs (15 Nov 2026) give US or Global inference only, with the region not pinning inferenceVendor docs. App A §4 step 3 and Ch 4 PR-1 item 4 are corrected above
HIPAABook 3: direct API only, BAA extends to Claude Code with ZDR; vendor docs (15 Nov 2026): Claude API and Foundry eligible, Claude Code not coveredVendor docs
Session-store authorityCh 9 §5.2: local file stays authoritative; vendor docs: true for fresh sessions only, store-resumed runs delete the local copyVendor docs
Computer useCh 9 §4.2: not HIPAA-eligible; vendor table: ZDR- and HIPAA-eligible (client-side)Vendor docs for eligibility; Book 3 for admission controls
Foundry feature and networking gapsBook 3 (Aug 2026): no published feature-limitation list or VNet guidance; vendor docs (15 Nov 2026) publish bothVendor docs
Anthropic-managed Google CloudAbsent from Book 3Included from vendor docs; contracting marked for fact-check
Bedrock, Google-managed Google Cloud, M365 Copilot, Managed Agents statusNot re-verified for this pageBook 3 / Paper 3, marked [FACT-CHECK]

Regulatory status, articles and dates are deliberately not restated here. See the regulatory map and regulatory calendar.

Source material

  • Book 3 (Deploying Claude Safely), Chapter 4, The Deployment Decision (§3 main idea; §4.1–4.6 the routes and the M365 Copilot surface; §4.7 sovereignty gap; §4.8 AWS and GCP equivalents; §5 four decision factors; §6 Bank A worked example and July re-run; §7 anti-patterns; PR-1 Azure-first decision tree; PR-2 contracting matrix template; PR-3 cookbook)
  • Book 3, Chapter 7, MCP and the Connector Broker (§4.1 the Messages API MCP connector and ZDR; per-route MCP parity)
  • Book 3, Chapter 9, The Anthropic API and Agent SDK (§4.1–4.4 API surface, MCP from the API side, Managed Agents as outsourcing; §5.1–5.6 Agent SDK subprocess model, permission pipeline, runtime hardening, SDK versus raw API; §7 cloud equivalents; §8 Asset Manager X; §9 anti-patterns; PR-1 API agent decision tree)
  • Book 3, Chapter 10, Data Classification, Retention, and DLP (§5.1–5.2 ZDR scope on the direct platform and the cloud routes)
  • Book 3, Appendix A, Anthropic Deployment Options Matrix (§1 overview; §2 master matrix; §3.1–3.5 per-route deep dives and the M365 Copilot sidebar; §4 seven-step decision sequence; §5 procurement and contracting cheat-sheet; §6 quarterly review checklist)
  • Book 3, Appendix C, MCP Server Registration and Approval Checklist (§5 item 17, ZDR posture of the mcp_servers parameter)
  • Book 3, Appendix D, Bounded Agency Envelope Template (§2.3 persistent_storage files_api_on validation rule)
  • Book 3, Appendix H, Vendor Concentration and Exit Playbook (§3.1 eight cleavage points; §3.2 per-route summary)
  • Book 3, Appendix I, Regulatory Mapping (§3 DORA and Anthropic's CTPP status; §6.1 GDPR/FADP transfer mechanisms)
  • Book 3, Appendix J, Glossary (Azure AI Foundry, Claude Platform on AWS, WorkOS, Sub-processor, Zero data retention, HIPAA-ready, Batch API, Files API)
  • Research Paper 3, Securing Claude Code in the Enterprise (§4.1 approved routes and the Foundry hosting, residency and provider facts; §4.2 rules; §4.3 Amazon and Google equivalents)
  • Research Paper 9, Data Classes, Processing Lanes and Controller/Processor Roles for AI (§6.2 where inference runs; §8.2 vendor documentation)

← All AI Delivery Factory guidance

On this page

  1. Decisions this page supports
  2. Treat the route as a portfolio decision
  3. Record who operates, bills and processes
    1. Source difference: who processes on Foundry
  4. Size the diligence to the processor
  5. Check residency route by route
    1. Record the transfer basis for every Anthropic-processed route
  6. Check zero data retention and HIPAA per feature, not per route
    1. ZDR by route (vendor docs, 15 Nov 2026)
    2. Features that leave ZDR
    3. Controls that make ZDR checkable
    4. The MCP connector: wire format only, broker decides
    5. HIPAA by route
  7. Walk the seven-step route decision
    1. The Azure-first shortcut (a second layer, not a replacement)
  8. Configure each route’s identity and client binding
  9. Govern the Microsoft 365 Copilot surface as a separate route
  10. Fill the contracting matrix
  11. Run the per-route procurement checklist
  12. Treat hosted managed agents as outsourcing
  13. Run Agent SDK agents as processes, not services
    1. Choose the SDK or the raw API deliberately
    2. Know what you are deploying: the subprocess model
    3. Treat session-store mirroring as best-effort
    4. Put mandatory checks where the permission pipeline cannot skip them
    5. Harden the runtime: a bank-grade profile
    6. Isolate tenants with four controls that travel together
  14. Re-run the portfolio every quarter
  15. Failure modes and recovery
  16. Ownership
  17. Acceptance checks
  18. Source status and differences

All pages in Build the platform →