Browse the reference ⌄
Concept published

The Anatomy of an AI Application

A six-tier view of what one AI product is made of, crossed by a trust and operations plane that attaches controls to every tier; what the factory already supplies per tier, how the anatomy maps to the six-layer product portfolio, and how to run an anatomy review.

Version
0.2.0
Owner
DEIXEI
Last reviewed
Reading time
8 min

For Cto · Ai Architect · Platform Engineer · Product Leader · Risk And Assurance

Sources and details
Section
Understand
Source works
Book 1 · Book 2 · Research Series
Source chapters
6, 11, 22
Refresh trigger
source change

Full source list ↓ Source index →

An AI application is more than a model and a prompt. It is a set of connected capabilities with different owners, change rates and failure modes. Use this anatomy during architecture review to locate what a product needs, what the factory already supplies, and where controls must attach. It is the checklist behind question 6 of the decision sequence: which catalogue assets already cover each tier?

An AI application spans six tiers, from experience and orchestration through models, data and hosting. A trust and operations plane crosses all six.

The six-tier anatomy and the cross-cutting trust and operations plane. Source: The AI Delivery Factory, Chapter 22, Figure 22.1.

Six tiers, one cross-cutting plane

Research Paper 1 (§4.1) numbers the tiers L0–L5 and the plane X; Book 2 (Ch 22 §4.1) uses the names only. The codes are useful in manifests and queries.

CodeTierWhat belongs hereWhat the factory already supplies (Book 2 Ch 22 §4.1)Questions for design
L5Experience and channelsChat, embedded copilots, APIs, batch jobs, event-triggered and IDE surfacesUI component library, conversation shells, feedback widgetsWho uses the product, through which channel, and what does the interface let them do?
L4Integration and interoperabilityTools, APIs, events, connectors, MCP servers, agent-to-agent endpointsTool broker, tool registry, agent cards, event contractsWhich systems can be called, under whose identity and with what authorisation?
L3Reasoning and orchestrationPrompts, context engineering, workflows, agents, planners, session statePrompt library, workflow templates, agent templates, memory managersWhich next steps are fixed in code, and which are selected by a model?
L2ModelsFoundation, small and specialised models, fine-tunes, classical ML, embedding and rerank modelsModel gateway, evaluation-backed model cards, model usage registryWhich model is selected for each task, how is it evaluated, and how can it be changed?
L1Data and knowledgeSources, ingestion, chunking, embeddings, vector and graph stores, semantic layer, long-term memoryIngestion pipelines, document parsers, index templates, entitlement-aware retrieval storeWhat data may enter the request, who is entitled to it, and what may persist?
L0Infrastructure and hostingCompute, accelerators, network, tenancy, region, sovereign or on-premises optionsLanding zones, private endpoints, model-serving runtimesWhere does processing occur, what reaches the network, and how is the runtime isolated?
XTrust and operations planeIdentity, authorisation, guardrails, evaluation, observability, cost, registries, audit evidenceThe services of the enterprise control plane, consumed by the productWhich controls execute at each tier, and what evidence do they leave?

Integration sits beside orchestration, not below it, because agents call tools and tools can call agents.

The plane is not a seventh tier and must never be drawn as one. It is Book 1’s enterprise agent control plane (Ch 11) seen from the product side — identity, registry, policy, observability, approval and evidence — met by a product as services it consumes rather than planes it operates. Controls attach to tiers and to the plane, so a product composed from catalogued components inherits its controls instead of negotiating them. If a tier can be composed without the plane, the firm gets a working product with controls negotiated separately each time.

One name, two positions. Integration and interoperability is both an anatomy tier (where a component lives) and a pattern family (how a capability is built). The classification line records the anatomy tier and the pattern family as separate fields so the ambiguity never bites.

Do not confuse the product portfolio with the anatomy

Two layered pictures appear in the factory, and confusing them is, per Book 2, the most common error when importing outside architecture material.

Six-layer product portfolio (Book 2 Ch 6)Application anatomy (Book 2 Ch 22)
QuestionWhat does the factory ship, in what order, funded how?What is one AI application made of, and which controls attach where?
UnitThe factory’s estateA single product
Used to decideWhat to fund and who owns itWhat not to build
Layers0 chassis · 1 AI primitives · 2 capability services · 2.5 experience layer · 3 horizontal workflows · 4 domain productsL0–L5 and the plane X

A research copilot occupies one row of the portfolio (Layer 4) and has every tier of the anatomy. Portfolio Layers 0 to 2.5 are platform-funded roots; Layers 3 and 4 are product-funded and carry business cases (application foundation).

The six-layer product portfolio, from the engineering chassis at the bottom to domain products at the top.

The factory’s six-layer product portfolio. Source: The AI Delivery Factory, Chapter 6, Figure 6.2.

Where the portfolio supplies each tier

The crosswalk below is Book 2’s (Ch 6 §4; the author labels the mapping his own). Use it in review to find the portfolio product that should cover a tier before a squad builds its own.

Anatomy tierWhere the portfolio supplies it
Infrastructure and hostingLayer 0: paved-road infrastructure, infrastructure module library
Data and knowledgeLayer 0 classification services; Layer 1 document ingestion and entitlement-aware retrieval store; Layer 2 retrieval-augmented generation service
ModelsLayer 1: model gateway and the models behind it
Reasoning and orchestrationLayer 1 prompt registry; Layer 2 agent runtime and structured extraction
Integration and interoperabilityLayer 0 API conventions; the tool broker beside the Layer 2 agent runtime
Experience and channelsLayer 2 UI component library and human-review console; Layer 2.5 portal platform and web pattern
Trust and operations planeLayer 0 identity and telemetry backbone; Layer 1 evaluation harness and gateway policy; Layer 2.5 catalogue

Read three things from it.

  1. Layers 3 and 4 do not appear in the right-hand column. They are whole applications with complete anatomies. A well-built one owns only its upper-tier specifics — prompts, workflow, evaluation cases, screens — and inherits the rest by reference.
  2. No portfolio row is labelled “governance”. The plane’s services are spread across Layers 0 to 2.5.
  3. A private copy of a portfolio-supplied tier is duplication. A Layer 4 product with its own model gateway, retrieval store or evaluation set is, in Book 2’s phrase, the “fourth file upload, one tier up”.

Keep five words apart

The anatomy only attaches ownership cleanly if five terms mean one thing each (Book 2 Ch 22 §4.5; definitions in the glossary). Book 2 names the owners of the model, agent and tool; the owners shown for the vendor and the AI system are this page’s recommendation.

TermWhat it doesWhere it sits in the anatomyOwner
ModelComputes; stateless, no tools, cannot actModels tierPlatform model team; model catalogue and usage registry
AgentDecides and acts inside an envelopeReasoning and orchestration, with an identity on the planeNamed wrangler
ToolExecutes deterministic code with real permissions, classified by effect (read-only, draft, reversible write, irreversible action)Integration and interoperabilityOwner of the system behind it
VendorSupplies; the model developer and host may be different partiesOutside the anatomy; recorded in third-party registersProcurement and third-party risk
AI systemThe whole product around the modelAll tiers plus the planeProduct owner; the unit put into production and regulated

Run the anatomy review

Before review — count what the squad poured (Book 2 Ch 6 §7). For each tier, ask whether the squad inherited it from the portfolio or built it privately. Every private gateway, retrieval store or evaluation set needs a reason in the design record, or becomes a contribution back to the catalogue.

For each tier, record:

  • The selected component, its catalogue identifier (or “new”) and its owner.
  • The interface and identity used at the boundary.
  • Data classes, entitlements and retention constraints.
  • Policy checks and the evidence they leave on the plane.
  • Evaluation and failure behaviour.
  • Version, lifecycle and replacement path.

These rows feed design record fields 4 (patterns per tier) and 5 (assets reused and proposed) on choose the AI product shape, and the BOM on BOM and recipes.

Then review the seams. A model may evaluate well while its retrieval layer crosses entitlements. A tool may be authorised while the agent identity is not attributable to a person. A safe runtime may still send sensitive context to an unapproved endpoint. Walk one request end to end and test each control where it executes, not where it is documented. For class 3 and 4 designs, the cut-set review on the shape page names the plane each control sits on; controls that share a tier and a plane are rarely independent.

Acceptance checks.

  • Every tier has a named component and owner, or an explicit “not used”.
  • Every tier covered by a portfolio product uses it, or the design record states why not.
  • Every boundary names the identity used and the policy check that executes there.
  • One end-to-end request has been walked and each plane control observed producing evidence.

Failure modes

FailureHow to recognise itRecovery
Portfolio and anatomy conflatedFunding arguments in a design review, or tier questions in a funding reviewUse the portfolio to fund, the anatomy to design
Importing someone else’s stack whole (Book 2 Ch 22 §8)Two people use “layer 3” for different things and neither noticesTranslate imported material at the door; hold the mapping centrally
The plane drawn as a tierA “governance layer” team owning controls that never execute in the other tiersAttach each control to the tier where it runs and to its plane
Private tiersRepeated private gateways, stores or evaluation sets across productsCount per tier at review; route to the portfolio owner

What this model does not decide

The anatomy is a design checklist, not a deployment topology or a compliance conclusion. It does not prescribe a cloud, model, vector store or agent framework. Hosting route, risk tier and permitted data use depend on the workload and the institution’s own policy and obligations; resolve them through choose the AI product shape and the relevant build guides.

Source status. The tier model is the author’s design proposal, presented in Research Paper 1 as a reading of the convergent published reference architectures. The “what the factory already supplies” column is from Book 2 Ch 22; the portfolio crosswalk is from Book 2 Ch 6, where the author labels it his own mapping.

Source material

  • Book 2 (The AI Delivery Factory), Chapter 22, The Shape of an AI Product (§4.1 application anatomy; §4.5 five words; §8 importing someone else's stack)
  • Book 2 (The AI Delivery Factory), Chapter 6, The Standard Application Foundation (§4 six-layer product portfolio; portfolio-to-anatomy table; §7 tier count)
  • Book 1 (Building Organizations for the Age of AI), Chapter 11, The Enterprise Agent Control Plane
  • Research Paper 1, A Taxonomy for a Reuse-Driven AI Factory (§4.1 Axis 1: layers)

← All AI Delivery Factory guidance

On this page

  1. Six tiers, one cross-cutting plane
  2. Do not confuse the product portfolio with the anatomy
    1. Where the portfolio supplies each tier
  3. Keep five words apart
  4. Run the anatomy review
  5. Failure modes
  6. What this model does not decide

All pages in Understand →