Architecture

How it comes together, end to end.

One reference implementation, from the data to the agent to the security operations center, on the cloud you already run.

The architecture tour, about three and a half minutes. Chapters: 0:00 what RJL Studio does; 0:20 three apps on one architecture; 1:16 the control plane; 1:32 from your data to the answer; 2:28 on AWS and alongside your data platforms; 2:56 what we are not; 3:13 your own cloud. Status labels follow the products page. Narration is AI-generated (Amazon Polly); turn on captions with the CC button. Download with captions burned in (MP4)

The full picture

Three disciplines, one system.

Most programs fund AI, data and security separately. They only work when designed together, and held together by orchestration and an operating model: the process, control plane, release gates and accountable owners that run them.

ORCHESTRATION AND OPERATING MODELDesign / Release / RunAIAgents and toolsEvaluation and outcomesDataMeaning and provenanceGoverned data productsSecurityIdentity and permissionsEnforcement and monitoringWhere two disciplines must be designed togetherAI + DATAGrounded contextMeaning and source evidenceAI + SECURITYBounded authorityIdentity and tool permissionsDATA + SECURITYGoverned data accessClassification and enforcementGoverned production AIEvidence for release · Oversight · Controlled changeProcessWorkflows and exceptionsControl planePolicy and executionRelease gatesEvaluation and approvalAccountabilityOwners and response
ORCHESTRATION AND OPERATING MODELAIAgents and tools · Evaluation and outcomesDataMeaning and provenance · Governed data productsSecurityIdentity and permissions · Enforcement and monitoringWhere two disciplines must be designed togetherAI + DATAGrounded contextMeaning and source evidenceAI + SECURITYBounded authorityIdentity and tool permissionsDATA + SECURITYGoverned data accessClassification and enforcementGoverned production AIEvidence for release · Oversight · Controlled changeProcessWorkflows and exceptionsControl planePolicy and executionRelease gatesEvaluation and approvalAccountabilityOwners and response
Design AI, data and security together. Three capabilities, one accountable operating model. A conceptual model, not a deployment topology.

One system, three views

This diagram is the main view. The other two describe the same system for a different purpose. None is a separate framework to buy or implement.

AI, data and security togetherDecide what must be designed and owned jointlyThis page and the offerings
Four responsibilitiesExplain the system to non-specialists: brain, nervous system, body, immune systemThe Four-Part System
Layers and capability mapSee what runs where, with example products, and assign owners one capability at a timeBelow, with the worksheet and The Reference Implementation

How the three views fit together. The three disciplines set what must be true: Trusted Data, Tested Capability and Bounded Access. The Four-Part System assigns the architectural job behind each one. Trusted Data is the brain’s work, and Bounded Access is the immune system’s. Tested Capability is what the four parts serve: agents and models reach work through the nervous system, run in the body, and are proven at release gates recorded in the control plane. The four phases, Frame, Prove, Build, then Operate and transfer, are how an engagement gets one workflow there.

The architecture

The agentic enterprise, layer by layer.

People and agents work in redesigned processes on top of five layers. Security frames every layer, and orchestration and operation run beside them. The names match the capability map and the product layers below.

Security, across every layer · identity for people and agents, labels, enforcement at the data, monitoring

People and agents

Redesigned business processes. Agents act within the authority of the person they serve, and a person stays in the loop for consequential actions.

AI and experience

Agent platform

ReasoningToolsMemoryOrchestrationGuardrailsEvaluationCatalogObservability

Models and analytics

Foundation modelsAdapted modelsReportingSelf-service

Access and interfaces

Data APIsGoverned measuresAI gatewayAgent toolsRetrievalCommand path for writes

Meaning and knowledge

Ontology and knowledge graphSemantic layerMetadataMaster dataSearch

The ontology says what is meant; the semantic layer computes the number. Context for the answer, never a grant of access.

Data platform

Data productsDomain platformsPipelinesStorageVector storage

Access is enforced here: masking and row access, every time.

Sources

Operational applicationsDocumentsExternal data

Orchestration and operation

  • Release gates and evaluation
  • DataOps, DevOps, model operations
  • Quality and lineage
  • FinOps: cost per completed task
  • Request evidence: who asked, which definition, measure and data versions, which policy decision, what happened

Operating model, underneath

Accountable owners, decision rights, skills and funding for running, not only building.

Vendor neutral. Four requirements anchor this design: identity for every agent, meaning separate from access authority, governed numbers from fixed measures rather than the model’s own arithmetic, and evidence that lets an authorized reviewer reconstruct a request.

On your platform

The same architecture on AWS, Azure, Google Cloud, Snowflake, Databricks or a mixed estate.

24 layers across the four parts and the control plane, 161 named services, each with its release status checked on 13 November 2026. Pick a platform, or the mixed estate most enterprises actually run, then click a layer, step through a flow, or compare platforms side by side.

LayerAWSMicrosoft AzureGoogle CloudSnowflakeDatabricksMixed estate (example)
Catalog, metadata and lineageAWS Glue Data Catalog GA
Amazon SageMaker Catalog GA
Microsoft Purview Unified Catalog GA
OneLake catalog GA
Knowledge Catalog (formerly Dataplex Universal Catalog) GASnowflake Horizon Catalog GAUnity Catalog GAdata.world (ServiceNow) GA
Semantic layer and metricsNo native universal semantic layer GapPower BI semantic models GA
Fabric IQ (workload) GA
Looker semantic layer (LookML) GA
BigQuery measures Preview
Semantic views GAUnity Catalog metric views GASemantic views GA
dbt Semantic Layer GA
Ontology and knowledge graphAmazon Neptune Database GA
Amazon Neptune Analytics GA
Fabric IQ ontology Preview
Graph in Fabric GA
Spanner Graph GA
BigQuery Graph Preview
No native graph store GapGenie Ontology Previewdata.world knowledge graph GA
Knowledge retrieval and vector searchAmazon Bedrock Knowledge Bases GA
Knowledge Bases GraphRAG with Neptune Analytics GA
Amazon S3 Vectors GA
Azure AI Search GA
Foundry IQ GA
Vertex AI Search (Gemini Enterprise Agent Platform) GA
BigQuery vector search GA
Cortex Search GAMosaic AI Vector Search GA
Knowledge Assistant GA
Cortex Search GA
Amazon Bedrock Knowledge Bases GA
Master data and entity resolutionAWS Entity Resolution GANo native MDM service GapNo native MDM service GapNo native MDM service GapNo native MDM service GapPartner MDM Gap
SaaS and enterprise source connectorsAWS Glue zero-ETL for applications GA
Amazon AppFlow GA
Fabric Data Factory connectors and Copy job GA
Fabric mirroring (SAP Datasphere, Oracle, Dataverse) GA
Integration Connectors GA
Cortex Framework for SAP and Salesforce GA
Snowflake Openflow GALakeflow Connect GASnowflake Openflow GA
Change data capture and streamingAWS Database Migration Service (CDC) GA
Amazon Kinesis Data Streams and Amazon MSK GA
Zero-ETL from Aurora, RDS and DynamoDB GA
Fabric mirroring for databases GA
Azure Event Hubs GA
Datastream GA
Pub/Sub and Managed Service for Apache Kafka GA
Snowpipe Streaming GA
Openflow database connectors Confirm
Lakeflow Connect database connectors GA
Structured Streaming GA
AWS Database Migration Service (CDC) GA
Apache Kafka GA
APIs, events and workflowAmazon API Gateway GA
Amazon EventBridge and AWS Step Functions GA
Azure API Management GA
Azure Logic Apps and Event Grid GA
Apigee GA
Workflows and Eventarc GA
Reverse ETL for BigQuery Preview
Snowflake SQL API and external access integrations GADatabricks Apps and Lakeflow Jobs GA
Lakebase GA
Hasura DDN GA
Amazon API Gateway GA
Agent tools, gateway and MCPAmazon Bedrock AgentCore Gateway GA
AWS MCP Server GA
MCP governance in Azure API Management GA
Azure MCP Server GA
Azure Logic Apps MCP Server GA
Google-managed MCP servers GA
Agent Gateway (Gemini Enterprise Agent Platform) Confirm
Snowflake-managed MCP server GA
MCP connectors for Cortex Agents Preview
Unity AI Gateway MCP services GA
Databricks managed MCP servers Preview
Amazon Bedrock AgentCore Gateway GA
Storage, open tables and historyAmazon S3 and S3 Tables (Apache Iceberg) GAOneLake and Azure Data Lake Storage Gen2 GACloud Storage and BigLake Iceberg tables GAApache Iceberg tables GADelta Lake and Iceberg managed tables GAApache Iceberg tables GA
Warehouse, lakehouse and operational storesAmazon Redshift, Athena and EMR GAFabric Data Warehouse and Lakehouse GABigQuery, Spanner and AlloyDB GASnowflake virtual warehouses GADatabricks SQL GASnowflake virtual warehouses GA
Pipelines and transformationAWS Glue ETL and Amazon MWAA GAFabric pipelines, Dataflow Gen2 and materialized lake views GADataform, Dataflow and Cloud Composer GADynamic Tables GALakeflow Declarative Pipelines GAdbt GA
Apache Airflow GA
Data products and sharingSageMaker Catalog data products GA
Redshift data sharing and AWS Data Exchange GA
Purview Unified Catalog data products GAKnowledge Catalog data products GA
BigQuery sharing (Analytics Hub) GA
Secure Data Sharing and Snowflake Marketplace GAOpenSharing (Delta Sharing) and Clean Rooms GASecure Data Sharing and Snowflake Marketplace GA
Models and AI platformAmazon Bedrock GAMicrosoft Foundry Models GAModel Garden (Gemini Enterprise Agent Platform) GACortex AI and AISQL GAModel Serving and Foundation Model APIs GAAmazon Bedrock GA
Cortex AI and AISQL GA
Agent runtime and memoryAgentCore Runtime and Memory GA
Amazon Bedrock Agents GA
Foundry Agent Service GAAgent Runtime, Sessions and Memory Bank GACortex Agents and Snowflake Intelligence GAAgent Bricks and Genie Agents Confirm
Managed agent memory and sessions Beta
AgentCore Runtime and Memory GA
Observability, evaluation and costAgentCore Observability and Evaluations GA
Amazon CloudWatch GA
Foundry Control Plane observability and evaluations GA
Azure Monitor GA
Cloud Trace, Monitoring and agent evaluation ConfirmAccount usage views and AI observability ConfirmMLflow tracing and system tables GAOpenTelemetry GA
AgentCore Observability and Evaluations GA
Identity for people and agentsAWS IAM Identity Center and AgentCore Identity GAMicrosoft Entra ID and Entra Agent ID GACloud IAM GA
Agent Identity Confirm
Role-based access control and OAuth GAUnity Catalog identities and service principals GAOkta GA
Microsoft Entra ID and Entra Agent ID GA
Access policy at the dataAWS Lake Formation and Amazon Verified Permissions GAOneLake security GABigQuery row and column security, policy tags and VPC Service Controls GAMasking and row access policies GAAttribute-based access control (ABAC) GAMasking and row access policies GA
Classification, DLP and DSPMAmazon Macie GAMicrosoft Purview Information Protection, DLP and DSPM GASensitive Data Protection GASensitive data classification GAData Classification GACyera GA
Microsoft Purview Information Protection, DLP and DSPM GA
AI guardrails and action policyAmazon Bedrock Guardrails GA
Policy in AgentCore GA
Azure AI Content Safety and Prompt Shields GA
Content safety for MCP and A2A in API Management GA
Model Armor GACortex Guard GAUnity AI Gateway guardrails ConfirmAmazon Bedrock Guardrails GA
Policy in AgentCore GA
Security operations (SIEM and SOAR)AWS Security Hub, Amazon GuardDuty and Amazon Security Lake GAMicrosoft Sentinel and Defender for Cloud GAGoogle Security Operations and Security Command Center GATrust Center GALakewatch ConfirmYour SIEM and SOAR Confirm
Keys and confidential computingAWS KMS and AWS Nitro Enclaves GAAzure Key Vault and Azure confidential computing GACloud KMS and Confidential Computing GATri-Secret Secure GACustomer-managed keys GAAWS KMS and AWS Nitro Enclaves GA
Tri-Secret Secure GA
Agent registry and release controlAmazon Agent Registry GAMicrosoft Agent 365 and Foundry Control Plane inventory GAAgent Registry (Gemini Enterprise Agent Platform) ConfirmCortex Agent versioning GAUnity AI Gateway registry GAAmazon Agent Registry GA
ServiceNow change and incident management GA
Audit and governance evidenceAWS CloudTrail and AWS Audit Manager GAMicrosoft Purview Audit and Compliance Manager GACloud Audit Logs and Assured Workloads GAAccess History GAAudit log system tables GAAWS CloudTrail and AWS Audit Manager GA
Access History GA

Examples, not endorsements. GA means generally available; Preview and Beta are not production commitments; Confirm means vendor sources disagree or no dated source was found; Gap means there is no native service. Status reflects public vendor sources on the date shown. Download the catalog (JSON). One page per platform: AWS, Azure, Google Cloud, Snowflake, Databricks. Richard has worked closely with several vendors named here as a customer and practitioner. No vendor reviewed or paid for this content.

Use case · reference example

A claims assistant, traced end to end.

A claims examiner asks who is connected to an assigned case, its status, and which procedure applies. This read-only architecture pattern supports the claims preparation guide: team A, group disability, region 2. Events within the assigned case are included; prior-claims history, internal notes, decisions, payments and customer contact are excluded from its narrowed release.

  1. 01

    Security

    The examiner signs in through single sign-on. The assistant runs under its own agent identity, registered to the claims owner, with a defined role.

  2. 02

    Security

    The request carries a short-lived token scoped to this examiner and this agent: only what both are allowed.

  3. 03

    AI

    A fixed sequence resolves claim status, the related parties and the applicable procedure. Cross-case search and note tools are unavailable in the narrowed runtime.

  4. 04

    DataSecurity

    Claim status comes from a certified data product through a narrow API. Tag-based masking hides fields this examiner may not see.

  5. 05

    DataSecurity

    Procedure documents were classified and labeled by the DSPM tool. Retrieval returns only documents this examiner may read, for this tenant.

  6. 06

    Security

    One document contains hidden instructions to email the file outside the company. The agent has no tool that can send externally; the attempt is refused and flagged.

  7. 07

    AI

    The answer separates facts from interpretation, cites its sources and the definition version it used, and flags an unresolved party match for the examiner.

  8. 08

    Security

    Every step is traced with the agent’s identity, the user, the tools, the data labels and each policy decision, and streamed to the SOC.

  9. 09

    Security

    Days later, the agent starts requesting claims outside the examiner’s assigned book. Each call is denied; the repeated denials alert the SOC, and a playbook suspends the agent identity and opens an incident for the owner.

  10. 10

    Security

    When an examiner leaves, the identity provider removes access, and the revocation test shows the assistant stops using it within the tested window.

  11. 11

    Orchestration

    The trace, the refused instruction, the incident and the revocation test become release evidence. The owner decides whether to restore the agent, and on what conditions.

The steps illustrate architecture and incident handling, not a client deployment or an executed test. The versioned workflow record and completed release decision define the worked guide’s accepted scope and held dependencies.

Orchestration

The process and technology that hold it together.

Control plane

One record of what was approved: versions, policies, owners and the conditions of each release.

Release pipeline

Every change, to data, model, prompt, tool or policy, passes the same gates.

Policy propagation

Each rule declares its source, targets, latency, drift check, rollback and owner.

Observability

One request ID from the user through every agent, tool and source, into the SOC.

Runbooks and recovery

Tested restriction, rollback and revocation, run by your own team.

Operating model

The data group owns meaning, the cyber group owns labels and enforcement rules, the AI owner owns the capability, and the business owns the outcome.

Go deeper

The detail behind the architecture.

Open what you need: the capability map for assigning owners, the costs that arrive after approval, and how agentic delivery stays safe.

The capability map: 63 capabilities, mapped to the same layers

The ownership view of the same system shown at the top of this page.

Ownership gaps stall more programs than technology does. The worksheet lists every capability with a one-line description and blank columns for current owner, accountable owner, decision rights and gaps. It assigns no owners: the right owner depends on your organization.

AI and experience

The capability the four parts serve · 13

Reporting and analytics, Self-service exploration, Data-driven applications, Data science sandbox, Prompt and instruction library, Foundation models, Model adaptation, Agents, Agent orchestration, Agent memory, Agent evaluation, Agent catalog, Agent observability

Access and interfaces

The nervous system · 6

Data APIs, Virtualization and federation, AI gateway, Retrieval services, Agent tool interfaces, Command path for writes

Meaning and knowledge

The brain · 8

Metadata, Ontology and knowledge graph, Semantic layer, Information architecture, Master and reference data, Chunking and embeddings, Data marketplace and search, AI asset search

Data platform

The brain’s data products · 12

Batch integration, Streaming and messaging, Pipeline orchestration, Data pipelines, Schema detection, Data modeling, Data preparation, Data storage, Vector storage, Cloud hosting, Containers, Accelerated compute

Sources

Systems of record · 3

Purpose-built databases, Operational applications, External and web data

Security, across every layer

The immune system · 7

Identity and access for people, Identity for agents, Single sign-on and zero trust, Classification and labels, Data protection, Monitoring and logging, Threat detection and response

Orchestration and operation, across every layer

The body and control plane · 10

Data quality, Lineage, Data architecture standards, Responsible AI, DataOps, DevOps, Model and AI operations, FinOps, Release gates, Request evidence

Operating model

Underneath all four · 4

Data and AI strategy, Upskilling and training, Research and talent programs, External workforce

Total cost of ownership: twelve recurring costs after approval

Build, licenses, vendor fees, integration and pilot compute are visible at approval. Twelve recurring costs arrive after it, and the architecture above is what keeps them in bounds.

What gets approvedBuild cost and software licensesVendor fees and initial integrationPilot computeMostly one-offApproval: most business cases stop hereWhat ownership costs, every yearData and meaningData preparation and upkeepKnowledge and index maintenanceRunning at real volumeProduction model and API usageSupport, incidents and recoveryQualityEvaluation and drift monitoringHuman review and exceptionsControl and evidenceSecurity and agent identityCompliance and audit trailPeople and changeChange management and trainingCleaning up unsanctioned AI useExit and end of lifeExit planning and portabilityRetirement and decommissioning
Twelve recurring costs in six groups, none of them in the first approval. Swipe sideways to see the whole drawing.

The Connected Enterprise Data & AI Blueprint

Agentic delivery: faster code still needs authority, independent checks and learning

Coding agents can draft, test and execute changes within bounded tools and identities. The loop starts from governed intent, validates independently of the agent that made the change, releases under named authority and feeds what operation reveals back into intent.

01Governed intentOutcome, owner, scope,constraints, acceptance02Assemble contextVersioned, minimized,traceable sources03Plan and assessCross-layer impact,unknowns, recovery04Generate changeBounded tools, identity,workspace, budget05Validate independentlyKnown answers, tests,security, data checks06Authorize and releaseNamed authority, gates,canary, rollback07Observe and reconcileOutcome, drift, incidents,learning into intentCode and architectureData and ontologyPolicy and securityRuntime and decisionsProvenance and freshnessControl principle: the system may draft, test and execute within authority. People keep purpose, risk acceptance and release.
Agentic delivery is a controlled evidence loop. A faster implementation step does not remove the need for authority, independent validation or operational learning. Swipe sideways to see the whole drawing.

Data Is Not Just Code

The paper

The full reference implementation.

The paper sets out the architecture diagrams and product detail layer by layer, the security model for agents and the security operations center, and two use cases traced end to end: anti-money-laundering alert investigation at a bank, and this claims workflow at an insurer. Twenty-three pages, free, no form.

Next step

See how this would fit your stack.

Set up time with Richard to discuss one workflow, what is blocking it and whether there is a useful next step. The first conversation is free.