# sellinaxie/enterprise-agentic-ai-platform architecture

> Architecture diagram of the GitHub repository sellinaxie/enterprise-agentic-ai-platform, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sellinaxie/enterprise-agentic-ai-platform
- Repository: https://github.com/sellinaxie/enterprise-agentic-ai-platform

## Overview

V8D is an authenticated enterprise AI architecture and risk-assessment platform. Its main workflow accepts an assessment, retrieves grounded knowledge, executes deterministic or agentic analysis, applies runtime risk controls, and persists results for product views or human review. A separate knowledge workflow parses text or bounded document uploads, then chunks, embeds, and stores material for vector and GraphRAG retrieval; an opt-in policy connector reuses ingestion. Groups also capture identity, provider portability, evaluation, telemetry, and the frontend. Some route, workflow, and agent implementations were not sampled, so uncertain connections are omitted or marked unverified.

Main entry points: [`app/services/assessments.py`](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/services/assessments.py) (Assessment orchestration), [`app/rag/ingestion.py`](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/ingestion.py) (Knowledge ingestion), [`app/rag/retrieval.py`](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/retrieval.py) (Evidence retrieval), [`app/api/routes/knowledge.py`](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/routes/knowledge.py) (Knowledge endpoints)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_product["Assessment product"]
  node_api["FastAPI application<br/>[main.py]"]
  node_api_routes["Versioned API routes<br/>[router.py]"]
  node_assessment_routes["Assessment endpoints<br/>[assessments.py]"]
  node_assessment_service["Assessment orchestration<br/>[assessments.py]"]
  node_execution_router["Execution selection"]
  node_agents["Assessment agents"]
  node_workflow["Assessment workflows"]
  node_assessment_store[("Assessment persistence<br/>[assessments.py]")]
end

subgraph group_knowledge["Knowledge and retrieval"]
  node_knowledge_routes["Knowledge endpoints<br/>[knowledge.py]"]
  node_file_ingestion["File parsing<br/>[service.py]"]
  node_ingestion["Knowledge ingestion<br/>[ingestion.py]"]
  node_knowledge_store[("Knowledge storage")]
  node_retrieval["Evidence retrieval<br/>[retrieval.py]"]
  node_graph_retrieval["GraphRAG enrichment"]
  node_policy_connector["Policy connector"]
end

subgraph group_governance["Identity and governance"]
  node_review[("Human review queue<br/>[runtime_reviews.py]")]
  node_identity["Authentication and RBAC"]
  node_risk_gate["Runtime risk gates<br/>[gate.py]"]
end

subgraph group_platform["Model and runtime platform"]
  node_providers["Model providers"]
  node_evaluation["Assessment evaluation"]
  node_telemetry["Runtime telemetry<br/>[telemetry.py]"]
end

subgraph group_interface["Product interface"]
  node_frontend["Authenticated product UI"]
  node_showcase["Public showcase"]
end

node_user(("Analyst / reviewer"))

node_user -->|"uses"| node_frontend
node_frontend -->|"calls API"| node_api
node_api -->|"mounts routes"| node_api_routes
node_api_routes -->|"includes"| node_assessment_routes
node_assessment_routes -.->|"dispatches"| node_assessment_service
node_assessment_service -.->|"selects execution"| node_execution_router
node_execution_router -.->|"routes execution"| node_agents
node_execution_router -.->|"routes execution"| node_workflow
node_assessment_service -.->|"retrieves evidence"| node_retrieval
node_assessment_service -.->|"persists results"| node_assessment_store
node_assessment_service -.->|"checks risk"| node_risk_gate
node_assessment_service -.->|"queues review"| node_review
node_knowledge_routes -->|"accepts uploads"| node_file_ingestion
node_file_ingestion -->|"delegates ingestion"| node_ingestion
node_ingestion -->|"stores chunks"| node_knowledge_store
node_knowledge_routes -->|"ingests documents"| node_ingestion
node_knowledge_routes -->|"searches evidence"| node_retrieval
node_retrieval -->|"searches vectors"| node_knowledge_store
node_ingestion -.->|"enriches graph"| node_graph_retrieval
node_retrieval -.->|"combines retrieval"| node_graph_retrieval
node_policy_connector -->|"reuses ingestion"| node_ingestion
node_assessment_routes -->|"requires principal"| node_identity
node_frontend -->|"supports review"| node_review
node_providers -.->|"supplies generation"| node_assessment_service
node_evaluation -.->|"evaluates outcomes"| node_assessment_service
node_api -->|"exports signals"| node_telemetry
node_showcase -->|"presents walkthrough"| node_user

click node_api "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/main.py"
click node_api_routes "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/router.py"
click node_assessment_routes "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/routes/assessments.py"
click node_assessment_service "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/services/assessments.py"
click node_execution_router "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/services/execution_router.py"
click node_agents "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/agents"
click node_workflow "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/graph"
click node_assessment_store "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/assessments.py"
click node_review "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/runtime_reviews.py"
click node_knowledge_routes "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/routes/knowledge.py"
click node_file_ingestion "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/ingestion/service.py"
click node_ingestion "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/ingestion.py"
click node_knowledge_store "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/knowledge_chunks.py"
click node_retrieval "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/retrieval.py"
click node_graph_retrieval "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/knowledge_graph"
click node_policy_connector "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/connectors/policy_repository.py"
click node_identity "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/identity"
click node_risk_gate "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/runtime/gate.py"
click node_providers "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/providers"
click node_evaluation "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/evaluation"
click node_telemetry "https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/runtime/telemetry.py"
click node_frontend "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/frontend/app"
click node_showcase "https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/frontend/app/demo"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_api,node_api_routes,node_assessment_routes,node_assessment_service,node_execution_router,node_agents,node_workflow,node_assessment_store,node_user toneBlue
class node_knowledge_routes,node_file_ingestion,node_ingestion,node_knowledge_store,node_retrieval,node_graph_retrieval,node_policy_connector toneAmber
class node_review,node_identity,node_risk_gate toneMint
class node_providers,node_evaluation,node_telemetry toneRose
class node_frontend,node_showcase toneIndigo
```

## Components

### Assessment product

- [FastAPI application](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/main.py): `app/main.py`
- [Versioned API routes](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/router.py): `app/api/router.py`
- [Assessment endpoints](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/routes/assessments.py): `app/api/routes/assessments.py`
- [Assessment orchestration](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/services/assessments.py): `app/services/assessments.py`
- [Execution selection](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/services/execution_router.py): `app/services/execution_router.py`
- [Assessment agents](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/agents): `app/agents`
- [Assessment workflows](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/graph): `app/graph`
- [Assessment persistence](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/assessments.py): `app/repositories/assessments.py`

### Knowledge and retrieval

- [Knowledge endpoints](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/api/routes/knowledge.py): `app/api/routes/knowledge.py`
- [File parsing](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/ingestion/service.py): `app/ingestion/service.py`
- [Knowledge ingestion](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/ingestion.py): `app/rag/ingestion.py`
- [Knowledge storage](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/knowledge_chunks.py): `app/repositories/knowledge_chunks.py`
- [Evidence retrieval](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/rag/retrieval.py): `app/rag/retrieval.py`
- [GraphRAG enrichment](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/knowledge_graph): `app/knowledge_graph`
- [Policy connector](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/connectors/policy_repository.py): `app/connectors/policy_repository.py`

### Identity and governance

- [Human review queue](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/repositories/runtime_reviews.py): `app/repositories/runtime_reviews.py`
- [Authentication and RBAC](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/identity): `app/identity`
- [Runtime risk gates](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/runtime/gate.py): `app/runtime/gate.py`

### Model and runtime platform

- [Model providers](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/providers): `app/providers`
- [Assessment evaluation](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/app/evaluation): `app/evaluation`
- [Runtime telemetry](https://github.com/sellinaxie/enterprise-agentic-ai-platform/blob/main/app/runtime/telemetry.py): `app/runtime/telemetry.py`

### Product interface

- [Authenticated product UI](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/frontend/app): `frontend/app`
- [Public showcase](https://github.com/sellinaxie/enterprise-agentic-ai-platform/tree/main/frontend/app/demo): `frontend/app/demo`

### Other components

- **Analyst / reviewer**

## Connections

- Analyst / reviewer → Authenticated product UI: uses (evidence: `README.md`)
- Authenticated product UI → FastAPI application: calls API (evidence: `README.md`)
- FastAPI application → Versioned API routes: mounts routes (evidence: `app/main.py`)
- Versioned API routes → Assessment endpoints: includes (evidence: `app/api/router.py`)
- Assessment endpoints → Assessment orchestration: dispatches
- Assessment orchestration → Execution selection: selects execution
- Execution selection → Assessment agents: routes execution
- Execution selection → Assessment workflows: routes execution
- Assessment orchestration → Evidence retrieval: retrieves evidence
- Assessment orchestration → Assessment persistence: persists results
- Assessment orchestration → Runtime risk gates: checks risk
- Assessment orchestration → Human review queue: queues review
- Knowledge endpoints → File parsing: accepts uploads (evidence: `app/api/routes/knowledge.py`)
- File parsing → Knowledge ingestion: delegates ingestion (evidence: `app/ingestion/service.py`)
- Knowledge ingestion → Knowledge storage: stores chunks (evidence: `app/rag/ingestion.py`)
- Knowledge endpoints → Knowledge ingestion: ingests documents (evidence: `app/api/routes/knowledge.py`)
- Knowledge endpoints → Evidence retrieval: searches evidence (evidence: `app/api/routes/knowledge.py`)
- Evidence retrieval → Knowledge storage: searches vectors (evidence: `app/rag/retrieval.py`)
- Knowledge ingestion → GraphRAG enrichment: enriches graph
- Evidence retrieval → GraphRAG enrichment: combines retrieval
- Policy connector → Knowledge ingestion: reuses ingestion (evidence: `app/connectors/policy_repository.py`)
- Assessment endpoints → Authentication and RBAC: requires principal (evidence: `README.md`)
- Authenticated product UI → Human review queue: supports review (evidence: `README.md`)
- Model providers → Assessment orchestration: supplies generation
- Assessment evaluation → Assessment orchestration: evaluates outcomes
- FastAPI application → Runtime telemetry: exports signals (evidence: `README.md`)
- Public showcase → Analyst / reviewer: presents walkthrough (evidence: `README.md`)