# msft-innovation-hub-india/bfsi-multi-agent-health-insurance architecture

> Architecture diagram of the GitHub repository msft-innovation-hub-india/bfsi-multi-agent-health-insurance, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-05-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance
- Repository: https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance

## Overview

1. **Repository shape**
   - This is a two-part system: a **Python backend** that performs AI-assisted claim fraud analysis, and a **React/TypeScript frontend** that visualizes claims, evidence, and agent workflow.
   - The backend also includes **batch/demo entrypoints** and a **FastAPI API layer**, so it supports both command-line execution and interactive app usage.

2. **Primary backend orchestration path**
   - The main execution flow starts in `run_fraud_detection.py` or `main.py`, then moves into `orchestrator.py` / `workflow_manager.py`.
   - These modules coordinate the end-to-end claim pipeline: collect evidence, run multi-agent analysis, extract a final decision, and generate a report.

3. **Core domain and shared logic**
   - `core/` is the shared business-logic boundary.
   - `core/models.py` defines the domain objects such as claim data and fraud decision outputs.
   - `core/prompts.py`, `core/instructions.py`, and `core/queries.py` hold the LLM/agent prompt templates and retrieval queries, while `core/config.py` and root `config.py` centralize runtime settings.

4. **Service layer responsibilities**
   - `services/` contains reusable orchestration helpers rather than agent logic itself.
   - `agent_factory.py` builds the AutoGen agents, `evidence_collector.py` gathers source material from Azure systems, `decision_extractor.py` parses the final outcome from agent conversations, and `report_generator.py` formats the result for output.

5. **Specialized agent boundary**
   - `agents/` contains focused analysis modules for specific claim dimensions.
   - The README describes the collaborating roles: fraud detection, medical validation, billing validation, policy balance validation, exclusions validation, and final coordination.
   - The code files show additional specialization for **X-ray analysis**, **billing**, **claim processing**, and **patient summary** generation.

6. **Multi-agent decision flow**
   - The key architectural pattern is an **AutoGen GroupChat-style collaboration**.
   - Evidence is fed into multiple agents, each agent produces a perspective, and a final coordinator synthesizes them into one of the system outcomes: approved, rejected, or pending.
   - This makes the analysis pipeline conversational and modular rather than a single monolithic model call.

7. **External data and AI services**
   - The backend integrates with **Azure AI Search** for document retrieval, **Azure Blob Storage** for stored claim/X-ray assets, **Azure OpenAI** for reasoning, and **Azure Custom Vision** for X-ray classification.
   - Deployment notes also show **Azure Cosmos DB** used for claim/state persistence in the hosted API setup.
   - Managed identity is the main runtime auth model in Azure deployment, reducing secret handling in production.

8. **Document indexing subsystem**
   - `Index-Creation/` and `index-creation-portal/` define the ingestion/search preparation side of the system.
   - Three search indexes are expected: one for bills, one for claims/exclusions/inclusions, and one for diagnostic data.
   - This is a distinct pre-processing boundary: documents are indexed first, then queried during claim analysis.

9. **Backend API layer**
   - `api/` contains the FastAPI-facing runtime pieces: `main.py`, Cosmos integration, and a real-time processor.
   - This layer likely exposes endpoints for triggering claim processing, polling results, and updating persisted claim state.
   - It acts as the bridge between the frontend and the AI/workflow subsystems.

10. **Frontend architecture**
   - `health-insurance-frontend/` is a standalone Vite React app written in TypeScript.
   - Its components are organized around the insurer workflow: dashboard stats, claim analysis, evidence analysis, patient summary, system status, and workflow visualization.
   - The frontend is presentation-first; it consumes APIs and local demo data rather than implementing analysis logic.

11. **Frontend data and utility boundaries**
   - `src/api/` contains client-side API adapters, including claim APIs and realtime hooks.
   - `src/utils/` provides loaders and transformers for claim data, logs, markdown simplification, and Azure storage helpers.
   - `src/types/` defines the frontend contract for claims, dashboard data, and underwriting-related shapes.

12. **Sample data and operational demo assets**
   - The `Data/` directory contains example PDFs for bills, discharge summaries, medical records, exclusions, and X-rays.
   - These assets support local testing, document viewer demos, and end-to-end workflow validation without needing a live claims feed.

13. **Deployment and runtime packaging**
   - `Dockerfile.backend` and `Dockerfile.frontend` package the two runtimes separately.
   - The frontend is served through Nginx in a multi-stage build, while the backend runs as Python/FastAPI with Uvicorn.
   - The repo is clearly designed for Azure Container Apps deployment with external ingress and managed identity.

14. **Architecture summary for a diagram**
   - A good diagram should show: **documents and X-rays entering Azure storage/search**, **backend orchestration pulling evidence and invoking multiple AI agents**, **decision/report generation**, and **frontend visualization of the workflow and results**.
   - The important boundaries are: **ingestion/indexing**, **analysis orchestration**, **API/persistence**, and **UI presentation**.

Main entry points: [`api/main.py`](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/main.py) (API main), [`health-insurance-frontend/src/App.tsx`](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/App.tsx) (React app), [`services/agent_factory.py`](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/agent_factory.py) (Agent factory), [`workflow_manager.py`](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/workflow_manager.py) (Workflow manager)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_backend["Backend AI system"]
  node_run_fraud_detection["Run fraud<br/>CLI entrypoint"]
  node_main_py["Main app<br/>Python entrypoint<br/>[main.py]"]
  node_orchestrator["Orchestrator<br/>workflow coordinator<br/>[orchestrator.py]"]
  node_workflow_manager["Workflow manager<br/>workflow engine"]
  node_core_models["Domain models<br/>shared schema<br/>[models.py]"]
  node_core_prompts["Prompts<br/>LLM templates<br/>[prompts.py]"]
  node_core_instructions["Instructions<br/>agent rules<br/>[instructions.py]"]
  node_core_queries["Queries<br/>[queries.py]"]
  node_core_config["Core config<br/>runtime settings<br/>[config.py]"]
  node_agent_factory["Agent factory<br/>agent builder<br/>[agent_factory.py]"]
  node_evidence_collector["Evidence collector<br/>retrieval service"]
  node_decision_extractor["Decision extractor<br/>parser"]
  node_report_generator["Report generator<br/>output service"]
  node_claim_agent["Claim agent<br/>analysis agent<br/>[claim.py]"]
  node_bill_agent["Bill agent<br/>analysis agent<br/>[bill.py]"]
  node_xray_agent["X-ray agent<br/>vision agent<br/>[xrayanalysis.py]"]
  node_patient_summary["Patient summary<br/>analysis agent<br/>[patientsummary.py]"]
  node_api_main["API main<br/>FastAPI app<br/>[main.py]"]
  node_cosmos_service["Cosmos service<br/>persistence adapter<br/>[cosmos_service.py]"]
  node_realtime_processor["Realtime processor<br/>stream handler"]
end

subgraph group_indexing["Indexing pipeline"]
  node_index_creation["Index creation<br/>ingestion pipeline<br/>[create_index.py]"]
  node_index_config["Index config<br/>index schema"]
  node_sample_docs[("Sample docs<br/>source documents")]
end

subgraph group_frontend["Frontend app"]
  node_frontend_app["React app<br/>Vite UI<br/>[App.tsx]"]
  node_dashboard["Dashboard<br/>UI view"]
  node_claim_analysis["Claim analysis<br/>UI module<br/>[ClaimAnalysis.tsx]"]
  node_workflow_ui["Workflow view<br/>UI module"]
  node_frontend_api["API client<br/>client adapter<br/>[claimsApi.ts]"]
  node_frontend_utils["UI utils<br/>transform helpers<br/>[claimDataLoader.ts]"]
end

node_run_fraud_detection -->|"starts"| node_orchestrator
node_main_py -->|"runs"| node_api_main
node_orchestrator -->|"delegates"| node_workflow_manager
node_workflow_manager -->|"collects"| node_evidence_collector
node_workflow_manager -->|"builds agents"| node_agent_factory
node_agent_factory -->|"instantiates"| node_claim_agent
node_agent_factory -->|"instantiates"| node_bill_agent
node_agent_factory -->|"instantiates"| node_xray_agent
node_agent_factory -->|"instantiates"| node_patient_summary
node_claim_agent -->|"uses"| node_core_prompts
node_bill_agent -->|"follows"| node_core_instructions
node_xray_agent -->|"exchanges"| node_core_models
node_patient_summary -->|"exchanges"| node_core_models
node_evidence_collector -->|"queries"| node_core_queries
node_evidence_collector -->|"reads"| node_sample_docs
node_evidence_collector -.->|"depends on"| node_index_creation
node_index_creation -->|"configured by"| node_index_config
node_index_creation -->|"indexes"| node_sample_docs
node_workflow_manager -->|"extracts decision"| node_decision_extractor
node_decision_extractor -->|"feeds"| node_report_generator
node_api_main -->|"persists"| node_cosmos_service
node_api_main -->|"streams"| node_realtime_processor
node_api_main -->|"triggers"| node_workflow_manager
node_frontend_app -->|"renders"| node_dashboard
node_frontend_app -->|"renders"| node_claim_analysis
node_frontend_app -->|"renders"| node_workflow_ui
node_frontend_app -->|"calls"| node_frontend_api
node_frontend_app -->|"loads"| node_frontend_utils
node_frontend_api -->|"consumes"| node_api_main
node_frontend_utils -.->|"demo data"| node_sample_docs
node_core_config -->|"configures"| node_api_main
node_core_config -->|"configures"| node_orchestrator

click node_run_fraud_detection "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/run_fraud_detection.py"
click node_main_py "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/main.py"
click node_orchestrator "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/orchestrator.py"
click node_workflow_manager "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/workflow_manager.py"
click node_core_models "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/models.py"
click node_core_prompts "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/prompts.py"
click node_core_instructions "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/instructions.py"
click node_core_queries "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/queries.py"
click node_core_config "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/config.py"
click node_agent_factory "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/agent_factory.py"
click node_evidence_collector "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/evidence_collector.py"
click node_decision_extractor "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/decision_extractor.py"
click node_report_generator "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/report_generator.py"
click node_claim_agent "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/claim.py"
click node_bill_agent "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/bill.py"
click node_xray_agent "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/xrayanalysis.py"
click node_patient_summary "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/patientsummary.py"
click node_api_main "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/main.py"
click node_cosmos_service "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/cosmos_service.py"
click node_realtime_processor "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/realtime_processor.py"
click node_index_creation "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Index-Creation/create_index.py"
click node_index_config "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Index-Creation/doc_index_config.py"
click node_sample_docs "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Data/Discharge-Summary.pdf"
click node_frontend_app "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/App.tsx"
click node_dashboard "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/InsurerDashboard.tsx"
click node_claim_analysis "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/components/ClaimAnalysis.tsx"
click node_workflow_ui "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/components/MultiAgentWorkflowPipeline.tsx"
click node_frontend_api "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/api/claimsApi.ts"
click node_frontend_utils "https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/utils/claimDataLoader.ts"

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_run_fraud_detection,node_main_py,node_orchestrator,node_workflow_manager,node_core_models,node_core_prompts,node_core_instructions,node_core_queries,node_core_config,node_agent_factory,node_evidence_collector,node_decision_extractor,node_report_generator,node_claim_agent,node_bill_agent,node_xray_agent,node_patient_summary,node_api_main,node_cosmos_service,node_realtime_processor toneBlue
class node_index_creation,node_index_config,node_sample_docs toneAmber
class node_frontend_app,node_dashboard,node_claim_analysis,node_workflow_ui,node_frontend_api,node_frontend_utils toneMint
```

## Components

### Backend AI system

Python orchestration, agents, API, and shared domain logic for claim fraud analysis.

- [Run fraud](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/run_fraud_detection.py): CLI entrypoint · Batch/demo entrypoint for starting fraud analysis from the command line. · `run_fraud_detection.py`
- [Main app](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/main.py): Python entrypoint · Top-level Python launcher for the backend runtime. · `main.py`
- [Orchestrator](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/orchestrator.py): workflow coordinator · Coordinates the end-to-end claim analysis pipeline. · `orchestrator.py`
- [Workflow manager](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/workflow_manager.py): workflow engine · Manages multi-step claim processing and agent handoffs. · `workflow_manager.py`
- [Domain models](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/models.py): shared schema · Claim and fraud-decision objects shared across backend layers. · `core/models.py`
- [Prompts](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/prompts.py): LLM templates · Prompt templates used to steer agent reasoning. · `core/prompts.py`
- [Instructions](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/instructions.py): agent rules · System instructions and behavioral guidance for the agents. · `core/instructions.py`
- [Queries](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/queries.py): retrieval queries · Search and retrieval queries used during evidence gathering. · `core/queries.py`
- [Core config](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/core/config.py): runtime settings · Shared configuration for the backend analysis runtime. · `core/config.py`
- [Agent factory](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/agent_factory.py): agent builder · Constructs the AutoGen agents used in the collaborative workflow. · `services/agent_factory.py`
- [Evidence collector](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/evidence_collector.py): retrieval service · Gathers claim evidence from Azure-backed sources and search. · `services/evidence_collector.py`
- [Decision extractor](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/decision_extractor.py): parser · Extracts the final fraud outcome from agent conversation output. · `services/decision_extractor.py`
- [Report generator](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/services/report_generator.py): output service · Formats the analysis result into a report for users or downstream systems. · `services/report_generator.py`
- [Claim agent](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/claim.py): analysis agent · Primary claim reasoning and fraud assessment specialist. · `agents/claim.py`
- [Bill agent](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/bill.py): analysis agent · Billing-focused validation and line-item scrutiny specialist. · `agents/bill.py`
- [X-ray agent](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/xrayanalysis.py): vision agent · X-ray classification and image-based claim evidence specialist. · `agents/xrayanalysis.py`
- [Patient summary](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/agents/patientsummary.py): analysis agent · Generates a concise patient-centric summary for the workflow. · `agents/patientsummary.py`
- [API main](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/main.py): FastAPI app · FastAPI runtime layer that exposes backend processing endpoints. · `api/main.py`
- [Cosmos service](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/cosmos_service.py): persistence adapter · Persistence integration for claim and workflow state in Cosmos DB. · `api/cosmos_service.py`
- [Realtime processor](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/api/realtime_processor.py): stream handler · Handles incremental processing and live updates for claim runs. · `api/realtime_processor.py`

### Indexing pipeline

Document preparation and search index creation used before claim analysis.

- [Index creation](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Index-Creation/create_index.py): ingestion pipeline · Builds the search indexes used to prepare documents for retrieval. · `Index-Creation/create_index.py`
- [Index config](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Index-Creation/doc_index_config.py): index schema · Defines document index configuration and field layout. · `Index-Creation/doc_index_config.py`
- [Sample docs](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/Data/Discharge-Summary.pdf): source documents · Representative claim, medical, and billing PDFs used for indexing and demo runs. · `Data/Discharge-Summary.pdf`

### Frontend app

React/TypeScript UI for claim review, workflow visualization, and demo data.

- [React app](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/App.tsx): Vite UI · Frontend shell for the insurer workflow visualization and demos. · `health-insurance-frontend/src/App.tsx`
- [Dashboard](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/InsurerDashboard.tsx): UI view · High-level claim status, stats, and summary presentation. · `health-insurance-frontend/src/InsurerDashboard.tsx`
- [Claim analysis](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/components/ClaimAnalysis.tsx): UI module · Claim review and evidence analysis screens. · `health-insurance-frontend/src/components/ClaimAnalysis.tsx`
- [Workflow view](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/components/MultiAgentWorkflowPipeline.tsx): UI module · Agent workflow, conversation, and pipeline visualization. · `health-insurance-frontend/src/components/MultiAgentWorkflowPipeline.tsx`
- [API client](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/api/claimsApi.ts): client adapter · Client-side adapters for claims APIs and realtime hooks. · `health-insurance-frontend/src/api/claimsApi.ts`
- [UI utils](https://github.com/msft-innovation-hub-india/bfsi-multi-agent-health-insurance/blob/main/health-insurance-frontend/src/utils/claimDataLoader.ts): transform helpers · Loaders and transformers for claims, logs, markdown, and Azure storage. · `health-insurance-frontend/src/utils/claimDataLoader.ts`

## Connections

- Run fraud → Orchestrator: starts · CLI execution enters the main workflow coordinator.
- Main app → API main: runs · Primary backend startup can enter the FastAPI layer.
- Orchestrator → Workflow manager: delegates · Orchestrator hands step control to the workflow manager.
- Workflow manager → Evidence collector: collects · Workflow begins by gathering claim evidence.
- Workflow manager → Agent factory: builds agents · Workflow creates the collaborating analysis agents.
- Agent factory → Claim agent: instantiates · Factory assembles the primary claim analysis agent.
- Agent factory → Bill agent: instantiates · Factory assembles the billing validation agent.
- Agent factory → X-ray agent: instantiates · Factory assembles the X-ray analysis agent.
- Agent factory → Patient summary: instantiates · Factory assembles the patient summary agent.
- Claim agent → Prompts: uses · Agent reasoning is guided by shared prompt templates.
- Bill agent → Instructions: follows · Agent behavior follows shared instructions.
- X-ray agent → Domain models: exchanges · Agent consumes and emits shared claim decision objects.
- Patient summary → Domain models: exchanges · Agent consumes and emits shared claim decision objects.
- Evidence collector → Queries: queries · Retrieval is driven by shared search/query definitions.
- Evidence collector → Sample docs: reads · Evidence is sourced from indexed claim documents and assets.
- Evidence collector → Index creation: depends on · Collected evidence assumes the search indexes exist.
- Index creation → Index config: configured by · Index creation uses the index schema definition.
- Index creation → Sample docs: indexes · Source PDFs and assets are ingested into search indexes.
- Workflow manager → Decision extractor: extracts decision · Conversation output is parsed into a final outcome.
- Decision extractor → Report generator: feeds · Parsed decision is formatted into a report.
- API main → Cosmos service: persists · API layer stores and retrieves claim state.
- API main → Realtime processor: streams · API layer supports live claim processing updates.
- API main → Workflow manager: triggers · API requests can start backend workflow runs.
- React app → Dashboard: renders · App composes the dashboard and main workflow screens.
- React app → Claim analysis: renders · App hosts the claim analysis and evidence review screens.
- React app → Workflow view: renders · App hosts the agent workflow and conversation visualizations.
- React app → API client: calls · UI uses API adapters to reach backend endpoints.
- React app → UI utils: loads · UI uses helper utilities for demo data and transformations.
- API client → API main: consumes · Client adapters communicate with the backend API.
- UI utils → Sample docs: demo data · UI loaders can work with local sample documents and logs.
- Core config → API main: configures · Runtime settings are shared with the API deployment.
- Core config → Orchestrator: configures · Workflow execution uses shared backend settings.
