# parva-28/bob-ai-hackathon-duckduckgo architecture

> Architecture diagram of the GitHub repository parva-28/bob-ai-hackathon-duckduckgo, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/parva-28/bob-ai-hackathon-duckduckgo
- Repository: https://github.com/parva-28/bob-ai-hackathon-duckduckgo

## Overview

YieldGuard is a semiconductor-yield investigation assistant: engineers inspect fleet and lot data, gather wafer-map, sensor, historical-case, and telemetry evidence, then review ranked root-cause hypotheses and containment actions. The web console fronts a FastAPI layer over MCP tools; IBM Bob can invoke those tools directly. The map preserves the documented vision, anomaly, planned-lot risk, conformal-abstention, telemetry, and playbook capabilities. Some UI-to-API and model-to-reasoning wiring is not shown in the excerpts, so those links are omitted or marked unverified.

Main entry points: [`src/mcp_server/server.py`](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/server.py) (MCP Tool Server), [`src/api/main.py`](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/api/main.py) (FastAPI Backend), [`src/mcp_server/adapters.py`](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/adapters.py) (Tool Adapters), [`src/web/app/overview/page.tsx`](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/overview/page.tsx) (Analyst Console)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_console["Analyst Console"]
  node_web["Analyst Console<br/>[page.tsx]"]
  node_investigation["Lot Investigation<br/>[page.tsx]"]
  node_lotanalysis["Lot Analysis<br/>[page.tsx]"]
  node_batchrisk["Batch Risk<br/>[page.tsx]"]
  node_equipment["Equipment View<br/>[page.tsx]"]
  node_pipeline["Pipeline Trace<br/>[page.tsx]"]
  node_playbook["Action Playbook<br/>[page.tsx]"]
end

subgraph group_service["Tool Services"]
  node_api["FastAPI Backend<br/>[main.py]"]
  node_validation["Input Validation<br/>[validate.py]"]
  node_mcp["MCP Tool Server<br/>[server.py]"]
  node_adapters["Tool Adapters<br/>[adapters.py]"]
  node_parammap["Parameter Mapping<br/>[param_map.py]"]
  node_provenance["Provenance<br/>[provenance.py]"]
  node_lotsensors["Lot Sensors<br/>[lot_sensors.py]"]
end

subgraph group_evidence["Evidence Stores"]
  node_stores[("Case and Telemetry Stores<br/>[stores.py]")]
end

subgraph group_analytics["ML Analytics"]
  node_wafer["Wafer Classifier<br/>[classifier.py]"]
  node_wafermodel["Wafer CNN<br/>[model.py]"]
  node_anomaly["Sensor and Batch Risk<br/>[anomaly.py]"]
  node_cmp["CMP Prediction<br/>[predict.py]"]
  node_abstain["Conformal Abstention<br/>[abstain.py]"]
end

subgraph group_reasoning["Reasoning"]
  node_reasoner["Root-Cause Reasoning<br/>[reasoning.py]"]
end

node_engineer(("Yield Engineer"))
node_bob(("IBM Bob"))

node_engineer -->|"inspects lots"| node_web
node_engineer -->|"investigates lot"| node_investigation
node_engineer -->|"dispatches actions"| node_playbook
node_web -.->|"requests data"| node_api
node_investigation -.->|"requests analysis"| node_api
node_api -->|"uses tool functions"| node_mcp
node_api -->|"validates inputs"| node_validation
node_bob -->|"calls tools"| node_mcp
node_mcp -->|"dispatches tools"| node_adapters
node_mcp -->|"maps parameters"| node_parammap
node_mcp -->|"records provenance"| node_provenance
node_mcp -->|"uses lot sensors"| node_lotsensors
node_adapters -->|"uses stores"| node_stores
node_adapters -->|"classifies maps"| node_wafer
node_adapters -->|"predicts CMP"| node_cmp
node_adapters -.->|"scores sensors"| node_anomaly
node_wafer -->|"runs model"| node_wafermodel
node_cmp -->|"applies gates"| node_abstain
node_mcp -.->|"ranks hypotheses"| node_reasoner
node_anomaly -.->|"matches historical cases"| node_stores
node_equipment -.->|"loads telemetry"| node_api
node_batchrisk -.->|"checks planned lots"| node_api
node_pipeline -.->|"runs traced analysis"| node_api

click node_web "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/overview/page.tsx"
click node_investigation "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/investigation/page.tsx"
click node_lotanalysis "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/lot-analysis/page.tsx"
click node_batchrisk "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/batch-risk/page.tsx"
click node_equipment "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/equipment/page.tsx"
click node_pipeline "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/pipeline/page.tsx"
click node_playbook "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/playbook/page.tsx"
click node_api "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/api/main.py"
click node_validation "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/api/validate.py"
click node_mcp "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/server.py"
click node_adapters "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/adapters.py"
click node_parammap "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/param_map.py"
click node_provenance "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/provenance.py"
click node_lotsensors "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/lot_sensors.py"
click node_stores "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/stores.py"
click node_wafer "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/vision/classifier.py"
click node_wafermodel "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/vision/model.py"
click node_anomaly "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/tabular/anomaly.py"
click node_cmp "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/cmp/predict.py"
click node_abstain "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/cmp/abstain.py"
click node_reasoner "https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/reasoning/reasoning.py"

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_web,node_investigation,node_lotanalysis,node_batchrisk,node_equipment,node_pipeline,node_playbook toneBlue
class node_api,node_validation,node_mcp,node_adapters,node_parammap,node_provenance,node_lotsensors toneAmber
class node_stores toneMint
class node_wafer,node_wafermodel,node_anomaly,node_cmp,node_abstain toneRose
class node_reasoner,node_engineer,node_bob toneIndigo
```

## Components

### Analyst Console

- [Analyst Console](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/overview/page.tsx): `src/web/app/overview/page.tsx`
- [Lot Investigation](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/investigation/page.tsx): `src/web/app/investigation/page.tsx`
- [Lot Analysis](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/lot-analysis/page.tsx): `src/web/app/lot-analysis/page.tsx`
- [Batch Risk](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/batch-risk/page.tsx): `src/web/app/batch-risk/page.tsx`
- [Equipment View](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/equipment/page.tsx): `src/web/app/equipment/page.tsx`
- [Pipeline Trace](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/pipeline/page.tsx): `src/web/app/pipeline/page.tsx`
- [Action Playbook](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/web/app/playbook/page.tsx): `src/web/app/playbook/page.tsx`

### Tool Services

- [FastAPI Backend](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/api/main.py): `src/api/main.py`
- [Input Validation](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/api/validate.py): `src/api/validate.py`
- [MCP Tool Server](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/server.py): `src/mcp_server/server.py`
- [Tool Adapters](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/adapters.py): `src/mcp_server/adapters.py`
- [Parameter Mapping](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/param_map.py): `src/mcp_server/param_map.py`
- [Provenance](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/provenance.py): `src/mcp_server/provenance.py`
- [Lot Sensors](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/lot_sensors.py): `src/mcp_server/lot_sensors.py`

### Evidence Stores

- [Case and Telemetry Stores](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/mcp_server/stores.py): `src/mcp_server/stores.py`

### ML Analytics

- [Wafer Classifier](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/vision/classifier.py): `src/models/vision/classifier.py`
- [Wafer CNN](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/vision/model.py): `src/models/vision/model.py`
- [Sensor and Batch Risk](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/tabular/anomaly.py): `src/models/tabular/anomaly.py`
- [CMP Prediction](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/cmp/predict.py): `src/models/cmp/predict.py`
- [Conformal Abstention](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/models/cmp/abstain.py): `src/models/cmp/abstain.py`

### Reasoning

- [Root-Cause Reasoning](https://github.com/parva-28/bob-ai-hackathon-duckduckgo/blob/main/src/reasoning/reasoning.py): `src/reasoning/reasoning.py`

### Other components

- **Yield Engineer**
- **IBM Bob**

## Connections

- Yield Engineer → Analyst Console: inspects lots (evidence: `src/web/app/overview/page.tsx`)
- Yield Engineer → Lot Investigation: investigates lot
- Yield Engineer → Action Playbook: dispatches actions (evidence: `src/web/app/playbook/page.tsx`)
- Analyst Console → FastAPI Backend: requests data
- Lot Investigation → FastAPI Backend: requests analysis
- FastAPI Backend → MCP Tool Server: uses tool functions (evidence: `src/api/main.py`)
- FastAPI Backend → Input Validation: validates inputs (evidence: `src/api/main.py`)
- IBM Bob → MCP Tool Server: calls tools (evidence: `README.md`)
- MCP Tool Server → Tool Adapters: dispatches tools (evidence: `src/mcp_server/server.py`)
- MCP Tool Server → Parameter Mapping: maps parameters (evidence: `src/mcp_server/server.py`)
- MCP Tool Server → Provenance: records provenance (evidence: `src/mcp_server/server.py`)
- MCP Tool Server → Lot Sensors: uses lot sensors (evidence: `src/mcp_server/server.py`)
- Tool Adapters → Case and Telemetry Stores: uses stores (evidence: `src/mcp_server/adapters.py`)
- Tool Adapters → Wafer Classifier: classifies maps (evidence: `src/mcp_server/adapters.py`)
- Tool Adapters → CMP Prediction: predicts CMP (evidence: `src/mcp_server/adapters.py`)
- Tool Adapters → Sensor and Batch Risk: scores sensors
- Wafer Classifier → Wafer CNN: runs model (evidence: `src/models/vision/classifier.py`)
- CMP Prediction → Conformal Abstention: applies gates (evidence: `src/models/cmp/predict.py`)
- MCP Tool Server → Root-Cause Reasoning: ranks hypotheses
- Sensor and Batch Risk → Case and Telemetry Stores: matches historical cases
- Equipment View → FastAPI Backend: loads telemetry
- Batch Risk → FastAPI Backend: checks planned lots
- Pipeline Trace → FastAPI Backend: runs traced analysis
