# rudikcloud/ai-incident-intelligence architecture

> Architecture diagram of the GitHub repository rudikcloud/ai-incident-intelligence, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/rudikcloud/ai-incident-intelligence
- Repository: https://github.com/rudikcloud/ai-incident-intelligence

## Overview

This is an incident-triage ML lifecycle: controlled failure scenarios drive telemetry collection and labeled dataset generation; validated measurements become engineered features for baseline and trained root-cause/incident-type predictions. Evaluation compares both approaches, while the FastAPI endpoint returns top-k rankings, confidence, and feature evidence. The graph shows the documented workflow and source-backed calls; deployment infrastructure and several collector internals were not sampled, so no additional runtime links are inferred.

Main entry points: [`src/eval/evaluate.py`](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/eval/evaluate.py) (Model evaluation), [`src/collect/generate_dataset.py`](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/collect/generate_dataset.py) (Scenario collector), [`src/serve/app.py`](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/serve/app.py) (Inference API), [`src/features/build_features.py`](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/features/build_features.py) (Feature engineering)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_collection["Telemetry collection"]
  node_collector["Scenario collector"]
end

subgraph group_features["Dataset and features"]
  node_dataset[("Incident dataset<br/>[incidents.csv]")]
  node_schema["Schema validation<br/>[dataset.py]"]
  node_engineering["Feature engineering<br/>[build_features.py]"]
end

subgraph group_models["Prediction models"]
  node_baseline["Heuristic baseline<br/>[baseline.py]"]
  node_training["Model training<br/>[train.py]"]
  node_artifact[("Model bundle")]
end

subgraph group_evaluation["Evaluation"]
  node_evaluation["Model evaluation<br/>[evaluate.py]"]
  node_metrics["Evaluation metrics<br/>[metrics.py]"]
  node_report["Evaluation report<br/>[eval.md]"]
end

subgraph group_serving["Inference API"]
  node_api["Inference API<br/>[app.py]"]
  node_response["Triage results"]
end

node_platform(("Failure platform"))
node_client(("API client"))

node_platform -->|"supplies telemetry"| node_collector
node_collector -->|"injects failures, runs workload"| node_platform
node_collector -->|"appends labeled rows"| node_dataset
node_collector -->|"uses schema columns"| node_schema
node_dataset -->|"validated by"| node_schema
node_schema -->|"provides features"| node_engineering
node_engineering -->|"prepares training features"| node_training
node_training -->|"saves models"| node_artifact
node_client -->|"submits incident"| node_api
node_api -->|"builds request features"| node_engineering
node_api -->|"loads models"| node_artifact
node_api -->|"returns rankings and evidence"| node_response
node_dataset -->|"evaluated against"| node_evaluation
node_evaluation -->|"loads engineered data"| node_engineering
node_evaluation -->|"scores heuristic predictions"| node_baseline
node_evaluation -->|"loads or trains models"| node_training
node_evaluation -->|"computes metrics"| node_metrics
node_evaluation -->|"writes results"| node_report

click node_collector "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/collect/generate_dataset.py"
click node_dataset "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/data/incidents.csv"
click node_schema "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/features/dataset.py"
click node_engineering "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/features/build_features.py"
click node_baseline "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/models/baseline.py"
click node_training "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/models/train.py"
click node_evaluation "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/eval/evaluate.py"
click node_metrics "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/eval/metrics.py"
click node_report "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/reports/eval.md"
click node_api "https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/serve/app.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_collector,node_client toneBlue
class node_dataset,node_schema,node_engineering toneAmber
class node_baseline,node_training,node_artifact toneMint
class node_evaluation,node_metrics,node_report toneRose
class node_api,node_response,node_platform toneIndigo
```

## Components

### Telemetry collection

- [Scenario collector](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/collect/generate_dataset.py): `src/collect/generate_dataset.py`

### Dataset and features

- [Incident dataset](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/data/incidents.csv): `data/incidents.csv`
- [Schema validation](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/features/dataset.py): `src/features/dataset.py`
- [Feature engineering](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/features/build_features.py): `src/features/build_features.py`

### Prediction models

- [Heuristic baseline](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/models/baseline.py): `src/models/baseline.py`
- [Model training](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/models/train.py): `src/models/train.py`
- **Model bundle**

### Evaluation

- [Model evaluation](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/eval/evaluate.py): `src/eval/evaluate.py`
- [Evaluation metrics](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/eval/metrics.py): `src/eval/metrics.py`
- [Evaluation report](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/reports/eval.md): `reports/eval.md`

### Inference API

- [Inference API](https://github.com/rudikcloud/ai-incident-intelligence/blob/main/src/serve/app.py): `src/serve/app.py`
- **Triage results**

### Other components

- **Failure platform**
- **API client**

## Connections

- Failure platform → Scenario collector: supplies telemetry (evidence: `README.md`)
- Scenario collector → Failure platform: injects failures, runs workload (evidence: `src/collect/generate_dataset.py`)
- Scenario collector → Incident dataset: appends labeled rows (evidence: `README.md`)
- Scenario collector → Schema validation: uses schema columns (evidence: `src/collect/generate_dataset.py`)
- Incident dataset → Schema validation: validated by (evidence: `src/features/dataset.py`)
- Schema validation → Feature engineering: provides features (evidence: `src/features/build_features.py`)
- Feature engineering → Model training: prepares training features (evidence: `src/models/train.py`)
- Model training → Model bundle: saves models (evidence: `src/models/train.py`)
- API client → Inference API: submits incident (evidence: `README.md`)
- Inference API → Feature engineering: builds request features (evidence: `src/serve/app.py`)
- Inference API → Model bundle: loads models (evidence: `src/serve/app.py`)
- Inference API → Triage results: returns rankings and evidence (evidence: `src/serve/app.py`)
- Incident dataset → Model evaluation: evaluated against (evidence: `src/eval/evaluate.py`)
- Model evaluation → Feature engineering: loads engineered data (evidence: `src/eval/evaluate.py`)
- Model evaluation → Heuristic baseline: scores heuristic predictions (evidence: `src/eval/evaluate.py`)
- Model evaluation → Model training: loads or trains models (evidence: `src/eval/evaluate.py`)
- Model evaluation → Evaluation metrics: computes metrics (evidence: `src/eval/evaluate.py`)
- Model evaluation → Evaluation report: writes results (evidence: `README.md`)
