# gozdekcr/message-to-crm-extractor architecture

> Architecture diagram of the GitHub repository gozdekcr/message-to-crm-extractor, 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/gozdekcr/message-to-crm-extractor
- Repository: https://github.com/gozdekcr/message-to-crm-extractor

## Overview

This is a small, rule-based property-message extractor with a browser demo and a standalone Python implementation. The documented workflow takes a customer message through relevance filtering and field extraction, then flags ambiguity and missing information for agent review before the agent updates the CRM. The README documents these stages, but no source excerpts were provided, so the edges below rely on that documentation; the CRM API is a future integration, not part of the current implementation.

Main entry points: [`demo`](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo) (Field extraction), [`demo/index.html`](https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/index.html) (Browser demo), [`demo/extractor.py`](https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/extractor.py) (Python extractor)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_extraction["Extraction"]
  node_message["Customer message"]
  node_relevance["Relevance filter"]
  node_field_extraction["Field extraction"]
  node_confidence["Confidence flags"]
  node_missing_fields["Missing fields"]
end

subgraph group_review["Agent review"]
  node_structured_output["Structured fields"]
end

subgraph group_implementations["Implementations"]
  node_browser_demo["Browser demo<br/>[index.html]"]
  node_python_extractor["Python extractor<br/>[extractor.py]"]
end

node_customer(("Customer"))
node_agent(("Agent"))
node_crm_record[("CRM record")]
node_crm_api["CRM API"]

node_customer -->|"sends"| node_message
node_message -->|"checks relevance"| node_relevance
node_relevance -->|"extracts fields"| node_field_extraction
node_field_extraction -->|"flags ambiguity"| node_confidence
node_field_extraction -->|"detects gaps"| node_missing_fields
node_confidence -->|"annotates fields"| node_structured_output
node_missing_fields -->|"identifies gaps"| node_structured_output
node_agent -->|"reviews"| node_structured_output
node_agent -->|"updates manually"| node_crm_record
node_browser_demo -.->|"implements"| node_field_extraction
node_python_extractor -->|"implements"| node_field_extraction
node_crm_api -.->|"would update"| node_crm_record

click node_message "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_relevance "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_field_extraction "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_confidence "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_missing_fields "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_structured_output "https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo"
click node_browser_demo "https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/index.html"
click node_python_extractor "https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/extractor.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_message,node_relevance,node_field_extraction,node_confidence,node_missing_fields toneBlue
class node_structured_output,node_crm_record toneAmber
class node_browser_demo,node_python_extractor,node_crm_api toneMint
class node_customer,node_agent toneIndigo
```

## Components

### Extraction

- [Customer message](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`
- [Relevance filter](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`
- [Field extraction](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`
- [Confidence flags](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`
- [Missing fields](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`

### Agent review

- [Structured fields](https://github.com/gozdekcr/message-to-crm-extractor/tree/main/demo): `demo`

### Implementations

- [Browser demo](https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/index.html): `demo/index.html`
- [Python extractor](https://github.com/gozdekcr/message-to-crm-extractor/blob/main/demo/extractor.py): `demo/extractor.py`

### Other components

- **Customer**
- **Agent**
- **CRM record**
- **CRM API**

## Connections

- Customer → Customer message: sends (evidence: `README.md`)
- Customer message → Relevance filter: checks relevance (evidence: `README.md`)
- Relevance filter → Field extraction: extracts fields (evidence: `README.md`)
- Field extraction → Confidence flags: flags ambiguity (evidence: `README.md`)
- Field extraction → Missing fields: detects gaps (evidence: `README.md`)
- Confidence flags → Structured fields: annotates fields (evidence: `README.md`)
- Missing fields → Structured fields: identifies gaps (evidence: `README.md`)
- Agent → Structured fields: reviews (evidence: `README.md`)
- Agent → CRM record: updates manually (evidence: `README.md`)
- Browser demo → Field extraction: implements
- Python extractor → Field extraction: implements (evidence: `README.md`)
- CRM API → CRM record: would update (evidence: `README.md`)
