AI & ML Overview¶

This document describes the AI and machine learning components used in the Pebble Business Orchestrator for intent recognition, entity extraction, and process intelligence.

AI Capabilities Summary¶

🛠️ Execution Context: Cloud vs. Local¶

Pebble supports both cloud-native and private, on-premise AI execution.

1. Intent Classification (The Brain)¶

Purpose¶

Automatically classify incoming emails into specific operational streams (Sales, Logistics, Quality, Tenders) to ensure they land on the correct Kanban board.

Model Hierarchy¶

graph TD
    A[Incoming Email] --> B{Intent Classifier}
    B --> C[Sales enquiry]
    B --> D[Logistics/Dispatch]
    B --> E[Tender/NIT]
    B --> F[General/Unclassified]

    C --> C1[New Quote]
    C --> C2[Follow-up]

    D --> D1[Tracking Query]
    D --> D2[Dispatch Proof]

Model Options¶

2. Business Entity Extraction (NER)¶

Purpose¶

Extract structured business identifiers to enable one-click synchronization with Odoo, Zoho, and Focus RT.

Critical Entities¶

3. Tender IQ (OCR & Vision)¶

Purpose¶

While the core of Pebble is email orchestration, Phase 3 involves deep intelligence for Tenders which often arrive as scanned documents.

Pipeline¶

1. OCR Engine: Azure AI Document Intelligence or Tesseract 5.
2. Layout Analysis: Identifying tables of "Item Codes" and "Quantities".
3. Similarity Engine: Comparing current NIT specs against historical "Closed Won" tender results.

4. Confidence & Human-in-the-Loop¶

Pebble follows an "Augment, Don't Automate" philosophy. Every AI decision includes a confidence score that determines UI behavior.

5. Model Training & Evaluation¶

Continuous Learning Loop¶

flowchart LR
    A[Production] --> B[Log Predictions]
    B --> C[User Moves Card]
    C{Correction?}
    C -->|Yes| D[Log as Negative Sample]
    C -->|No| E[Log as Positive Sample]
    D & E --> F[Retrain Intent Model]
    F --> G[Deploy Updated Weights]

← Back to Home | View MVP Scope