Introduction

Intro to Tally's Logistics Context Graph

Logistics operations are fragmented by nature. A single shipment touches dozens of emails, multiple documents, and several systems — each using different reference numbers and inconsistent naming conventions. No single source can maintain a complete operational picture.

Traditional databases try to force this reality into rigid schemas, requiring normalized keys and relationships that simply don't exist consistently across supply chain partners. The result is brittle join logic that breaks with every schema migration.

Tally takes a different approach. The Logistics Context Graph (LCG) is a labeled property graph that continuously ingests fragmented inputs — emails, PDFs, structured feeds — and resolves them into a richly connected knowledge graph across your entire operation. Relationships are first-class elements, not derived join artifacts. Entity resolution automatically recognizes that "Ref #123" on an invoice and "Container 123" in an email thread are the same entity, merging records across sources without a shared key.

The result is multi-hop traversal across your operational network — without the overhead of maintaining relational schemas as your data evolves. And ultimately, a foundation for agentic applications that reason about your operations the way your best operators do.

Let's start with the end result — a resolved Shipment in the graph — then break down what makes it possible.

The system is built on four stages:

Stage	What It Does	You Get
Connect	Integrate your structured and unstructured data sources	A single pane of continuous data flow into the graph
Extract	Tally extracts natural language, documents and other unstructured data into structured entities with metadata classifications	Clean, typed, normalized data entities with specific mapping to logistics context
Resolve	Extracted entities are linked and clustered into shipment-centric subgraphs	Complete operational context of shipments, customers, financials, and exceptions.
Query	Power your applications with graph intelligence and multi-hop reasoning	APIs and context to enable high fidelity agentic capabilities.