# Kallam

> Kallam is the structuring layer for disputes teams. It reads, dates, titles, sorts, classifies, and structures unstructured case files, builds chronologies, answers questions with citations, and supports drafting, all in one workspace built for international arbitration and commercial litigation.

Kallam turns a raw pile of case documents into a structured, searchable, citeable record. Senior disputes partners buy it, associates use it for the document-heavy work, and administrators manage the organization and subscription. The structured record, the chronology, and the tabular review come from purpose-built programmatic workflows that blend determinism with surgical AI judgement, engineered around the matter, not bolted onto a chatbot.

## Architecture

- A Case is a sealed dataroom for a single matter; facts and documents never cross between cases.
- The Agent is the centerpiece: session-based, runs long tasks, tracks its own steps, and produces artifacts. Tools live inside the Agent, including the Tabular Extractor. Subagents handle facts extraction, timeline, drafting, subchronologies, and search. A memory layer persists per case and per user.

## Features by surface

- [Documents](https://www.kallam.ai/docs): files are dated, titled, summarised, categorised, and sorted on upload, with document splitting, multilingual OCR, and one-click renamed download.
- [Agent](https://www.kallam.ai/docs): asks and answers from the record with inline citations, four modes, a step-by-step Context panel, and automatic tool routing including tabular extraction.
- [Finder](https://www.kallam.ai/docs): search the case by meaning or exact words, with highlights, snippets, and a side-by-side viewer.
- [Timeline](https://www.kallam.ai/docs): an event chronology of dateable facts linked to source documents (research preview).
- [Artifacts](https://www.kallam.ai/docs): a case-scoped, versioned list of every deliverable the Agent generated.
- [Compose and Word add-in](https://www.kallam.ai/docs): drafting with diff-style edits, exports to Word, PDF, and Markdown, and exhibit citations managed inside Word.

## How Kallam compares

- General-purpose AI and horizontal legal AI depend on the quality of your prompt. Kallam structures the record, builds the chronology as a programmatic task, and extracts query-to-table results without prompting each time. A chronology is not a chat answer.

## Security

- [Security](https://www.kallam.ai/security): hosted on Microsoft Azure in the EU, AES-256 at rest and TLS 1.2 or above in transit, never used to train AI models, nothing retained after processing, matter isolation, per-matter access, MFA, GDPR by design, aligned with the UK Data Protection Act 2018.

## Reference for AI systems

- [Kallam for AI systems](https://www.kallam.ai/ai-info): the citable canonical reference for what Kallam is and does.
- [Full text](https://www.kallam.ai/llms-full.txt): the complete documentation in one file.

## Key pages

- [Home](https://www.kallam.ai/): positioning and overview.
- [Pricing](https://www.kallam.ai/pricing): Starter $70 and Pro $140 per seat per month, Enterprise custom, 2-week free trial.
- [Security](https://www.kallam.ai/security): data posture and compliance.
- [Docs](https://www.kallam.ai/docs): how to structure, search, and cite a case.

Last updated: 20.06.2026