Skip to content
Lintel

Platform

How Lintel is built.

A credible, non-confidential overview of the pipeline and the design choices that keep every output traceable.

Ingestion pipeline

From scan to verified obligation.

  1. 1

    OCR

    Scanned pages become text with layout.

  2. 2

    Structure

    Headings, tables and schedules are recognised.

  3. 3

    Clause segmentation

    Numbered clauses and cross-references are identified.

  4. 4

    Extraction

    Obligations and fields are proposed with citations.

  5. 5

    Linking

    Clauses, obligations and events are connected.

  6. 6

    Verification

    A person reviews low-confidence items.

Architecture

Layers

A simplified layered view. Interfaces marked planned are not yet available.

Layered architecture from interfaces at the top to data and security at the bottom.InterfacesWeb console · Email ingestion · API & webhooks (planned)WorkflowsObligations · Notice engine · Evidence vault · Claims workbenchIntelligenceExtraction · Linking · Hybrid retrieval (project-scoped) · Model-agnostic AI gatewayIngestionOCR → Structure → Clause segmentation → Extraction → Linking → VerificationData & securityTenant isolation · Encryption in transit and at rest · Audit log · Evidence chain-of-custody

Design choices

What we insist on

  • Provenance on every field

    Each extracted value stores its source page, text span and a confidence score, so any field can be traced and challenged.

  • Review queue

    Low-confidence extractions are routed to a person. Approved values are versioned; edits are logged.

  • Hybrid retrieval, scoped by project

    Keyword and semantic search run only inside the project’s own documents. Nothing crosses tenants.

  • Model-agnostic AI gateway

    Model calls go through one gateway so models can be swapped or evaluated without changing product behaviour.

  • Evaluation on annotated sample contracts

    Extraction is evaluated against annotated sample contracts before changes ship. We do not publish an accuracy percentage.

  • Multi-tenant isolation

    Each customer’s data is separated logically, with role-based, project-scoped access and audit logging.

  • Evidence chain-of-custody

    Every evidence item has a timestamp, a hash and an access log.

  • API and webhooks (planned)

    A versioned REST API and webhook events are planned. They are not yet available.

These are design principles for a product in early access. They are not certifications or measured results.

Start with one contract.

Join early access, or book a walkthrough and we will show you how a single agreement becomes a live register.