ACTIVEIn-house SaaSCustomisable

Aideed · AI Contract Risk Analysis

Upload a contract and see its risks in minutes: itemised issues, four risk levels, conversational follow-up questions

Contract analysisCustom agents

Enterprise / custom inquiry Explore our AI capabilities

Overview & features

Our in-house SaaS for AI contract risk analysis: upload a file or paste the text, and the AI returns itemised risks and revision suggestions, graded critical / high / medium / low, with a report. Includes conversational follow-up, a contract template library and drafting. Contract text is encrypted at rest and de-identified before it reaches the model; domestic models take priority so that data stays in-country.

Key features

File upload or pasted text; AI returns itemised risks, revision suggestions and a report
Four risk levels (critical / high / medium / low), encoded in both colour and text
Conversational follow-up (streamed output), template library and drafting
AES-256-GCM encryption at rest, de-identification before the model, domestic models first

The entire path from zero to launch — architecture, compliance, testing and deployment — was completed by our team alone, and it serves as a working reference for the enterprise LLM application work we take on.

Architecture: NestJS modular monolith + Next.js frontend, Prisma / PostgreSQL, asynchronous analysis via BullMQ
Models: multi-provider abstraction, domestic model by default, switchable
Quality: synthetic regression suite + LLM-as-judge evaluation

Architecture & stack

Next.js 16NestJSPostgreSQLRedis / BullMQDeepSeek / Claude

Applications

Enterprise AI

FAQ

Does data from AI applications leave China?

By default we use models hosted in China and deploy in China, so data does not leave the country. If an overseas model is required, the customer makes that choice explicitly after a compliance assessment.