ACTIVE
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
Legal tech / enterprise services
In-house: AI Contract Risk Analysis SaaS
An AI contract-analysis product taken from zero to launch: NestJS modular monolith + Next.js, encrypted contract storage, de-identification before the model, domestic models first; ICP filing completed and live.
- Client
- Quantusteck in-house product
- Industry
- Legal tech / enterprise services
- Region
- China
- Year
- 2026
01
Challenge
The first version grew out of control by trying to do everything at once, and was scrapped and rewritten. The second version had to deliver, with a small team, trustworthy risk analysis, strict data compliance, verifiable quality and sustainable iteration.
02
Approach
- Architecture: NestJS modular monolith + Prisma / PostgreSQL + BullMQ async analysis, Next.js frontend BFF
- Compliance: AES-256-GCM encryption at rest, de-identification before the model, multi-provider abstraction, domestic model by default
- Quality: spec-first, vertical-slice delivery, synthetic regression suite and LLM-as-judge
- Delivery: conversational analysis (SSE), template library and drafting, marketing site and SEO, ICP filing and launch
03
Result
Live with ICP filing complete; the architecture, compliance design and delivery method are reused directly in our enterprise LLM application work.
Stack
Next.js 16NestJSPostgreSQLRedis / BullMQDeepSeek / Claude
Related products
ACTIVE
Enterprise LLM Application Development
Agents, RAG knowledge bases, mini-programs and on-premise deployment — bringing LLM capability into your business workflows
RAG knowledge baseCustom agents