AlibabaProductionEvidence: Medium65/100

Cordis China: AI agents for distributor self-service document retrieval using Qwen in Model Studio

Cordis China built an AI-based distributor self-service application on Alibaba Cloud to reduce manual handling of technical documentation, customs import declarations, and inspection and quarantine certificates. The solution combined Qwen in Alibaba Cloud Model Studio, Mobi low-code development, and Alibaba Cloud AnalyticDB integration with ERP and document repositories. The application was deployed for distributor users in China and uses AI agents to retrieve product, lot, and document information with role-based access controls.

Organization
Cordis China
Industry
Healthcare
Location
China
Published
July 2026

Reported outcomes

1,000 users

distributor users deployedAdoption & scale

+100%search accuracy for file-present cases

Strategic outcomes

Customer experience & trustImproved distributor self-serviceCost efficiencyReduced manual workloadOther strategic outcomeImproved service level
Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Distributor users deployed: 1,000 users increase

Alibaba Cloud Customer StoryJul 20, 2026Customer storyExplicit claimMedium evidence strength

Already deployed across distributor users in China

Normalized claim

Search accuracy for file-present cases: 100% increase

Alibaba Cloud Customer StoryJul 20, 2026Customer storyExplicit claimMedium evidence strength

Now it's 100% if file is there

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
Cordis China
Provider
Alibaba
Maturity
Production

The application was deployed for distributor users in China and uses AI agents to retrieve product, lot, and document information with role-based access controls

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 2 of 2

  • 1Document processing
  • 2Workflow automation
  • Distributor document requests for technical documentation and customs-related paperwork were handled manually and were time-consuming.
  • Assistants had to coordinate with supply chain and logistics partners, match documents to lot information, and record linkages in Excel.
  • The China commercial team needed faster, more self-service access for distributors while keeping access limited to purchased products and lots.
  • Built three Model Studio agents: a Q&A agent for product and lot usage, a lot lookup agent using plugins to fetch contract numbers, and a knowledge-base search agent for customs and inspection documents.
  • Used Mobi low-code to create a distributor-facing web application with QR-code login, email verification, chat, and multi-lot search.
  • Integrated backend product, lot, ERP, and customs/document data with Alibaba Cloud AnalyticDB and scoped search permissions to the distributor's purchased orders and lots.
  • The platform improved service level and reduced manual workload.
  • It established a front window for distributor self-service and a faster process for China operations.
  • The solution was deployed to more than 1,000 distributor users.
Architecture

Cordis China connected ERP order and lot data, document repositories, and customs/inspection files on Alibaba Cloud AnalyticDB. On top of that data, it built three Qwen-powered Model Studio agents for Q&A, lot lookup via plugins, and knowledge-base retrieval, then exposed them through a Mobi low-code distributor portal with QR-code login and email verification. Logistics partners upload documents into the Mobi knowledge base, and access is restricted to the distributor's purchased products and lots.

Sources & evidence1
Evidence: Medium65/100Evidence strength
  • Customer explicitly identified
  • Deployment status explicitly supported
  • Primary source available
  • Quantified outcome available
  • Technical implementation details available
Type: Customer StoryPublished: Jul 20, 2026Publisher: Alibaba CloudEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.