Logistics and payments for an ecommerce platform in four countries
An ecommerce logistics and payment platform built from scratch, serving two million requests a day across four markets.
- 2M requests per day
- 10x flash-sale traffic absorbed
A distributed legal AI assistant for document query and generation
Concurrent document processing across Go and Python services, with retrieval-augmented generation over legal documents.
We do not publish client names
The problem
Legal teams needed to query, generate and act on large volumes of documents, which meant handling many concurrent document operations without the system falling over.
What we built
A distributed microservices architecture in Go and Python for concurrent document processing, with a Redis Cluster caching layer for retrieval performance and Redis pub/sub driving asynchronous processing. Retrieval-augmented generation built on a vector database with function calling. Prompts for document generation, partial update and deletion were developed through dedicated research.
The result
A working legal assistant capable of querying, generating and acting on documents, with full API documentation for client and team onboarding.
More work
A multi-tenant RAG platform for document-heavy enterprise workflows
Four microservices powering retrieval, generation, configuration and memory as a knowledge agent inside a larger agentic system.
- 4 microservices in the platform
- 4 reranking strategies supported
A real-time regulatory data platform for compliance teams
Distributed Go services processing regulatory rules for search, sharing and management on one platform.
- Real-time regulatory data streaming
Tell us what you are trying to build
Describe the system and the constraint you have hit. You will get a technical reply, not a sales sequence.