The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
MyCarrier: DevOps & Cloud Transformation for Scalable Logistics SaaS
Preview description:
We helped MyCarrier move toward cloud-ready DevOps: adapted the system for microservices, implemented CI/CD and test automation, moved workloads to Azure, achieved 99.9% availability, decreased update delivery time to minutes.
Full description:
Problem
MyCarrier was growing fast, and the monolithic codebase became harder and more expensive to maintain. It was heavy, resource-consuming, and less suitable for the client’s long-term scaling plans. The team also needed faster delivery processes, but changes in the codebase and cloud migration had to stay unnoticed by users. Their logistics workflows could not be interrupted.
Solution
IT Craft aligned the project infrastructure with a microservices architecture and prepared the system for cloud operation. The team started with a technical audit and developed the migration strategy consisting of 20-28 items. The process was divided into pre-migration, migration, and post-migration phases, thus the product could keep running while infrastructure changed step by step.
The team moved non-critical standalone jobs to the cloud, connected virtual machines to Azure Storage Account, moved logging to MongoDB Atlas, and transferred user data and related processes to the cloud. New app functionality was released as microservices. IT Craft also designed and fine-tuned a CI/CD pipeline, automated infrastructure deployments, and reduced update delivery time through regression test automation.
Results
· Achieved 99.9% system availability.
· Maintained high fault tolerance using three shared clusters.
· Reduced update delivery time from hours to minutes.
· Enabled Sprint focus changes every two weeks based on client priorities.
Tech Stack:
· Azure Cloud
· MongoDB Atlas
· Azure SQL
· Azure App Service
· Azure Functions
· Azure Storage Account
great job
That’s a solid transformation. Cutting update time from hours to minutes is a huge improvement.
solid writeup
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I built MobiFix Nairobi : A Mobile auto care company.
I rebuilt the moment an inbound “Can I book with you?” becomes “You’re booked.”
MobiFix Nairobi is a fictional mobile automotive service business built around one simple problem: booking vehicle services often means back-and-forth messages, checking availability, coordinating technicians, confirming locations, and handling payments manually.
I designed the experience so the customer can:
→ Choose a service
→ Select their vehicle
→ Enter their location
→ Pick an available date and time
→ Add their details
→ Review the booking
→ Complete payment
→ Receive a booking confirmation and code
Behind the scenes, the business gets a real dashboard with bookings, calendar, customers, services, technicians, availability, analytics, and website management — all backed by real data.
The goal was to make the entire journey feel less like “requesting an appointment” and more like simply getting booked.
Built with Lovable and Lovable Cloud.
MobiFix: https://carmobifix.lovable.app
(I haven't submitted the actual project link because of the environment variables, I'm using Lovable Cloud.)
Looking great...
I designed and built an enterprise AI automation system using n8n, AI agents, RAG, Redis, and PostgreSQL to automate complex business workflows, improve decision-making, and create scalable AI-powered operations.
The system uses n8n as the automation orchestration layer, where incoming business events trigger workflows that route tasks to specialized AI agents. A RAG pipeline retrieves relevant knowledge from business data sources, allowing AI agents to generate accurate, context-aware responses and decisions. Redis handles queue-based processing for high-volume tasks, while PostgreSQL stores structured data, workflow history, and audit records.
The automation architecture connects multiple technologies including n8n, OpenAI API, AI Agents, RAG pipelines, Vector Databases, Redis, PostgreSQL, APIs, Webhooks, Slack integrations, Docker, and Python services to create reliable enterprise workflows.
The solution helps businesses reduce manual operations, automate repetitive processes, improve response times, maintain better data accuracy, and scale AI workflows securely. It includes monitoring, validation, error handling, and human approval flows to ensure reliable production usage.
Tech Stack: n8n, OpenAI, AI Agents, RAG, LangChain, Redis, PostgreSQL, Qdrant, Python, FastAPI, Docker, APIs, Webhooks, Slack.
A RAG answer without a source is hard to use in real work.
For Shamrock Marketing, I built a workflow for technical standards, product specs and repair guides. It splits documents into passages tagged by product and procedure, retrieves relevant context with Azure AI Search, and generates answers with document and page citations.
A reviewer can open the exact source before acting on an answer. That is the difference between a plausible response and a usable workflow.
If your team answers repeat questions from dense PDFs, does more time go into finding the right document or checking the answer?
