AI Agents & Automation That Ship | Voice AI, LLMs, .NET
Not every automation needs an LLM. A B2B business was receiving purchase orders from retailers through SPS Commerce.
Someone on the team then checked stock by hand, retyped each order into Sage 50 as a sales order, and kicked off fulfillment.
We built a platform on ASP.NET (http://ASP.NET) Core and C# that handles it end to end.
→ Purchase orders come in through SPS Commerce automatically
→ Stock and order details are validated before anything is created
→ Sales orders land in Sage 50 without retyping
→ Anything odd is flagged as an exception instead of quietly slipping through Less manual work across the whole order lifecycle, cleaner data, and orders that keep moving without anyone copying fields between screens.
I build a lot of AI agents now. But the first question on every scoping call is still the same.
Does this need judgement, or does it just need wiring? Half the time it's wiring.
0
54
An AI agent that can move money is only useful if it can't move it on its own.
Haia lets people manage their banks, crypto wallets and brokerages from one place, just by saying what they want done.
I built the AI orchestration layer. The interesting design choice wasn't the model. It was deciding where the model is not allowed to act.
→ The agent turns a request into a step by step plan
→ Each step is routed to the right banking API, wallet, chain or brokerage
→ Security and compliance checks run before anything executes
→ The user approves every move, and transactions are signed on their own device It's fully non-custodial.
Zero private keys ever exposed, to us or to the model.
If you're building agents that touch money, health records or anything you can't undo, design the approval step first. Then the AI.
1
1
126
Your support team goes home at 6. Your customers don't. An online retailer we worked with had a simple problem.
Shoppers asked questions at 11pm, on weekends, on holidays.
The answers came the next morning, and by then a lot of them had bought somewhere else.
We built a 24/7 AI chat into their store. Not a FAQ bot that says "I didn't understand that" three times.
It handles the common questions on its own, recommends products inside the conversation, and drops every chat into their CRM with the full customer context.
When a person does step in, they aren't starting from zero. → 50% more conversions → 35% faster response time → 40% less support workload The part people underestimate is the CRM link.
A chat that sells but forgets who the customer is just moves the problem to your team. Support and sales turned out to be the same conversation.
1
1
137
Senior AI Engineer & Full Stack Architect
Senior AI Engineer & Full Stack Architect
Fullstack Engineer | Web/Mobile
Fullstack Engineer | Web/Mobile
Migrated Xamarin Form app to .net MAUI and improved UI design and overall API and mobile app performance.
0
57
I worked on migrating applications from Azure AD Graph to Microsoft Graph, ensuring a smooth transition by updating permissions, endpoints, and token scopes. Having handled similar migrations before, I took the lead in implementing the necessary changes and aligning configurations with Microsoft’s current identity standards. I also planned for contingencies by preparing for potential delays and coordinating with the team to request extensions when needed. My role involved guiding the process efficiently and providing hands-on support to minimize disruption during the migration
1
91
A SAAS app in the travel sector, focusing on Tour Operators or Online Travel Agencies (OTAs).
I was responsible for architecture, logic, server, and technology selection to ensure optimal performance, including advanced cache management
0
78
I am working closely with the Front End developers and product owners to deliver backend Endpoints.
Bondex is a web 3.0-based job portal having +5M users. active job seekers, companies and recruiters.
My role includes:
1) Develop new features and functionality
2) provide support,
3) Discussions with the product owner for new functionality
1
64