I'm Neil Busque, an AI engineer in New Jersey. I build agents, LLM features, RAG systems and MCP integrations that connect to the tools where your work already happens.
I build software that uses AI for a specific job, with enough context, testing and guardrails to be useful after the demo. In practice, that includes:
I work in small, written tasks, test the risky parts and review every change. AI coding tools write a lot of the code, and they make me fast. My job is to catch what they get wrong before your team or your customers do. I shipped more than 40 apps, agents and automations in 2026. Read how I ship in days and browse the work.
Prompting is the easy part. The useful work is choosing the right boundary, connecting the data safely, testing the failure cases and leaving behind something another engineer can maintain.
Message me on WhatsApp, email busqueneil@gmail.com or connect on LinkedIn. Prefer the automation side? See hiring for AI automation, or read when to bring me in.
Whichever fits the job, usually Claude or GPT. I set things up so you can switch models later without starting over.
I plan for it. Every agent gets clear limits that you approve before launch. Anything risky, like spending money, publishing or deleting, waits for a person to approve it. I test it on real examples from your business before it goes live.
Yes. I've taken over apps started by other developers and by AI app builders, cleaned them up and kept building. I'll look at what you have and tell you whether to keep it or start fresh.
Send a few lines about the work. I keep working until you are proud of it. If I am not the right fit, I will tell you on the first call.