bilal.
Book a call

AI agents & automation that actually run.

I turn messy support queues, returns and shipping decisions into systems your team trusts. Built for production, not for the demo.

Book a call
Bilal Ahmad

Operator turned engineer. Leading automation at Nysonian, co-founder of ZavrAI.

The stack it runs on See the work

Less theatre.
More things that work.

0

automations running in production

60-70%

less manual returns work, estimated

0

orders analysed for one shipping decision

The opinion I keep coming back to

Your first agent
should be boring.

Start with the task your team repeats every single day. Make it dependable. Then earn the complexity.

  1. 01

    Learn the work before automating it.

    I started on the operations floor. I find where the work actually breaks, on real orders and real handoffs, before I write a line of it.

  2. 02

    Give the system the right context.

    The order, the policy, the tool. Retrieve what is needed when it is needed. A bounded job for the agent, and everything deterministic stays deterministic.

  3. 03

    Stay for the unglamorous part.

    Retries, monitoring, the exception nobody mentioned. I ship it, then keep it alive alongside the people who depend on it every day.

Good engineering feels like

one less thing
to think about.

Systems in daily use.

Built and maintained alongside the people who use them.

Bilal Ahmad, AI agent and automation engineer Bilal, pronounced Bee-Laal

The human in the loop

I was the person
doing it manually.

The floor. The orders. The handoffs. I knew the friction before I ever wrote the code to remove it.

Today I lead automation at Nysonian and co-founded ZavrAI. I build AI agents, context pipelines and operational systems for a US ecommerce business, with inventory kept in sync across six countries.

My honest opinion after shipping these: earn the complexity. Start with something dependable and boring, then grow it once people trust it.

  1. 2023 to 2025

    Floor Manager

    ECS. Ran the floor. Learned exactly where work breaks.

  2. Early 2025

    Operations Executive

    Nysonian. Mapped the manual processes worth automating.

  3. Mid 2025

    Automation Engineer

    Nysonian. Built the automation program from scratch.

  4. Aug 2025 to now

    Automation Team Lead

    Nysonian. Promoted in six months. Own delivery and the team.

The tools follow
the problem.

Agents & context

Claude API, Tool calling, RAG, Ollama, turbovec

Systems & operations

TypeScript, Python, n8n, PostgreSQL, Shopify, ShipHero

Before you ask

Questions
worth answering.

Short, honest answers for recruiters, operators and founders sizing up whether to work together.

What does an AI agent and automation engineer actually do?

I build AI agents and automation systems that take repetitive operational work off your team: customer support triage, returns and RMA lifecycles, and order or shipping decisions. I connect the tools, give the agent the right context, and keep it running in production, not just in a demo.

Should my first AI agent be big and ambitious?

No. Your first agent should be boring. Start with one task your team repeats every day, make it dependable, and earn the complexity from there. Ambitious agents nobody trusts get switched off within a month.

Can you automate customer support without losing the human touch?

Yes. A well-built support agent handles routine, low-risk requests like order status and closes them quickly. Money-related and sensitive conversations escalate to a person by design. The goal is a shorter queue, not a wall between customers and your team.

What tools and tech stack do you build with?

Claude API and tool calling for agents, n8n and Python for workflows, PostgreSQL for data, and integrations with Shopify, ShipHero and carrier APIs. I also work with RAG, Ollama and TypeScript. I pick the tool that fits the problem rather than forcing the problem into a tool.

How long does it take to ship a production automation?

A focused first automation is usually a few weeks from scoping to something live in production. The unglamorous part, retries, monitoring and the edge cases nobody mentioned, is part of the work, not an afterthought bolted on later.

Are you available to hire, and do you work remotely?

I lead automation at Nysonian and co-founded ZavrAI, and I take on selected projects and roles. I work remotely with teams anywhere. The fastest way to check fit is a short discovery call.

Last updated September 11, 2026
Currently Pakistan,

Your next chapter

Let's make
room for better.

I'm here to

A bottleneck to untangle. A returns mess. A support queue that never ends. Let's scope it and see what a dependable system would actually save you.

Book a call
Note from Bilal

Hi, thanks for scrolling this far.

To me, good automation is quiet. It just works, every day, without anyone thinking about it.

If something here stuck with you, say hello.