Jamil Moughal

Senior Software Engineer | AI & Cloud | Building and sharing the experiences

Join engineers figuring out what AI agents actually cost to run.

Subscribe on Substack (opens another site)
123456

Six local models, same tools, same questions, different behaviour.

Experiments

Experiment 1, August 2026

I put six different brains inside the same agent

Six local LLMs, the same tools, the same questions. I measured how differently they behaved.

Read the experiment (opens another site)

On the bench

One agent, two frameworks

The same agent built in LangGraph and in CrewAI, then run on local models. What does each framework cost?

LangGraph, CrewAI, Ollama

Where the tokens go

The same kinds of questions sent through one agent, compared model by model on token usage.

granite4.2, qwen2.5, qwen3.5

The instrument

PCPilot

The local desktop agent behind these experiments. It streams from Ollama and acts through tiered tools, with path guards, deny lists, a permission ledger and an undo journal.

Python, PyQt6, Ollama

See all projects

About

At Hach in Düsseldorf, I work on the services that connect IoT devices to the cloud through Azure IoT Hub and Service Bus. I've also helped drive AI adoption there, including AI-assisted coding, automated code reviews and workflow automation.

I have more than ten years of full-stack experience across .NET, React and Azure, and I've worked with AI and ML since 2020.

Read my resume

Writing

Read everything on Substack