SWShahmy Wahabdeensoftware engineer · builder
2026AI systemsIn progress

MCP-powered web agent

An exploration of how an agent can gather context, choose tools, and make useful progress while keeping a person in the loop.

Live demo coming soon

01 / The idea

What I'm exploring

The interesting part of an agent is not the model call. It is the context around the model: what it can see, what it can do, and how clearly it can explain what happened.

This project is a place to test those boundaries with small, observable workflows instead of pretending the whole system is magic.

02 / The approach

Small steps, visible trade-offs.

  • Start with a narrow task and a small set of tools.
  • Make every action inspectable and easy to interrupt.
  • Use the results to improve the interface before adding more capability.

03 / The outcome

What success looks like.

The goal is a reliable experiment that demonstrates useful AI interaction without hiding the reasoning or the trade-offs.

Project details

Status
In progress
Year
2026
Category
AI systems
Stack
MCP · AI agents · TypeScript

Keep exploring

Questions about an experiment? I'm happy to discuss the thinking behind it.

Get in touch