AB KineticsContact
● About

Boardroom, IDE, shop floor, rulebook.

Agents that touch real machines need all four. I have worked in each of them — that is what I write and speak from.

Zone ABoardroom

Strategy & ROI

Investment cases and ROI gates leadership can track — not strategy decks that stall.

Zone BIDE

Agent architecture

LangGraph, MCP, n8n, Azure — orchestration and retrieval designed for enterprise constraints.

Zone CShop floor

Machines & service

Wafer handlers, sensors, pneumatics, field service. I know what the agent is actually touching.

Zone DRulebook

Governance

AI Act, Machinery Regulation, Data Act — translated into controls engineers can build.

§02 — Drawn by

An engineer first.

I write about agents I have built, for machines I have serviced. AB Kinetics is the name I publish under.
Portrait
Portrait of Abhimanyu Kanwar
Drawn by
Abhimanyu Kanwar
Role
Senior AI Solutions Manager, service AI for semiconductor equipment

“I've trained engineers on the machines, fixed them on the shop floor, and now build agents that diagnose them. Governance isn't paperwork to me — it's what decides how far an agent may act on a real machine.”

I'm a mechanical and production engineer from RWTH Aachen. I researched troubleshooting agents at the University of Cambridge Institute for Manufacturing, and AI governance through agent simulation at CARMA.

In my role at a leading semiconductor equipment manufacturer, I work on service AI: I led a production AI assistant used by 100+ field engineers, and I architect agent workflows on LangGraph and n8n.

AB Kinetics is where I write and speak about that work: service agents, the autonomy levels that govern them, and the EU rules they have to meet.

Currently learningSemiconductor process control (SPC) and epitaxy fundamentals.

  • RWTH Aachen — M.Sc. Production Engineering
  • University of Cambridge IfM — master thesis
  • Cambridge Service Alliance
  • CARMA — AI Risk Management & Alignment
  • AIRSI 2025 — published
  • Turing College — AI Ethics
§03 — Process route

Every station left a tool.

Batteries taught safety margins. Logistics taught KPIs. Training taught how engineers actually learn. Research taught rigour. Production taught everything else.
  1. 2017RWTH AachenMechanical engineering
  2. 2020Mercedes-Benz EQLi-ion battery development
  3. 2021AmazonDelivery operations & KPIs
  4. 2023Semiconductor equipmentTechnical trainer, field service
  5. 2024Cambridge · CARMAAgent & AI-governance research
  6. 2025Semiconductor equipmentAI solutions in field service
  7. NowService AI & governanceWriting as AB Kinetics
§04 — Track record

Built by someone who has held the wrench.

Before building agents, I trained engineers on the machines and serviced them on the shop floor. That's why I know what an agent is touching.
  • 100+

    field engineers using a production AI service assistant I led

  • 30+

    service engineers in a field test of my troubleshooting agent

  • 3

    continents where I have trained engineering and service teams

N-01Production

A global AI service assistant

In my role at a leading semiconductor equipment manufacturer, I led end-to-end delivery of a proprietary AI service assistant.

Prototype to production on Azure, with external development teams, LangGraph orchestration and Model Context Protocol for scalable retrieval.

→ In daily use by 100+ field engineers.

N-02Research

Troubleshooting agent for semiconductor robotics

Master thesis at the University of Cambridge Institute for Manufacturing on wafer-handling robot failures.

A troubleshooting agent combining retrieval-augmented generation with knowledge graphs, tested in industry with service engineers.

→ Field-tested with 30+ engineers; published at AIRSI 2025.

Release for production

Let's talk.

auf Deutsch geht's auch.

Conference talks, research collaborations, or a question about the framework — email is the fastest way to reach me.

Drawn
A. Kanwar
Location
Aachen, DE
Languages
English · Deutsch