From Particle Physics to AI Agents: My Week of Discovery
Source: Dev.to
Introduction
I am a PhD student at VUB working on H + c analysis for the CMS experiment at CERN. My days are filled with ROOT histograms, machine‑learning models for jet tagging, endless debugging, and lots of chats with Gemini, ChatGPT, and other AI models. I have trained neural networks and transformers, and I thought I knew AI.
Then I took the 5‑Day AI Agents Intensive Course and realized I had been using AI tools without understanding AI systems. This was my first real AI course, and it changed everything.
Day 1: The Question That Broke My Brain
“What’s the difference between an LLM and an agent?”
My honest first thought: “Aren’t they the same thing?”
The course showed the architecture: Planner, Executor, Memory, Evaluator. I saw myself in that loop:
- Plan today’s analysis strategy
- Execute the code
- Remember what failed yesterday
- Evaluate if I’m making progress
I was doing the agent loop manually every single day.
Realization: What if the system could do this reasoning autonomously?
Day 4: The Validation Part
Later on Day 4, the course demonstrated how to validate agent decisions. As an experimental physicist, this felt familiar—we validate everything with multiple checks and cross‑references.
Insight: Agents need the same rigor we apply to detector data. Not blind trust, but systematic validation.
Day 5: Building My Advisory Panel
For my capstone project, I built an AI Advisory Panel: a multi‑agent system where specialized agents collaborate to solve problems. Instead of one agent trying to do everything, I created a panel of experts:
- One agent analyzes the problem
- Another suggests solutions
- A third evaluates trade‑offs
They debate and reach consensus. This mirrors our research group meetings—different people, different expertise, working toward the best answer.
Why I built it this way: I wanted something broadly useful, a system that could help anyone regardless of field. Multiple perspectives benefit everyone.
Demo can be found here: https://youtu.be/hKYb8bk01AI
What Actually Changed
Before: I saw AI as passive tools waiting for my commands.
After: I see AI as systems I can design to reason, collaborate, and act autonomously.
The practical difference: I’m now thinking about building a full research‑partner agent—one that doesn’t just execute tasks but actually collaborates on the physics. It could:
- Suggest alternative analysis approaches I haven’t considered
- Point out potential systematic issues before they become problems
- Help brainstorm solutions when I’m stuck
- Learn from my reasoning patterns and complement my thinking
Not replacing me, but partnering with me.
What I’m Taking Forward
Having built something general‑purpose, I now want to create a specialized research‑partner agent deeply integrated with my analysis—one that knows the files, understands the CMS detector, and can have actual scientific discussions with me. I’m still learning and still building.
Thank You
To Google and Kaggle: For making this accessible and intense. The daily structure worked perfectly.
To the Discord community: For the debugging help and the reminder that we are all figuring this out together.