📈 Vibe-coding AI agents to solve optimization problems, from academic to industrial settings, suboptimal solutions are sometimes the best

Local Optimum: short, imperfect-yet-useful ideas - Edition #25

Welcome to a new edition of Local Optimum: a short, imperfect-yet-useful collection of ideas related to optimization, decision-making, and applied Operations Research.

Let’s dive in! 🪂

1) 🤖 Vibe-coding AI agents to solve optimization problems

I’ve run a fast test.

I wanted to know how to embed an optimization solver into an AI Agent workflow.

So I used Claude Code (and tested Codex CLI, though not that much).

What it does:

→ Goes to LinkedIn

→ Opens the Queens game

→ Reads the board

→ Solves it

→ And clicks to place the Queens automatically

In its first try, it took 5 min 48 seconds to solve it, and after improving the workflow a bit, 1 min 02 seconds.

It’s not perfect yet, but it shows something powerful: how you can plug an optimization engine inside an LLM Agent.

The result: intuition from AI, rigor from OR.

2) 🎓 From academic to industrial settings

Moving from university to an industry environment can be difficult.

You don’t know how to translate business problems into math/algorithms, ship solutions, or communicate with stakeholders.

But next Wednesday 22nd October you’ll be one step closer to understanding that shift thanks to this Nextmv event:

3) 🎯 Suboptimal solutions are sometimes the best

A model is a simplification of reality, so it will not include all the details (by definition).

Also, an optimization model is an investment, so use it wisely to help you better understand the reality of your problem.

That’s why Jeff Cam reminded us that optimal solutions are not always the best ones.

Read more here:

📈 #25 OR in action: why suboptimal solutions are sometimes the best

---

And that’s it for today!

If you’re finding this newsletter valuable, consider doing any of these:

1) 🔒 Subscribe to the full version: if you aren’t already, consider becoming a paid subscriber. You’ll get access to the full archive, a private chat group, and 30% off new products.

2) 🤝🏻 Collaborate with Feasible. I’m always looking for great products and services that I can recommend to subscribers. Also, if you want to write an article with me, I’m open to that! If you are interested in reaching an audience of Operations Research Engineers, you may want to do that here.

3) 📤 Share the newsletter with a friend, and earn rewards in compensation. You’re just one referral away from getting The Modern OR Engineer Playbook: Mindset, methods, and metrics to deliver Optimization that matters.

If you have any comments or feedback, just respond to this email!

Have a nice day ahead ☀️

Borja.