Geoffrey De Smet

@geoffreydesmet
468 Followers
83 Following
117 Posts
Timefold CTO, OptaPlanner creator, Java coder, open source contributor, speaker, Artificial Intelligence (mathematical optimization, metaheuristics, constraint solving)
Timefoldhttps://timefold.ai
GitHubhttps://github.com/ge0ffrey
Twitterhttps://twitter.com/GeoffreyDeSmet
LinkedInhttps://www.linkedin.com/in/ge0ffrey/

Vehicle Routing Problems are difficult to solve,
especially at scale with real-world constraints.

Both for humans and software.

In this video, I explain why VRPs are challenging,
what technology solutions exist
and how you can solve them easily in practice.

https://www.youtube.com/watch?v=Lcdw8i38X78

Solve a Vehicle Routing Problem with AI

YouTube
At the Dublin Java User Group, Tom will solve Santa's scheduling and routing optimization problems with Timefold Solver (our open source solver previously known as OptaPlanner) on Tue 27 jan:
https://www.meetup.com/dublinjavausergroup/events/312770573/
DubJUG 262: How we optimized Santa's travels in Java with Timefold, Tue, Jan 27, 2026, 6:15 PM | Meetup

In time honoured fashion, our first DubJUG events of the year are linked with the jChampions Conference, and today we're announcing our second visiting Java Champions of 20

Meetup

Our new API for Pickup and Delivery Routing is out!

It optimizes in-route pickup and delivery of people or packages.

Such as
- Non-emergency medical transport to bring patients to the hospital
- School bus optimization
- Food delivery
- Parcel delivery

https://app.timefold.ai/models/pickup-delivery-routing

Pick-up and Delivery Routing: out-of-the-box PlanningAI by Timefold

Assign pick-up and delivery jobs to drivers, optimizing for increased productivity and reduced travel time.

"Why can't you just have ChatGPT generate a schedule for you?"

In this podcast, Mackenzie Jackson and I didn't just drink sake, we also covered complex scheduling and routing with AI and founding a company.

Watch it here:
https://www.youtube.com/watch?v=58CM0Zr4O_E&t=2020s

Digital Identities, Fraud, and the Future of AI with Veriff & Timefold: The Secure Disclosure

YouTube

An Open Source project needs a real-time chat for the community to come together.

So we created a Discord chat for Timefold Solerv.

To ask questions.
To discuss ideas.
Or to figure out how to hack the solver to run your crazy experiment.

Join us:
https://discord.gg/976RcEVVHW

In the Optimization4All podcast, Cristina Radu and I talked about Operations Research, starting a company and Timefold.

Watch the podcast:
https://www.youtube.com/watch?v=rrLby4O5mA0

Geoffrey De Smet: From a hobby to building a company

YouTube

If it takes 10 000 hours to master a craft,
what do you get for 10 000 commits?

Timefold Solver, our Open Source solver for complex scheduling and routing problems, just reached 10 000 commits on GitHub:
https://github.com/TimefoldAI/timefold-solver

Can the optimal solution for a Traveling Salesman Problem (TSP) have crossing paths?

No, it cannot.
Because of the Triangle Inequality principle.

But in reality, it can.
Because there's road infrastructure: highways, one-way streets, etc.

In the real-world, solution optimality is rarely obvious.

A great plan is worthless if you can't explain why.

For the operators to trust your software, they need more than a button to "Schedule with AI" that generates the optimized schedule for their employees.

They need explainability. Learn how:
https://timefold.ai/blog/explainable-ai-how-to-build-trust-in-optimization

How to build trust in planning optimization: Explainable PlanningAI

Optimization algorithms can spit out mathematically brilliant schedules, but if planners can’t see the rationale, those “perfect” plans end up in the…

Timefold