Course · On demand from 16 November 2026
Building football solutions with Agentic AI
Turn your football challenges into working tools. No coding experience required.
Overview
Every club has questions that never reach the top of the analysts' list. Is the team really better since the new manager arrived? What changed after we brought in help? Who in the league plays the way we do? The people asking usually know exactly what they want to see. Until now, getting it meant waiting for someone who could code.
Agentic AI changes who can answer these questions. This course gives you exclusive access to our Earpiece App Builder, a no-code web-based tool for solving footballing problems. You also get full access during the course to our API, giving you access to 300+ men's and women's competitions. You can build whatever you want on all the data you need.
You describe your problem in plain English. App Builder then works through it with you: it asks what you mean, checks that the data can actually answer the question, shows you a plan, builds the app and tests it against real matches. It stops for your approval at each step, and if the data cannot answer your question, it tells you instead of guessing.
This course teaches you to work with App Builder and similar agents: turning a football problem into a clear request, judging what comes back, and knowing what to do when the agent gets it wrong.
Problems you could solve
These are the kinds of questions we have worked on with clubs, and each one can be answered with Earpiece data:
Is the club going in the right direction since the new manager arrived?
Points and expected goals per match across the season, with the managerial change marked.
Did anything change after the intervention?
A team's playing style in a chosen run of matches, compared with its own season average.
What kind of team are we playing on Saturday?
An opposition one-pager: how they press, how direct they are, which formations they use and how they switch between them.
Who improved most last season?
Pick a quality and two seasons, and see every player's before and after, with a written summary underneath.
Would this player fit the way we play?
A player's current team compared with yours, across style of play.
Which teams sit higher in the table than their play deserved?
Points against the quality of chances created and conceded.
Where are we shooting from?
Shot zones compared with the rest of the league.
Bring your own question. Part of the course is finding out which questions the data can answer, and how to ask the ones it can.
Curriculum
Module 1
Setting up
Get familiar with Earpiece App Builder and build your first app, an expected goals (xG) app, by talking to the agent.
Module 2
Owning your own problem
Choose a question from your own work and take it through the agent's steps: understand, check the data, plan, build, verify.
Module 3
When the agent gets it wrong
Troubleshooting, and learning to work with the agent rather than around it: reading its plan, correcting its assumptions, and iterating until the app answers your question.
Module 4
Presentations and feedback
Present your app and get feedback from David and the Twelve team.
What's included
- Access to course videos for two years
- Access to Earpiece App Builder
- Two meetings with David Sumpter for feedback on your app at the start and end of your project
- A Slack group for troubleshooting and rapid feedback
- Weekly support sessions with Mahlet "Mahi" Sewinet, who designed and built App Builder
- One month of unlimited individual Earpiece access (worth €300)
- API access to event data across 300+ men's and women's competitions
- A certificate of completion
After the course. Students who graduate can sign up for continued access to Earpiece App Builder, subject to agreement.
Course leader
Professor David Sumpter
Co-founder, Twelve Football
Professor David Sumpter is a professor of applied mathematics at Uppsala University and the author of Soccermatics, a book that explores the application of mathematical modelling to football. He co-founded Twelve Football and has worked with major clubs and national federations worldwide.
Who it's for
- Scouts and performance staff at clubs
- Football analysts with little or no coding experience
- Club staff who want practical apps for their own work, without learning to program
- Data scientists who want to speed up their work
Testimonials
"The course teacher dedicated time to sit with me individually, start from scratch, and write a customised step-by-step plan. This was going above and beyond and really assisted me as a relative beginner in Python."
Liam Cody
Pro Solutions Team Lead, StatsPerform
"Thank you for all this course does for the community. I'll be joining a Brazilian club as a data scientist in the upcoming weeks, and it is crystal clear that it would not happen without your course."
Rodrigo Salvador
Red Bull Bragantino
"I appreciated the course very much. I recommend it for anyone interested in gaining additional knowledge in data science and analysis in their organization."
Martin Vogelbein
Scouting, Match Analysis — Deutscher Fußball-Bund
"Especially the insight into presenting the results via Python Streamlit was a big game changer for me. We are now establishing this framework at TSG Hoffenheim."
Fabian Rupp
Business Intelligence & Data Analytics, Hoffenheim
Get the latest on football data and AI
Get sharp insight on how the game is changing, practical ideas you can use in your work, and early access to new features and updates from Twelve.