# AI agents manage fantasy soccer. They're not ready yet.

> An experiment deploying AI agents to build and manage a Premier League fantasy team shows promise but still lags behind human expertise.
- Title: AI agents manage fantasy soccer. They're not ready yet.
- Summary: An experiment deploying AI agents to build and manage a Premier League fantasy team shows promise but still lags behind human expertise. AI agents managing a…
- Keywords: ai agents, fantasy soccer, prediction markets, machine learning, forecasting, frontier models, gpt-5, haifeng xu, agents, manage, fantasy, soccer
- Source: WIRED — https://wired.com/story/i-put-ai-agents-in-charge-of-a-fantasy-team
- Author: Will Knight
- Published: 2026-10-28T18:30:00+00:00
- Read time: 1 min
- Topics: ai agents, fantasy soccer, prediction markets, machine learning, forecasting, frontier models, gpt-5, haifeng xu
## An AI experiment with fantasy soccer
The author deployed AI agents to build and manage a Premier League fantasy team to test whether a swarm of bots could assemble a winning roster.
## Earlier attempts were unrealistic
A few years ago, a tool from the UK's Turing Institute selected teams by modeling fantasy league data but ignored real-world information like player injuries or management changes.
## Codex built a multi-agent system
The author asked Codex to create agents that read news, analyzed results, ran prediction models, and critiqued suggestions. This approach significantly improved team recommendations.
## More agents didn't help much
Increasing the number of agents to more than one hundred did not substantially improve suggestions, only raising the API bill without meaningful gains.
## Frontier models show real promise
According to Haifeng Xu at the University of Chicago, newer models may excel at predictions because they consume and analyze huge amounts of real-world information and orchestrate complex systems.

> AI is just getting smarter in understanding the world, I feel like that's the fundamental reason they're improving.
## Testing models on prediction markets
Xu and colleagues tested frontier models on prediction markets like Kalshi and Polymarket. GPT-5 performed best, followed by Grok 4, Claude Sonnet, Gemini, and Llama.

> Very quickly we started to realize that models did really well.
## Humans still have an advantage
AI often lags behind superforecasters because humans understand real-world dynamics more deeply, though evidence suggests this edge is eroding as AI improves.
## The fantasy team underperformed
The author's AI-managed team has not outscored the average over recent weeks and will not influence the author's own selections, but AI will likely improve rapidly.
## Key takeaway

AI agents managing a fantasy soccer team improved significantly over previous attempts but still underperformed average human players, though researchers expect rapid advancement.