Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group L · Matchday 13 · 2026-06-23

England vs Ghana

Foxborough, United States · neutral venue

Full time ENG 0–0 GHA
The agent called England (77%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 17.5%
66.1%
ENG win
22.8%
Draw
10.9%
GHA win
Top scorelines
  • 1–0 17.5%
  • 2–0 14.2%
  • 0–0 13.0%
  • 3–0 8.9%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
ENG win
77.0%
Draw
15.7%
GHA win
7.3%

England's squad value is 7.1x Ghana's, with elite attackers like Kane, Bellingham, and Rashford far outclassing Ghana's key players. Recent form is solid for England, while Ghana has lost three of four. The model's 68% home win is a reasonable baseline, but the talent gap and depth justify a slight upward adjustment to 78%, offset only slightly by Saka's likely absence from the starting XI. Ghana's overperformance against stronger opposition is noted but insufficient to close the chasm in quality. England's expected goals of 1.97 reflect their attacking strength, but Ghana's defense is likely to concede multiple goals given the talent disparity. The most likely scorelines are 2-0 and 1-0, with 3-0 also plausible if England finish chances. Ghana's attack, led by Ayew and Partey, may struggle to score against England's defense, making a clean sheet probable. The 0-0 draw is less likely given England's offensive firepower.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 8 sources kept:
  • “England vs Ghana 2026-06-23 lineup news” match · 3 hits
    Late fitness or lineup changes could shift the forecast.
  • “England squad injuries June 2026” ENG · 3 hits
    Key player injuries would significantly affect England's strength.
  • “Ghana squad injuries June 2026” GHA · 2 hits
    Key player injuries would significantly affect Ghana's strength.
Agent scorelines
generated 2026-06-22
Last 5 — ENG
+0.18 pts/match vs model expectation · opp. avg #41
  • URU #12 -0.9
  • JPN #18 -2.1
  • NZL #94 +0.2
  • COS #66 +0.3
  • CRO #15 +1.2
GF / GA last 10: 26 / 4
Last 5 — GHA
+0.24 pts/match vs model expectation · opp. avg #33
  • AUT #23 -0.8
  • GER #7 -0.3
  • MEX #20 -0.7
  • WAL #44 +0.0
  • PAN #72 +1.4
GF / GA last 10: 11 / 13
Head-to-head (last 5)
  • 2011-03-29 England 1–1 Ghana
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
13.0
5.8
1.6
0.3
0.1
0.0
0.0
1
17.5
7.8
2.1
0.4
0.1
0.0
0.0
2
14.2
6.3
1.7
0.4
0.1
0.0
0.0
3
8.9
4.0
1.1
0.2
0.0
0.0
0.0
4
4.8
2.2
0.6
0.1
0.0
0.0
0.0
5
2.3
1.0
0.3
0.1
0.0
0.0
0.0
6
1.1
0.5
0.1
0.0
0.0
0.0
0.0

Rows = ENG goals; columns = GHA goals. Above-diagonal cells are home wins; diagonal = draws; below = away wins. Truncated at 6 — the joint mass past that is < 1 %.

Expected goals (Poisson rate, λ)
1.85
ENG
0.49
GHA

Independent-Poisson rates. W/D/L and the score grid integrate the full 13×13 joint under these two parameters.

News context — injuries, suspensions, projected XI — is not part of the model, which sees only past results.