Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group L · Matchday 17 · 2026-06-27

Panama vs England

East Rutherford, United States · neutral venue

Full time PAN 0–2 ENG
The agent called England (82%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–1 15.2%
7.9%
PAN win
17.9%
Draw
73.6%
ENG win
Top scorelines
  • 0–1 15.2%
  • 0–2 14.3%
  • 0–3 10.6%
  • 0–0 9.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
PAN win
5.3%
Draw
12.7%
ENG win
82.0%

The model already heavily favours England (73% away win), and every supplied factor reinforces that direction. Panama's recent form is poor, their squad value is near the bottom, and the only head-to-head was a 6-1 England win. England's key players are world-class and fully available. The only mild counterweight is that England's recent form is merely in line with expectations, but that does not close the gap. I increase England's win probability to 83%, trimming home and draw accordingly, because the talent and historical gap is too large to keep the prior unchanged. England's expected goals (2.30) and Panama's (0.47) suggest a comfortable win with clean sheet likely. The most probable scorelines are 0-2, 0-3, and 0-1, reflecting England's defensive solidity and Panama's low scoring threat. A 0-0 draw is unlikely (6%) given England's attacking quality, while a 1-3 or 1-2 result accounts for a possible Panama consolation goal.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Panama vs England 2026-06-27 lineup injuries” match · 3 hits
    Late fitness or lineup changes could shift the forecast significantly.
  • “England squad 2026 World Cup injuries suspensions” ENG · 3 hits
    Key England players missing could heavily impact their strength.
  • “Panama squad 2026 World Cup injuries suspensions” PAN · 3 hits
    Key Panama players missing could change their defensive or attacking capability.
Agent scorelines
generated 2026-06-27
Last 5 — PAN
-0.54 pts/match vs model expectation · opp. avg #57
  • BRA #3 -0.1
  • DOM #149 +0.5
  • BIH #64 -0.5
  • GHA #55 -1.1
  • CRO #15 -0.6
GF / GA last 10: 14 / 15
Last 5 — ENG
-0.17 pts/match vs model expectation · opp. avg #50
  • JPN #18 -2.1
  • NZL #94 +0.2
  • COS #66 +0.3
  • CRO #15 +1.2
  • GHA #55 -1.3
GF / GA last 10: 21 / 4
Head-to-head (last 5)
  • 2018-06-24 England 6–1 Panama
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
9.6
15.2
14.3
10.6
6.7
3.8
2.0
1
4.1
6.5
6.1
4.5
2.8
1.6
0.9
2
1.1
1.7
1.6
1.2
0.7
0.4
0.2
3
0.2
0.3
0.3
0.2
0.1
0.1
0.0
4
0.0
0.1
0.1
0.0
0.0
0.0
0.0
5
0.0
0.0
0.0
0.0
0.0
0.0
0.0
6
0.0
0.0
0.0
0.0
0.0
0.0
0.0

Rows = PAN goals; columns = ENG 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)
0.47
PAN
2.31
ENG

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.