Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group E · Matchday 10 · 2026-06-20

Ecuador vs Curaçao

Kansas City, United States · neutral venue

Full time ECU 0–0 CUW
The agent called Ecuador (84%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 17.8%
72.1%
ECU win
20.0%
Draw
7.6%
CUW win
Top scorelines
  • 1–0 17.8%
  • 2–0 15.6%
  • 0–0 12.2%
  • 3–0 10.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
ECU win
84.3%
Draw
11.0%
CUW win
4.7%

The statistical model already gives Ecuador a strong 74% win probability, but the squad market value gap (12.4x) and Curaçao's two key absences (Gorre, St Jago) indicate the model may be conservative. Ecuador's recent form is solid, while Curaçao's is poor, and the head-to-head is blank. Conditions are neutral. I raise Ecuador's win probability to 85% to reflect the talent chasm and availability advantage, lowering draw and away win accordingly. Ecuador's expected goals of 2.24 from the model are reasonable, but given Curaçao's weakened defense and Ecuador's attacking talent (Valencia, Plata, Yeboah), a 2-0 or 3-0 win is most likely. Curaçao's scoring threat is minimal (0.40 xG), so clean-sheet outcomes dominate. The 0-0 draw is possible but unlikely given the disparity.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 6 sources kept:
  • “Ecuador vs Curaçao 2026-06-21 lineup news” match · 3 hits
    Late fitness or lineup changes could shift match odds.
  • “Curaçao squad news June 2026” CUW · 3 hits
    Additional unavailable players beyond Gorre and St Jago could weaken Curaçao.
Agent scorelines
generated 2026-06-20
Last 5 — ECU
-0.19 pts/match vs model expectation · opp. avg #44
  • MAR #11 -0.1
  • NED #9 +0.1
  • KSA #74 +1.0
  • GUA #100 +0.4
  • CIV #26 -1.5
GF / GA last 10: 12 / 6
Last 5 — CUW
-0.18 pts/match vs model expectation · opp. avg #72
  • CHI #98 -1.2
  • AUS #29 -0.3
  • SCO #39 -0.3
  • ARU #186 +0.2
  • GER #7 -0.1
GF / GA last 10: 20 / 21
Head-to-head (last 5)

No prior meetings in the dataset.

▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
12.2
4.4
1.0
0.2
0.0
0.0
0.0
1
17.8
6.5
1.4
0.2
0.0
0.0
0.0
2
15.6
5.7
1.2
0.2
0.0
0.0
0.0
3
10.6
3.9
0.8
0.1
0.0
0.0
0.0
4
6.2
2.3
0.5
0.1
0.0
0.0
0.0
5
3.3
1.2
0.3
0.0
0.0
0.0
0.0
6
1.6
0.6
0.1
0.0
0.0
0.0
0.0

Rows = ECU goals; columns = CUW 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)
2.07
ECU
0.39
CUW

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.