Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group E · Matchday 4 · 2026-06-14

Ivory Coast vs Ecuador

Philadelphia, United States · neutral venue

Full time CIV 1–0 ECU
The agent called Ecuador (40%) — Better than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–0 20.9%
26.0%
CIV win
33.8%
Draw
40.1%
ECU win
Top scorelines
  • 0–0 20.9%
  • 0–1 17.2%
  • 1–0 13.0%
  • 1–1 10.7%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CIV win
26.7%
Draw
33.0%
ECU win
40.3%

The model's prior (25/33/42) reflects Ecuador's higher baseline strength, likely due to their deeper European-based talent. Recent form shows both teams over-performing, but Ivory Coast's margin is larger and their friendly win over France is a strong signal. However, Ecuador's key players at top clubs (Caicedo, Estupiñán) provide a quality edge. The head-to-head is blank, conditions are neutral, and no injuries affect either side. The facts slightly narrow the gap but not enough to flip the prior; I maintain the model's probabilities as the best estimate. The model's expected goals (CIV 0.70, ECU 1.05) suggest a low-scoring affair, with 0-0 and 0-1 as the top scorelines. The defensive solidity of both teams (Ivory Coast's recent form includes clean sheets, Ecuador's WDDWW shows defensive resilience) supports a low total. The most likely outcomes are 0-0, 0-1, and 1-0, with a draw slightly more probable than a win for either side.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Ivory Coast vs Ecuador 2026-06-14 lineup news” match · 3 hits
    Late fitness or lineup changes could shift the forecast.
  • “Ivory Coast squad injuries suspensions June 2026” CIV · 3 hits
    Key player absences would affect team strength.
  • “Ecuador squad injuries suspensions June 2026” ECU · 3 hits
    Key player absences would affect team strength.
Agent scorelines
generated 2026-06-14
Last 5 — CIV
+1.46 pts/match vs model expectation · opp. avg #36
  • BUR #64 +1.2
  • EGY #37 -1.4
  • KOR #34 +1.6
  • SCO #39 +1.6
  • FRA #5 +2.5
GF / GA last 10: 19 / 8
Last 5 — ECU
+0.46 pts/match vs model expectation · opp. avg #55
  • NZL #83 +0.8
  • MAR #11 -0.2
  • NED #9 +0.1
  • KSA #69 +1.1
  • GUA #102 +0.4
GF / GA last 10: 12 / 5
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
20.9
17.2
8.5
3.3
1.1
0.3
0.1
1
13.0
10.7
5.3
2.0
0.7
0.2
0.1
2
4.8
4.0
2.0
0.8
0.3
0.1
0.0
3
1.4
1.2
0.6
0.2
0.1
0.0
0.0
4
0.4
0.3
0.1
0.1
0.0
0.0
0.0
5
0.1
0.1
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 = CIV goals; columns = ECU 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)
0.71
CIV
0.99
ECU

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.