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

Ivory Coast vs Ecuador

Philadelphia, United States · neutral venue

Most likely scoreline
0–0 20.1%
24.6%
CIV win
33.1%
Draw
42.3%
ECU win
Top scorelines
  • 0–0 20.1%
  • 0–1 17.5%
  • 1–0 12.3%
  • 1–1 10.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CIV win
29.3%
Draw
33.7%
ECU win
37.0%

The model and intel both suggest Ecuador as the stronger side on paper, but Ivory Coast's recent form (+1.49 pts/match over expectation, including a friendly win over France) is too strong to ignore. I shift the home win probability up from 25% to 30% and reduce away win from 42% to 37%, keeping the draw near the model's 33% as a plausible result given the lack of head-to-head data and the competitive balance. The model's low expected goals (0.69-1.05) and the defensive solidity of both sides (no major injuries, disciplined squads) point to a low-scoring match. The most likely scorelines are 0-0, 0-1, 1-0, and 1-1, with a slight tilt toward Ecuador due to their individual quality, but Ivory Coast's form gives them a realistic chance of a 1-0 or 2-1 win.

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 injuries” match · 3 hits
    Late fitness or lineup changes could significantly affect the match outcome.
  • “Ivory Coast squad 2026 World Cup injuries suspensions” CIV · 3 hits
    Key player absences would shift the balance of the game.
  • “Ecuador squad 2026 World Cup injuries suspensions” ECU · 3 hits
    Key player absences would shift the balance of the game.
Agent scorelines
generated 2026-06-13
Last 5 — CIV
+1.49 pts/match vs model expectation · opp. avg #37
  • BUR #65 +1.2
  • EGY #39 -1.4
  • KOR #37 +1.6
  • SCO #38 +1.6
  • FRA #5 +2.5
GF / GA last 10: 19 / 8
Last 5 — ECU
+0.43 pts/match vs model expectation · opp. avg #55
  • NZL #85 +0.8
  • MAR #12 -0.2
  • NED #9 +0.1
  • KSA #70 +1.0
  • GUA #100 +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
20.1
17.5
9.1
3.7
1.3
0.4
0.1
1
12.3
10.6
5.5
2.2
0.8
0.2
0.1
2
4.5
3.9
2.0
0.8
0.3
0.1
0.0
3
1.3
1.1
0.6
0.2
0.1
0.0
0.0
4
0.3
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)
0.69
CIV
1.05
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.