Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group I · Matchday 16 · 2026-06-26

Senegal vs Iraq

Toronto, Canada · neutral venue

Full time SEN 5–0 IRQ
The agent called Senegal (70%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 17.0%
60.0%
SEN win
25.1%
Draw
14.7%
IRQ win
Top scorelines
  • 1–0 17.0%
  • 0–0 13.7%
  • 2–0 12.7%
  • 1–1 9.0%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
SEN win
70.0%
Draw
20.7%
IRQ win
9.3%

The statistical model already gives Senegal a strong 55% win probability, and the squad market value gap (Senegal 77th percentile vs Iraq 2nd percentile) is a massive independent signal that the model may understate due to Senegal's recent underperformance. Senegal's key players are far superior and play at higher club levels. The only counterweight is Senegal's poor recent form and the absence of GK É. Mendy, but these are insufficient to overcome the talent chasm. I increase Senegal's win probability to 70%, reducing draw and Iraq win accordingly. Senegal's expected goals (1.47) and Iraq's (0.61) suggest a low-scoring game tilted toward Senegal. The talent gap should produce more chances for Senegal, but Iraq's defensive setup and Senegal's recent scoring struggles (2 goals in last 5 matches) cap the total. The most likely scorelines are 2-0 and 1-0, with 2-1 and 3-0 also plausible. Draws like 1-1 or 0-0 are possible but less likely given the quality disparity.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Senegal squad injury updates June 2026” SEN · 3 hits
    Check for late fitness issues beyond Mendy that could affect lineup.
  • “Iraq squad injury updates June 2026” IRQ · 3 hits
    Iraq's key player availability could shift match odds.
  • “Senegal vs Iraq neutral venue Toronto weather forecast June 26 2026” match · 3 hits
    Weather conditions (heat, rain, wind) can impact play style and performance.
Agent scorelines
generated 2026-06-26
Last 5 — SEN
-0.96 pts/match vs model expectation · opp. avg #44
  • GAM #86 +0.5
  • USA #37 -1.4
  • KSA #74 -0.8
  • FRA #5 -0.8
  • NOR #19 -1.3
GF / GA last 10: 15 / 14
Last 5 — IRQ
-0.26 pts/match vs model expectation · opp. avg #48
  • AND #167 +0.8
  • ESP #1 +0.9
  • VEN #47 -1.0
  • NOR #19 -0.5
  • FRA #5 -0.3
GF / GA last 10: 9 / 15
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
13.7
7.2
2.3
0.6
0.1
0.0
0.0
1
17.0
9.0
2.9
0.7
0.1
0.0
0.0
2
12.7
6.7
2.1
0.5
0.1
0.0
0.0
3
7.4
3.9
1.2
0.3
0.1
0.0
0.0
4
3.7
1.9
0.6
0.2
0.0
0.0
0.0
5
1.7
0.9
0.3
0.1
0.0
0.0
0.0
6
0.7
0.4
0.1
0.0
0.0
0.0
0.0

Rows = SEN goals; columns = IRQ 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)
1.66
SEN
0.59
IRQ

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.