Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group C · Matchday 14 · 2026-06-24

Morocco vs Haiti

Atlanta, United States · neutral venue

Full time MAR 4–2 HAI
The agent called Morocco (78%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 15.6%
73.7%
MAR win
18.1%
Draw
7.6%
HAI win
Top scorelines
  • 1–0 15.6%
  • 2–0 14.6%
  • 3–0 10.7%
  • 0–0 10.0%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
MAR win
77.7%
Draw
16.0%
HAI win
6.3%

The model already gives Morocco a strong 72% win probability, and the supplied intel reinforces that. Morocco's recent form is positive (+0.30 pts/match over expectation) while Haiti's is poor (DWLLL). The squad value gap is enormous (8.1x) and key players like Hakimi and Brahim Díaz play at elite clubs, while Haiti's best players are at lower-tier sides. No injuries or conditions alter the picture. I adjust the win probability slightly upward to 78% to reflect the talent and form advantage, keeping the draw at 15% and away win at 7%. Morocco's expected goals (2.10) and Haiti's (0.43) from the model suggest a low-scoring game for Haiti. The most likely scorelines are 2-0 and 1-0, reflecting Morocco's dominance but not a blowout. 3-0 is also plausible given the squad gap. Haiti's narrow defeat to Scotland (1-0?) shows they can be competitive, so 2-1 and 1-1 are possible but less likely.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Morocco national team injuries suspensions June 2026” MAR · 3 hits
    Key player availability could shift Morocco's strength significantly.
  • “Haiti national team injuries suspensions June 2026” HAI · 3 hits
    Haiti's squad depth is thin; missing a starter could heavily impact performance.
  • “Atlanta weather forecast June 24 2026” match · 3 hits
    Extreme heat or rain could affect playing conditions and team tactics.
Agent scorelines
generated 2026-06-24
Last 5 — MAR
+0.27 pts/match vs model expectation · opp. avg #59
  • BUR #122 +0.2
  • MAD #110 +0.2
  • NOR #19 -0.8
  • BRA #3 +0.0
  • SCO #39 +1.2
GF / GA last 10: 20 / 4
Last 5 — HAI
-0.17 pts/match vs model expectation · opp. avg #48
  • ICE #60 +0.2
  • NZL #94 +1.4
  • PER #42 -0.8
  • SCO #39 -0.6
  • BRA #3 -0.1
GF / GA last 10: 12 / 11
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
10.0
4.1
1.0
0.2
0.0
0.0
0.0
1
15.6
6.4
1.6
0.3
0.0
0.0
0.0
2
14.6
6.0
1.5
0.3
0.0
0.0
0.0
3
10.7
4.4
1.1
0.2
0.0
0.0
0.0
4
6.7
2.8
0.7
0.1
0.0
0.0
0.0
5
3.8
1.6
0.4
0.1
0.0
0.0
0.0
6
2.0
0.8
0.2
0.0
0.0
0.0
0.0

Rows = MAR goals; columns = HAI 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)
2.28
MAR
0.45
HAI

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.