Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group C · Matchday 3 · 2026-06-13

Haiti vs Scotland

Foxborough, United States · neutral venue

Most likely scoreline
0–1 13.1%
15.6%
HAI win
21.4%
Draw
62.7%
SCO win
Top scorelines
  • 0–1 13.1%
  • 0–2 11.2%
  • 0–0 9.2%
  • 1–1 8.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
HAI win
16.0%
Draw
20.7%
SCO win
63.3%

The model already heavily favours Scotland (63% away win), and the supplied intel supports that lean. Scotland's recent form is stronger (+0.26 pts/match vs expectations) against tougher opposition (rank #50) compared to Haiti's (in-line vs rank #76). Scotland's key players operate at a higher club level (Napoli, Aston Villa, Bournemouth) than Haiti's (Esteghlal, AEK Athens, Almere City), reinforcing the quality gap. No injuries, neutral conditions, and no head-to-head history leave no reason to diverge from the model; I slightly increase away probability to 65% to reflect the form and player quality edge. With Scotland's expected goals at 2.01 and Haiti's at 0.76, the most likely outcome is a low-scoring away win. The top scoreline 0-1 (13%) reflects Scotland's defensive solidity and Haiti's limited attack. 0-2 (12%) and 0-0 (9%) are also plausible, while 1-1 (9%) accounts for a potential Haiti goal. The distribution is concentrated on low totals given both teams' moderate attacking output.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Haiti vs Scotland 2026-06-14 starting lineup injuries” match · 3 hits
    Late fitness or lineup changes could significantly affect the match outcome.
  • “Haiti national team squad news June 2026” HAI · 3 hits
    Key player availability or suspensions may shift the balance.
  • “Scotland national team squad news June 2026” SCO · 3 hits
    Key player availability or suspensions may shift the balance.
Agent scorelines
generated 2026-06-13
Last 5 — HAI
+0.14 pts/match vs model expectation · opp. avg #76
  • NIC #151 +1.0
  • TUN #43 -0.7
  • ICE #61 +0.1
  • NZL #85 +1.5
  • PER #42 -0.8
GF / GA last 10: 15 / 10
Last 5 — SCO
+0.26 pts/match vs model expectation · opp. avg #50
  • DEN #14 +1.9
  • JPN #18 -1.3
  • CIV #32 -1.3
  • CUW #114 +0.5
  • BOL #72 +1.4
GF / GA last 10: 21 / 10
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
9.2
13.1
11.2
7.5
4.3
2.2
1.1
1
6.0
8.6
7.4
4.9
2.8
1.5
0.7
2
2.4
3.4
2.9
1.9
1.1
0.6
0.3
3
0.7
1.0
0.9
0.6
0.3
0.2
0.1
4
0.2
0.3
0.2
0.2
0.1
0.0
0.0
5
0.0
0.1
0.1
0.0
0.0
0.0
0.0
6
0.0
0.0
0.0
0.0
0.0
0.0
0.0

Rows = HAI goals; columns = SCO 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)
0.76
HAI
2.01
SCO

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.