Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group C · Matchday 9 · 2026-06-19

Scotland vs Morocco

Foxborough, United States · neutral venue

Full time SCO 0–1 MAR
The agent called Morocco (51%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–0 18.1%
20.2%
SCO win
30.6%
Draw
49.2%
MAR win
Top scorelines
  • 0–0 18.1%
  • 0–1 18.0%
  • 0–2 10.8%
  • 1–0 10.2%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
SCO win
19.3%
Draw
29.3%
MAR win
51.3%

The model already favours Morocco (47% away win), and the supplied intel supports that lean rather than challenging it. Morocco's squad is significantly more valuable (1.8x), their key players operate at higher club levels, and their recent form came against stronger opposition than Scotland's. The head-to-head result also favours Morocco. With no injuries or conditions to offset these gaps, I slightly increase Morocco's probability from 47% to 50%, trimming the draw and home win accordingly. Morocco's expected goals (1.18) and Scotland's (0.65) from the model suggest a low-scoring match. Morocco's defensive solidity (clean sheets in recent form) and Scotland's modest attack point to a 1-0 or 2-0 away win as most likely, with the 0-0 draw also plausible. I keep the top scorelines close to the model's distribution, slightly favouring Morocco clean-sheet outcomes.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 6 sources kept:
  • “Scotland vs Morocco 2026-06-19 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could significantly alter lineup strength.
  • “Scotland Morocco Foxborough weather forecast 2026-06-19” match · 3 hits
    Weather conditions like heat or rain can affect playing style and stamina.
Agent scorelines
generated 2026-06-19
Last 5 — SCO
+0.48 pts/match vs model expectation · opp. avg #66
  • JPN #18 -1.2
  • CIV #26 -1.2
  • CUW #119 +0.5
  • BOL #73 +1.4
  • HAI #96 +0.8
GF / GA last 10: 22 / 10
Last 5 — MAR
-0.06 pts/match vs model expectation · opp. avg #58
  • PAR #35 +1.3
  • BUR #122 +0.2
  • MAD #110 +0.2
  • NOR #19 -0.8
  • BRA #3 +0.0
GF / GA last 10: 20 / 4
Head-to-head (last 5)
  • 1998-06-23 Scotland 0–3 Morocco
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
18.1
18.0
10.8
5.0
2.0
0.7
0.2
1
10.2
10.1
6.1
2.8
1.1
0.4
0.1
2
3.4
3.4
2.0
1.0
0.4
0.1
0.0
3
0.9
0.9
0.5
0.3
0.1
0.0
0.0
4
0.2
0.2
0.1
0.1
0.0
0.0
0.0
5
0.0
0.0
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 = SCO goals; columns = MAR 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)
0.63
SCO
1.24
MAR

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.