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

Canada vs Switzerland

Vancouver, Canada

Full time CAN 1–2 SUI
The agent called Switzerland (45%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–1 11.2%
30.2%
CAN win
25.2%
Draw
44.5%
SUI win
Top scorelines
  • 0–1 11.2%
  • 1–1 10.4%
  • 0–0 9.8%
  • 1–0 9.0%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CAN win
30.0%
Draw
25.0%
SUI win
45.0%

The model prior already favours Switzerland (43% away win vs 32% home win). Squad market value (Switzerland ~2.5x more valuable, ranks 19 vs 30), key player depth (Xhaka, Embolo, Vargas vs David, Davies), and Canada's injury to Koné all reinforce that edge. Recent form is neutral, conditions are neutral, and no market data to adjust. I nudge the away win slightly higher to 45% and lower home win to 30%, reflecting the structural talent gap and availability advantage. Switzerland's expected goals (1.46) edge Canada's (1.18) aligns with a likely low-scoring match. Most probable scorelines are 0-1 (11%), 1-1 (10%), and 0-2 (9%). Canada's attack (David, Larin) can score but Switzerland's defence (Kobel) is solid, so 1-1 is plausible. The distribution skews toward Switzerland winning by one goal.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 6 sources kept:
  • “Canada vs Switzerland 2026-06-24 lineup news” match · 3 hits
    Late fitness or lineup changes could shift the forecast.
  • “Switzerland squad injuries suspensions June 2026” SUI · 3 hits
    Key Swiss player availability could affect match outcome.
Agent scorelines
generated 2026-06-24
Last 5 — CAN
+0.02 pts/match vs model expectation · opp. avg #67
  • ICE #60 -0.9
  • TUN #53 -0.7
  • UZB #69 +1.0
  • BIH #64 -0.9
  • QAT #87 +0.7
GF / GA last 10: 14 / 4
Last 5 — SUI
-0.24 pts/match vs model expectation · opp. avg #55
  • NOR #19 -0.3
  • JOR #75 +0.5
  • AUS #29 -0.9
  • QAT #87 -1.5
  • BIH #64 +0.9
GF / GA last 10: 20 / 10
Head-to-head (last 5)
  • 2002-05-15 Switzerland 1–3 Canada
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
9.8
11.2
7.7
4.1
1.9
0.8
0.3
1
9.0
10.4
7.1
3.8
1.8
0.7
0.3
2
5.0
5.7
4.0
2.1
1.0
0.4
0.2
3
2.2
2.5
1.7
0.9
0.4
0.2
0.1
4
0.8
0.9
0.6
0.3
0.2
0.1
0.0
5
0.3
0.3
0.2
0.1
0.1
0.0
0.0
6
0.1
0.1
0.1
0.0
0.0
0.0
0.0

Rows = CAN goals; columns = SUI 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)
1.14
CAN
1.49
SUI

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.