Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group B · Matchday 2 · 2026-06-12

Canada vs Bosnia and Herzegovina

Toronto, Canada

Most likely scoreline
1–0 12.6%
53.0%
CAN win
24.3%
Draw
22.6%
BIH win
Top scorelines
  • 1–0 12.6%
  • 0–0 10.1%
  • 1–1 9.9%
  • 2–0 9.5%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CAN win
49.3%
Draw
28.0%
BIH win
22.7%

The model's prior favours Canada (54%) due to home advantage and squad quality, but the confirmed absence of Alphonso Davies—Canada's best player and a world-class left-back—significantly weakens their defence and transition. Bosnia's recent form is poor (five draws) but they have veteran quality in Dzeko and a solid midfield. The Davies injury is a strong signal that reduces Canada's edge, so I lower their win probability from 54% to 50% and raise the draw to 28%, keeping Bosnia's away win near the model's 22%. With Canada's attack still potent (David, Buchanan) but Davies missing, the expected goals drop slightly from 1.72 to ~1.5. Bosnia's attack is modest (0.92 xG in model) and they struggle to score consistently. A 1-0 or 1-1 draw is most plausible, with 0-0 also possible given Canada's defensive uncertainty. The scoreline distribution shifts toward lower totals.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Canada vs Bosnia and Herzegovina 2026-06-12 lineup injuries” match · 3 hits
    Late fitness or lineup changes could shift the forecast.
  • “Canada national team injuries June 2026” CAN · 3 hits
    Key player absences would significantly affect Canada's strength.
  • “Bosnia and Herzegovina national team injuries June 2026” BIH · 3 hits
    Key player absences would significantly affect Bosnia's strength.
Agent scorelines
generated 2026-06-12
Last 5 — CAN
+0.30 pts/match vs model expectation · opp. avg #44
  • ECU #16 -0.1
  • VEN #45 +1.6
  • ICE #61 -0.9
  • TUN #43 -0.6
  • UZB #54 +1.3
GF / GA last 10: 11 / 4
Last 5 — BIH
-0.19 pts/match vs model expectation · opp. avg #45
  • AUT #22 +0.4
  • WAL #46 +0.1
  • ITA #13 +0.2
  • NOR #71 -0.7
  • PAN #74 -0.3
GF / GA last 10: 20 / 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
10.1
7.8
3.7
1.3
0.4
0.1
0.0
1
12.6
9.9
4.6
1.7
0.5
0.1
0.0
2
9.5
7.4
3.5
1.3
0.4
0.1
0.0
3
5.6
4.4
2.0
0.7
0.2
0.1
0.0
4
2.8
2.2
1.0
0.4
0.1
0.0
0.0
5
1.3
1.0
0.5
0.2
0.1
0.0
0.0
6
0.5
0.4
0.2
0.1
0.0
0.0
0.0

Rows = CAN goals; columns = BIH 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)
1.68
CAN
0.93
BIH

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.