Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group G · Matchday 5 · 2026-06-15

Belgium vs Egypt

Seattle, United States · neutral venue

Full time BEL 1–1 EGY
The agent called Belgium (58%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 15.8%
52.1%
BEL win
27.3%
Draw
20.5%
EGY win
Top scorelines
  • 1–0 15.8%
  • 0–0 14.1%
  • 2–0 10.7%
  • 1–1 10.1%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
BEL win
57.7%
Draw
25.7%
EGY win
16.7%

The model already favours Belgium (53% win), and the supplied intel reinforces that. Belgium's recent form is strong against weaker opponents, but their key players (De Bruyne, Tielemans) are in excellent form at top clubs, while Egypt's stars (Salah, Marmoush) have modest recent ratings. Egypt's coach publicly acknowledged the difficulty of the match. No injuries or conditions disrupt Belgium's advantage. I raise Belgium's win probability from 53% to 58% and lower Egypt's from 20% to 17%, reflecting a clear but not overwhelming edge. Belgium's expected goals (1.49) and Egypt's (0.72) suggest a low-scoring match leaning to Belgium. The most likely scoreline is 1-0 (14%), consistent with Belgium's defensive solidity and Egypt's struggle to score. 2-0 (12%) and 2-1 (10%) are also plausible. A draw (0-0 or 1-1) is possible but less likely given Belgium's quality advantage.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 8 sources kept:
  • “Belgium vs Egypt 2026-06-15 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could significantly alter the forecast.
  • “Belgium manager 2026 June” BEL · 3 hits
    A recent manager change could affect tactics and team morale.
  • “Egypt key player injury 2026 June” EGY · 2 hits
    Absence of a star player like Salah would shift the balance.
Agent scorelines
generated 2026-06-15
Last 5 — BEL
+0.69 pts/match vs model expectation · opp. avg #61
  • LIE #187 +0.0
  • USA #35 +1.2
  • MEX #21 -0.8
  • CRO #15 +1.7
  • TUN #48 +0.7
GF / GA last 10: 37 / 6
Last 5 — EGY
+0.58 pts/match vs model expectation · opp. avg #27
  • NIG #40 -0.4
  • KSA #69 +1.5
  • ESP #1 +0.6
  • RUS #24 +1.6
  • BRA #3 -0.4
GF / GA last 10: 13 / 6
Head-to-head (last 5)
  • 2022-11-18 Egypt 2–1 Belgium
  • 2018-06-06 Belgium 3–0 Egypt
  • 2005-02-09 Egypt 4–0 Belgium
  • 1999-03-30 Belgium 0–1 Egypt
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
14.1
9.0
3.5
1.0
0.3
0.1
0.0
1
15.8
10.1
3.9
1.2
0.3
0.1
0.0
2
10.7
6.8
2.6
0.8
0.2
0.0
0.0
3
5.6
3.6
1.4
0.4
0.1
0.0
0.0
4
2.5
1.6
0.6
0.2
0.0
0.0
0.0
5
1.0
0.7
0.3
0.1
0.0
0.0
0.0
6
0.4
0.2
0.1
0.0
0.0
0.0
0.0

Rows = BEL goals; columns = EGY 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)
1.45
BEL
0.73
EGY

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.