Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group G · Matchday 16 · 2026-06-26

Egypt vs Iran

Seattle, United States · neutral venue

Full time EGY 1–1 IRN
The agent called Egypt (42%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–0 19.0%
33.3%
EGY win
32.8%
Draw
33.9%
IRN win
Top scorelines
  • 0–0 19.0%
  • 0–1 14.6%
  • 1–0 14.5%
  • 1–1 11.1%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
EGY win
41.7%
Draw
31.0%
IRN win
27.3%

The statistical model slightly favours Iran (35% vs 32%), but the squad value gap (5.4x in Egypt's favour), the presence of elite players like Salah and Marmoush, Egypt's over-performance in recent form, and the news that Iran's star striker Azmoun is omitted all point to Egypt being stronger than the model implies. I shift the prior toward Egypt, raising home win to 40% and lowering away win to 27%, while keeping draw near the model's 33% given the limited head-to-head history and Iran's solid recent results. Egypt's expected goals rise from 0.87 to about 1.1 given the talent advantage and Iran's weakened attack without Azmoun; Iran's drop to about 0.8. The most likely scorelines reflect a low-scoring match with Egypt slight favourites: 1-0 (14%), 0-0 (13%), 1-1 (12%).

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Egypt vs Iran 2026-06-27 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could shift the balance.
  • “Egypt squad 2026 June injuries” EGY · 3 hits
    Key player availability is unknown and could affect Egypt's strength.
  • “Iran squad 2026 June injuries” IRN · 3 hits
    Key player availability is unknown and could affect Iran's strength.
Agent scorelines
generated 2026-06-26
Last 5 — EGY
+0.52 pts/match vs model expectation · opp. avg #26
  • ESP #1 +0.6
  • RUS #22 +1.6
  • BRA #3 -0.4
  • BEL #10 +0.2
  • NZL #94 +0.9
GF / GA last 10: 16 / 8
Last 5 — IRN
+0.23 pts/match vs model expectation · opp. avg #60
  • COS #66 +1.2
  • GAM #86 +0.9
  • MAL #45 +1.4
  • NZL #94 -1.1
  • BEL #10 +0.2
GF / GA last 10: 16 / 7
Head-to-head (last 5)
  • 2000-06-07 Iran 1–1 Egypt
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
19.0
14.6
6.7
2.4
0.7
0.2
0.1
1
14.5
11.1
5.1
1.8
0.6
0.2
0.0
2
6.6
5.1
2.3
0.8
0.3
0.1
0.0
3
2.3
1.8
0.8
0.3
0.1
0.0
0.0
4
0.7
0.5
0.3
0.1
0.0
0.0
0.0
5
0.2
0.2
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 = EGY goals; columns = IRN 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)
0.9
EGY
0.91
IRN

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.