Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group K · Matchday 13 · 2026-06-23

Portugal vs Uzbekistan

Houston, United States · neutral venue

Full time POR 5–0 UZB
The agent called Portugal (77%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 14.8%
70.9%
POR win
19.0%
Draw
9.6%
UZB win
Top scorelines
  • 1–0 14.8%
  • 2–0 13.6%
  • 3–0 9.8%
  • 0–0 9.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
POR win
76.7%
Draw
16.0%
UZB win
7.3%

The statistical model already favours Portugal at 65%, but the squad market value gap (94th vs 23rd percentile) indicates the model may understate the talent disparity, as Portugal's elite players (Bruno Fernandes, Bernardo Silva, Ronaldo) far outclass Uzbekistan's modest squad. Uzbekistan's poor recent form (-0.47 pts/match) and likely demoralizing loss to Colombia in their opener further tilt the scale. I raise Portugal's win probability to 78% to reflect the clear talent and form advantage, while keeping a small draw chance (15%) for tournament variance. Portugal's expected goals of 1.89 from the model are conservative given the squad gap; I expect 2-3 goals from Portugal. Uzbekistan's expected goals of 0.57 reflect their limited attacking threat, so a clean sheet is likely. The most probable scorelines are 2-0 and 1-0, with 3-0 also plausible if Portugal's attack clicks.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Portugal vs Uzbekistan 2026-06-23 lineup injuries” match · 3 hits
    Late fitness or lineup changes could shift match odds.
  • “Portugal squad 2026 World Cup injuries suspensions” POR · 3 hits
    Key player absences like Ronaldo or Fernandes would heavily impact Portugal.
  • “Uzbekistan squad 2026 World Cup injuries suspensions” UZB · 3 hits
    Uzbekistan's star players missing could swing forecast.
Agent scorelines
generated 2026-06-22
Last 5 — POR
-0.02 pts/match vs model expectation · opp. avg #35
  • MEX #20 -0.7
  • USA #37 +1.0
  • CHI #28 +0.7
  • NIG #38 +0.6
  • COD #54 -1.2
GF / GA last 10: 22 / 10
Last 5 — UZB
-0.36 pts/match vs model expectation · opp. avg #37
  • GAB #82 +1.1
  • VEN #47 -0.2
  • CAN #41 -0.8
  • NED #9 -0.3
  • COL #8 -0.5
GF / GA last 10: 12 / 12
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
9.6
4.6
1.3
0.3
0.1
0.0
0.0
1
14.8
7.1
2.1
0.5
0.1
0.0
0.0
2
13.6
6.5
1.9
0.4
0.1
0.0
0.0
3
9.8
4.7
1.4
0.3
0.1
0.0
0.0
4
6.0
2.9
0.8
0.2
0.0
0.0
0.0
5
3.3
1.6
0.5
0.1
0.0
0.0
0.0
6
1.7
0.8
0.2
0.1
0.0
0.0
0.0

Rows = POR goals; columns = UZB 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)
2.22
POR
0.53
UZB

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.