Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group K · Matchday 7 · 2026-06-17

Portugal vs DR Congo

Houston, United States · neutral venue

Most likely scoreline
1–0 16.3%
65.0%
POR win
22.5%
Draw
12.3%
COD win
Top scorelines
  • 1–0 16.3%
  • 2–0 13.3%
  • 0–0 12.0%
  • 3–0 8.5%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
POR win
74.0%
Draw
17.0%
COD win
9.0%

The statistical model already gives Portugal a strong 65% win probability, but the supplied intel points to an even larger gap. Portugal's squad is vastly more valuable (94th vs 32nd percentile), their key players are in excellent form, and they have over-performed expectations recently. DR Congo, meanwhile, faced disruption from an Ebola-related isolation order and cancelled training camp, which likely hampers preparation. The climate-controlled dome neutralizes any weather factor. I raise Portugal's win probability to 72%, lowering draw and away win accordingly. Portugal's expected goals (1.88) and DR Congo's low xG (0.56) suggest a relatively low-scoring match with Portugal controlling. The most likely scorelines are 2-0 and 1-0, reflecting Portugal's defensive solidity and DR Congo's limited attack. A 3-0 is possible if Portugal's stars click, while a 1-1 draw is less likely but not negligible given DR Congo's occasional counter threat from Wissa.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Portugal vs DR Congo 2026-06-17 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could significantly affect the forecast.
  • “Portugal squad 2026 World Cup lineup injuries” POR · 3 hits
    Key player availability like Ronaldo or Fernandes could shift the odds.
  • “DR Congo squad 2026 World Cup injuries suspensions” COD · 3 hits
    Absence of a key defender or attacker could change match dynamics.
Agent scorelines
generated 2026-06-16
Last 5 — POR
+0.53 pts/match vs model expectation · opp. avg #45
  • ARM #101 +0.1
  • MEX #21 -0.7
  • USA #35 +1.1
  • CHI #28 +0.7
  • NIG #40 +0.6
GF / GA last 10: 26 / 9
Last 5 — COD
-0.18 pts/match vs model expectation · opp. avg #67
  • ALG #29 -1.0
  • BER #170 +0.2
  • JAM #96 +1.2
  • DEN #14 +0.1
  • CHI #28 -1.2
GF / GA last 10: 11 / 5
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
12.0
6.0
1.8
0.4
0.1
0.0
0.0
1
16.3
8.2
2.5
0.6
0.1
0.0
0.0
2
13.3
6.7
2.0
0.5
0.1
0.0
0.0
3
8.5
4.3
1.3
0.3
0.1
0.0
0.0
4
4.6
2.3
0.7
0.2
0.0
0.0
0.0
5
2.3
1.2
0.3
0.1
0.0
0.0
0.0
6
1.0
0.5
0.2
0.0
0.0
0.0
0.0

Rows = POR goals; columns = COD 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)
1.88
POR
0.56
COD

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.