Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group K · Matchday 17 · 2026-06-27

Colombia vs Portugal

Miami Gardens, United States · neutral venue

Full time COL 0–0 POR
The agent called Portugal (46%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline
0–0 14.5%
31.7%
COL win
29.3%
Draw
39.0%
POR win
Top scorelines
  • 0–0 14.5%
  • 0–1 13.5%
  • 1–0 11.9%
  • 1–1 11.1%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
COL win
26.0%
Draw
27.7%
POR win
46.3%

The statistical model already gives Portugal a slight edge (39% win), but the squad market value gap (Portugal ~3.2x more valuable, ranked 4th vs 22nd) and the quality of key players (Bruno Fernandes, Bernardo Silva, Ronaldo vs Colombia's Díaz and aging James) suggest Portugal's talent advantage is larger than the model captures. Colombia's recent form is strong but against weaker opponents (avg rank #53), while Portugal's form is solid against tougher sides (avg rank #43). I shift probability from home win to away win, raising Portugal's chances to 47%, lowering Colombia to 25%, and keeping draw near the model's 28%. Portugal's superior squad depth and attacking talent (Ronaldo, Bruno Fernandes, Bernardo Silva) should generate more chances, while Colombia's defense, led by Mina (Cagliari), is less tested. Expected goals move from model's 1.21-1.06 to roughly 1.4-0.9, making 0-1 and 1-1 the top scorelines, with 0-2 also likely. Low-scoring draw (0-0) remains possible but less probable given Portugal's offensive quality.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Colombia vs Portugal 2026-06-27 team news injuries suspensions” match · 3 hits
    Late fitness updates or suspensions could shift the forecast.
  • “Colombia starting lineup 2026-06-27” COL · 3 hits
    Key player availability like James Rodriguez or Luis Diaz affects Colombia's strength.
  • “Portugal starting lineup 2026-06-27” POR · 3 hits
    Cristiano Ronaldo or Bruno Fernandes availability is crucial for Portugal.
Agent scorelines
generated 2026-06-27
Last 5 — COL
+0.56 pts/match vs model expectation · opp. avg #54
  • FRA #5 -1.2
  • COS #66 +0.5
  • JOR #75 +0.4
  • UZB #69 +0.7
  • COD #54 +0.9
GF / GA last 10: 20 / 8
Last 5 — POR
+0.14 pts/match vs model expectation · opp. avg #45
  • USA #37 +1.0
  • CHI #28 +0.7
  • NIG #38 +0.6
  • COD #54 -1.2
  • UZB #69 +0.6
GF / GA last 10: 24 / 8
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
14.5
13.5
7.6
3.3
1.2
0.4
0.1
1
11.9
11.1
6.2
2.7
1.0
0.3
0.1
2
5.9
5.5
3.1
1.3
0.5
0.2
0.1
3
2.3
2.1
1.2
0.5
0.2
0.1
0.0
4
0.7
0.7
0.4
0.2
0.1
0.0
0.0
5
0.2
0.2
0.1
0.1
0.0
0.0
0.0
6
0.1
0.1
0.0
0.0
0.0
0.0
0.0

Rows = COL goals; columns = POR 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)
0.99
COL
1.15
POR

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.