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

Colombia vs DR Congo

Zapopan, Mexico · neutral venue

Full time COL 1–0 COD
The agent called Colombia (66%) — Better than the model call right

The forecast below is what the agent published before kickoff.

Most likely scoreline
1–0 18.7%
57.5%
COL win
27.5%
Draw
14.9%
COD win
Top scorelines
  • 1–0 18.7%
  • 0–0 16.3%
  • 2–0 12.8%
  • 1–1 9.1%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
COL win
66.0%
Draw
22.3%
COD win
11.7%

The model's prior (60% home win) is supported by Colombia's superior squad value (2.2x, ranking 22 vs 33), stronger recent form against better opposition, and a clear talent advantage in key players like Díaz and Rodríguez. DR Congo's gritty 0-0 draw with Portugal is a mild counterweight, but Colombia's attacking depth and overall quality justify a slight upward adjustment from the prior. The moderate altitude and humid conditions are neutral for both sides. I move Colombia's win probability to 65%, reflecting the talent gap and form edge. Colombia's expected goals (1.61) and DR Congo's low xG (0.55) suggest a low-scoring game, with 1-0 and 2-0 as the most likely outcomes. DR Congo's defensive organization (shown vs Portugal) could keep it tight, but Colombia's firepower should break through. The 0-0 draw is possible but less likely given Colombia's attacking talent.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Colombia national team injuries suspensions June 2026” COL · 3 hits
    Late fitness or suspension news could change Colombia's lineup.
  • “DR Congo national team injuries suspensions June 2026” COD · 3 hits
    Late fitness or suspension news could change DR Congo's lineup.
  • “Colombia vs DR Congo 2026 match preview” match · 3 hits
    Check for any reported lineup changes or tactical news.
Agent scorelines
generated 2026-06-22
Last 5 — COL
+0.17 pts/match vs model expectation · opp. avg #46
  • CRO #15 -1.6
  • FRA #5 -1.2
  • COS #66 +0.5
  • JOR #75 +0.4
  • UZB #69 +0.7
GF / GA last 10: 25 / 11
Last 5 — COD
-0.02 pts/match vs model expectation · opp. avg #62
  • BER #169 +0.2
  • JAM #91 +1.1
  • DEN #14 +0.0
  • CHI #28 -1.3
  • POR #6 +0.5
GF / GA last 10: 11 / 6
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
16.3
8.0
2.3
0.5
0.1
0.0
0.0
1
18.7
9.1
2.7
0.6
0.1
0.0
0.0
2
12.8
6.2
1.8
0.4
0.1
0.0
0.0
3
6.9
3.3
1.0
0.2
0.0
0.0
0.0
4
3.1
1.5
0.4
0.1
0.0
0.0
0.0
5
1.3
0.6
0.2
0.0
0.0
0.0
0.0
6
0.5
0.2
0.1
0.0
0.0
0.0
0.0

Rows = COL 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)
1.49
COL
0.54
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.