Agent Lab — a live forecast exhibit · Applied AI
← Schedule
Group A · Matchday 8 · 2026-06-18

Czech Republic vs South Africa

Atlanta, United States · neutral venue

Most likely scoreline
1–0 15.0%
45.2%
CZE win
28.9%
Draw
25.8%
RSA win
Top scorelines
  • 1–0 15.0%
  • 0–0 14.8%
  • 1–1 10.8%
  • 0–1 10.7%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CZE win
53.3%
Draw
27.7%
RSA win
19.0%

The statistical model gives Czech Republic a 45% win probability, but the squad market value gap (3.2x) and recent form (South Africa underperforming by -0.94 pts/match) point to a stronger edge. Czech Republic's key players operate at higher club levels (Schick at Leverkusen, Soucek at West Ham) and have better recent ratings than South Africa's (e.g., Zwane at 5.2). The head-to-head is ancient and irrelevant. Conditions are neutral. I raise the home win probability to 55%, lowering away win to 18% and draw to 27%. Czech Republic's expected goals (1.27) and South Africa's (0.84) suggest a low-scoring match. The most likely scorelines are 1-0 and 2-0, reflecting Czech superiority but not a rout. 1-1 and 0-0 are plausible given South Africa's defensive potential. 0-1 is less likely due to Czech Republic's form advantage.

What the agent weighed
What the agent chose to investigate
The agent decided what to check on tavily — 9 sources kept:
  • “Czech Republic national football team squad injuries June 2026” CZE · 3 hits
    Key player injuries could significantly impact Czech Republic's strength.
  • “South Africa national football team squad injuries June 2026” RSA · 3 hits
    Key player injuries could significantly impact South Africa's strength.
  • “Czech Republic vs South Africa neutral venue Atlanta weather forecast June 18 2026” match · 3 hits
    Extreme weather (heat, humidity) could affect performance and tactics.
Agent scorelines
generated 2026-06-16
Last 5 — CZE
-0.13 pts/match vs model expectation · opp. avg #51
  • REP #50 -0.7
  • DEN #14 -0.1
  • KOS #57 +1.1
  • GUA #102 +0.5
  • KOR #34 -1.3
GF / GA last 10: 19 / 11
Last 5 — RSA
-0.94 pts/match vs model expectation · opp. avg #84
  • PAN #75 -0.7
  • PAN #75 -1.7
  • NIC #152 -1.5
  • JAM #96 -0.6
  • MEX #21 -0.7
GF / GA last 10: 12 / 13
Head-to-head (last 5)
  • 1997-12-13 South Africa 2–2 Czech Republic
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
14.8
10.7
4.6
1.6
0.5
0.1
0.0
1
15.0
10.8
4.7
1.6
0.5
0.1
0.0
2
9.1
6.6
2.8
1.0
0.3
0.1
0.0
3
4.3
3.1
1.3
0.5
0.1
0.0
0.0
4
1.8
1.3
0.5
0.2
0.1
0.0
0.0
5
0.6
0.5
0.2
0.1
0.0
0.0
0.0
6
0.2
0.2
0.1
0.0
0.0
0.0
0.0

Rows = CZE goals; columns = RSA 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)
1.27
CZE
0.84
RSA

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.