The page changed after submission.
Submitting one row changed the position of later rows. An index-based selector could therefore target the wrong match. The lesson: bind an action to match identity and re-check the target before the next entry.
Automation
A good prediction is useless once the deadline passes.
A personal football prediction experiment combining research, a mathematical model and market information with a submission workflow. The main lesson was about deadlines, not accuracy.
Not one prompt. An entire workflow.
This personal football prediction experiment connected research, calculations, a human decision and browser submission. The engineering scope was the coordination between those steps, not just a model that predicts scores.
- 104
- matches in the tournament scope
- 126
- archived research runs
Source: project archive review, 11 September 2026. These describe scope, not successful automated submissions or correct predictions.
Research
The agent collected match research. Repeated research runs allowed the analysis to be refreshed rather than relying on a single conversation.
Calculation
A mathematical model calculated expected goals and possible score probabilities. Market odds were an input to the model, not merely a comparison afterwards.
Selection
Probabilities had to become a specific score selection. The most likely score and the best choice for the competition’s scoring rules are not necessarily identical.
Human approval
In the later workflow, I reviewed the proposal and decided what to submit. This boundary was added during development; not every earlier submission had this approval step.
Control rule: information or approval missing → stop and ask.
Browser entry
The automation located the correct match in the prediction form and entered the selection. This was interaction with a real web form, not just an answer displayed in chat.
Checks and logging
Submissions and results were collected for review. Differences between logs and standings showed why an internal record is not automatically the final source of truth.
What the work taught me
A prepared prediction is not a submitted prediction.
One documented missed deadline left a prepared prediction unsubmitted. Completed analysis, human approval and timely submission require separate checks. Having an alert does not prove the failure cannot recur.
An outcome needs evidence.
The captured standings and internal point totals did not fully reconcile. This page therefore does not claim a final placing, an accuracy percentage or estimated time savings.
Next step
Get in touch Want to build something similar?
Let us talk about how to build with AI while you keep control of the result.