Decision Tree Solver

"Should we settle or go to trial" is not answered by instinct or by whoever argues longest — it is three numbers and a probability, and most people have never actually multiplied them. This skill extracts the tree hiding inside a messy decision (the choices, the chances, the payoffs, the costs of playing), computes the rollback with the bundled script, and — the part instinct can never do — finds the break-even: the probability at which the recommendation flips. Because "trial is worth it if you win 60% of the time" is an opinion, but "the answer flips at 90% — are you more than 90% sure?" is a decision made tractable. The script is deterministic, stdlib-only, and shows its arithmetic.

What This Skill Produces

• The extracted tree — decisions, chance nodes with probabilities, outcomes with values, and the costs of each path, pulled from the situation as described
• The rollback — expected value at every node, the best choice named at every fork, from the script
• The break-even scan — for each two-way uncertainty, the probability at which the top-level choice flips, which is the number that makes probability arguments productive
• The robustness read — whether the answer survives the probabilities being argued about, or hinges on a number nobody can defend
• The leaves-out list — what expected value cannot see here: risk appetite, one-shot vs repeated, the unquantified costs

Required Inputs

Ask for these if not provided:

• The choices — the real options on the table, including the do-nothing one
• The uncertainties — what could happen under each choice, and the requester's honest probability for each (pushing back on false precision is part of the job)
• The payoffs and costs — the money (or a stated proxy) at each end point, and what each path costs to walk: fees, time priced honestly, deposits
• The stakes context — one-shot or repeatable, and whether the worst branch is survivable — because expected value is the right tool for repeatable bets and needs a caveat for ruinous one-shots