3 tagged ampl, measured the same way as everything else here.
Agent
Expert AMPL debugger for infeasibility, unboundedness, IIS, conflict analysis, and solve failures. Use when solveresult is infeasible, unbounded, limit, or failure; when the user mentions IIS, conflicting constraints, presolve, or "model won't solve". Readonly diagnosis — fixes are suggestions until verified.
Agent
Optimization expert that explains AMPL models: variable-constraint linkage, logical vs algebraic constraints, problem classification, and complexity analysis. Use when the user asks why a model behaves a certain way, wants a walkthrough, needs logic mapped to algebra, or has unclear modeling decisions. Readonly …
Agent
Senior AMPL/amplpy reviewer. Classifies models, analyzes formulation complexity, flags formulation smells that make models hard to solve (logic, nonlinearity, density, big-M, weak bounds, coupling), audits amplpy workflows, and reports best-practice violations. Use before production deployment, PR review, when solves…