What does an open net leave to the planner?
Use an independent open-net implementation as a structural reference. See why the same assembled process can still fire Frame twice unless selected work is declared separately.
Higher-autonomy experiments
Higher-autonomy experiments
Toy scenario
Start in Boundary Contract Lab: a cliffside refuge needs frame and roof lifts. Give them one shared lift, then two independent lifts. See which work can start together—and why two possible orders need not mean parallel work.
The wider aim is reusable process descriptions that generate lawful project options. These agent-led trials use Petri nets and monoidal structure; each makes its construction, checks and limits inspectable.
Use an independent open-net implementation as a structural reference. See why the same assembled process can still fire Frame twice unless selected work is declared separately.
Keep valid work, revise what feedback invalidates, and distinguish a possible success from a policy that handles every modeled outcome.
Start with one mechanism and meaningful project states. Generate different work branches, inspect joint resource starts and replay each plan's typed supplies and schedule.
Explore a selected trace's ancestry family, test its alternative sequential orders, and compose typed process fragments.
Generate execution witnesses, inspect exact dependencies, and discover when a simple sequence/parallel plan loses a legal order.