We write a lot about what optimized utility design produces — the smallest distribution that serves every tool within capacity. This post shows the two runs that produce it. Both walkthroughs below are real product runs on an illustrative demo fab, each around half a minute.
Auto-design: from candidate panels to the smallest set
The auto-design run answers the siting question: how many panels does this fab actually need, and where do they go? A human designer has to commit to a panel count early and make it work. The run does the opposite — it starts generous and earns its way down:
- Lay out candidates. Candidate panels for both substation trains spread across the grid — more than the fab will keep.
- Connect. Every tool connects to its closest feasible panel, so run lengths start short and stay honest.
- Consolidate and prune. The run consolidates load onto the fewest panels that keep runs short, then removes every panel left unused — in the demo, ten candidates become six panels.
- Balance. Paired tool models re-route so every model lands on both trains — redundancy is enforced by the run, not checked afterwards.
The end state is the one we keep coming back to on this blog: the smallest panel set that serves every tool, with the shortest runs the layout allows. Fewer panels means less switchgear, less cable, and less cleanroom floor given over to distribution — which is exactly the mechanism behind the 500-not-700 result on a leading-edge logic fab.
Auto-assign: every open demand, matched in seconds
Placing the distribution is half the job. The auto-assign run answers the hook-up question: which utility connection serves each demand? In the walkthrough below, a fab's mechanical assignments view holds 719 utility connections with a handful still unassigned — the kind of remainder that normally means an engineer cross-referencing layouts and load tables by hand:
- Select the open demands. The unassigned demand POCs — each with its component, load, and building level — are picked straight from the assignments table.
- Propose. Auto-assign matches every one to its nearest feasible utility connection, with the distance computed and the feasibility check shown next to each proposal.
- Review and accept. The proposals land as a reviewable list, not a silent mutation — accept, and the assignments write back to the living model.
An assignment isn't a judgment call buried in a spreadsheet — it's a proposal you can see, with the distance and the check that justified it.
The part we'd point owners at is the last caption in the clip: hours of manual matching, done in seconds. Not because the seconds themselves matter much — but because when matching is that cheap, it gets re-run every time the layout moves, and the assignments stay a computed, current fact of the model instead of a spreadsheet someone maintains.
Where these runs fit
Both runs are stages of the loop we describe in How it works: capture the demands, optimize, apply the result to the living model, re-run on every change. The first demo is electrical and the second mechanical on purpose — the same engine drives both sides of the distribution, so every system and piece of equipment comes out of one set of assumptions. And because millions of configurations are evaluated on every optimization run, "re-run it after the layout change" is a click-scale decision, not a re-engineering project.
Your engineers run these themselves: load the tool layout and the utility demands, and the sized mechanical and electrical distribution comes back with the living model behind it.