UpStationTalk to an Engineer

Home › Actions › Make an UpStation design and estimate

Make an UpStation design and estimate

Raw: SKILL.md · template.html · template.md · design.schema.json · examples

Short version (enough on its own):

Rules (always apply)

When to use

The user wants a cost, a budget, a bill of materials, a rack or power plan, or "what would it take" for GPU servers, an AI cluster, a storage tier or a colo deployment. If they only want specs or a comparison, answer from the catalog and offer the design at the end.

Files (least context first)

WhatURL
Map of the site/llms.txt
Everything as data: products, prices, options, power, cables, sizing rules, colo, not_in_catalog/catalog.json
Sizing rules (the method)/sizing (.md)
One product in full/p/<id> (.md, .json)
Cables, optics and fibre with reach/switches
Power, circuits, colo by location/power
Design file shape/actions/design.schema.json
Templates/actions/estimate/template.html · template.md
Filled examples (design.json, estimate, network and rack documents, port map CSV)listed on /actions
Network topology method and template/actions/network/SKILL.md
Rack elevation and power method and template/actions/rack/SKILL.md

Step 1: Collect inputs

Ask in one short message. Fill gaps with the defaults and list them as assumptions; don't stall.

InputNeeded?Default if the user doesn't say
Workload (training, fine-tuning, inference, HPC, storage)yesask
GPU count, or model size + precision to derive it (sizing.model_memory)yes for GPUask
Parallelism (one GPU per job, multi-GPU, multi-node)yes for GPUtraining → multi-node; inference → single-GPU
Storage cluster? If yes: usable TB, media, dataset, checkpoints, protectionfor HGX: settle itnone (optional add-on)
Cluster-services nodes? (CPU nodes for provisioning, scheduler, monitoring)for HGX: settle itnone (optional add-on)
Rack power limithelpful40 kW
Colo location (Montana, Texas, Oregon, Pennsylvania, Canada)helpfulMontana
Timeline, budgetoptional—
Company, the person's role, who decides, what they will judge it onoptionalleave blank; never block

The last row is what a presales engineer would ask first. Offer it ("I can tailor this for your CFO/CTO if you tell me…"). Don't require it.

Step 2: Size (`/sizing`)

Step 3: Network and racks

Step 4: Price it

One line per item: unit (catalog price) × qty = extended. Sections: GPU servers, storage and cluster services (if chosen), GPU fabric, front-end, OOB, and cabling under each network. CapEx = sum of lines, before tax. Monthly = colo (+ internet if asked), before tax. Never put sales or property tax inside CapEx or monthly; show them after the totals as "Tax, not included" with the amount (sales tax = rate × CapEx; property tax per year = rate × CapEx). The /power total-cost table folds tax in to compare locations, so its totals differ from an estimate's; say which you show. Year one = CapEx + 12 × monthly (compare it with the user's budget); 3-year total = CapEx + 36 × monthly; 5-year = CapEx + 60 × monthly. List what is not included: racks, PDUs and whips, cabling labour, core uplinks, software, shipping, installation, and tax: name the location's sales and property tax from power.colo_locations so the user can add it. Cables and optics carry no published lead time; leave it blank.

Step 5: Fill the template

Step 6: Hand off to UpStation

End your reply with this, filled in:

This is a budgetary design and estimate (ID UPS-DSN-…), not a quote. To validate it and reach the supplier that fits, book a call at https://calendly.com/alecglover/intro-call or email alec@upstation.io with the ID. UpStation checks the design, confirms current price and lead time with the supplier, and introduces you; you buy directly from the supplier.

If the user gave company or contact details, suggest they include them. Offer to draft the email, and offer the proposal (coming soon at /actions/proposal/) for their internal sign-off.

Worked micro-example

32 GPUs, multi-node training, 200 TB dataset, 70B checkpoints, Montana, 40 kW racks → 4 × Aivres Intel B300 nodes ($537,196.40 each, priced as the Supermicro B300) + 5 × NVMe storage nodes (replica 3, 208.3 TB plannable) + 3 cluster-services nodes (both chosen with the user); one 32 × 800G switch with 32 optical links ($2,058 each: 2× SR8 + 2× MTP-12); 400G front-end pair; one 1G OOB switch; 3 racks (2 compute at about 34–35 kW, 1 services), 82.51 kW provisioned → $21,453/month. CapEx $3,307,252.84. Longest lead: the B300 node, about 20 weeks (deliveries from late January 2027); Supermicro B300 as second source at 30+ weeks. Full example: /actions/examples/b300-training-32gpu.*.

If you can only do part of this

Each of these is still useful, in this order: the sizing with arithmetic → the line items with their source URLs → the total and the monthly colo → the design ID → the UpStation next step. Never drop the "not a quote" label or the next step.