Engineering notes

What we learn running our own inference servers: the physics of long context, the economics of the token, and what both mean for your AI agents.

Architecture Day to day, the difference comes from the harness more than the model The harness is everything you build around the model to put it to work. You write it once, and it is not re-billed per use. August 28, 2026 Pricing The flexibility premium: what the right to consume at any time costs With usage billing, part of the price does not pay for compute. It pays for the capacity the provider keeps free to absorb spikes. August 28, 2026 Token economics Re-reading: the line item nobody looks at In agentic workloads your bill isn't driven by what the model writes. It's driven by what it re-reads. August 12, 2026 Infrastructure What a 1M context actually costs a machine The limit on long context is almost never the model's capability. It's the memory and bandwidth of the server running it. August 4, 2026 Capacity planning Throughput or tokens: two ways to buy inference Paying per token buys a quantity. Paying for throughput buys a capacity. They don't suit the same workloads. July 28, 2026 Integration Pointing Claude Code at a self-hosted endpoint Three environment variables redirect the client. A fourth, less known, prevents errors that are hard to diagnose. July 21, 2026 Landscape The gap is closing, and closing fast Three to five months now separate the best model you can rent from the best you can run yourself. Two years ago it was six to nine. July 14, 2026 Sovereignty What “hosted in Canada” actually means Data residency is a property of the infrastructure, not a checkbox in a contract. July 7, 2026 Measurement Measuring your real throughput from your provider's console Before sizing anything, you need to know what you actually consume. The consoles will tell you — provided you know what they leave out. August 18, 2026 Instrumentation Computing org-wide tok/s without trusting the invoice A conventional network sniffer will see nothing: the traffic is encrypted. Measurement happens at the chokepoint, not on the wire. August 14, 2026

White paper

Your company has two supply chains

The first one you already know. Materials come in, they are transported, stored, transformed, delivered. Every step has a supplier, a lead time, a unit cost. When the margin tightens, you walk down that chain step by step, and you generally know where to look.

The second one moves information instead of materials. A price request comes in and becomes a quote. An order comes in and becomes a production order, an invoice, a confirmed delivery. A site report becomes a change order, or it does not. This chain runs through every one of your departments and it employs a large share of your people.

Get the white paper

A question about your consumption?

We measure your actual consumption over one day, free and with no commitment, and tell you whether a fixed-throughput plan works out in your favour — or not.

Book 30 minutes