Company

Engineering notes.

Design decisions, incident reviews, and the occasional strong opinion about routing. Written by the people who operate the platform.

Routing is a product decision, not an infrastructure one

Choosing a model per request looks like plumbing. It is actually a decision about what your product is willing to trade — and it belongs to the people who own the outcome.

Placeholder Name

What a trace should contain when the callee is a model

Traditional tracing assumes deterministic callees. Model calls break that assumption in three specific ways, and each one changes what you should record.

Placeholder Name

Notes on prompt prefix caching in a multi-tenant gateway

Caching shared prefixes across requests is easy. Doing it without leaking anything between tenants, and without lying about token counts, is the interesting part.

Placeholder Name

Why we ship 12-month deprecation windows

A deprecation window is a promise about someone else's roadmap. Twelve months is the shortest span that survives a real planning cycle.

Placeholder Name

Incident review: delayed trace ingestion, 8 June

A bad deploy of the span writer put nine minutes of lag into trace ingestion. Inference was unaffected. Here is what happened and what we changed.

Placeholder Name

A practical way to find out if a cheaper model is good enough

Vendor benchmarks will not answer this. A shadow-traffic experiment against your own evaluation set will, in about two weeks.

Placeholder Name

How much does that feature cost? A method

Per-request cost is easy. Per-feature and per-customer cost require a tagging discipline you have to adopt before you need the answer.

Placeholder Name

Every card links to the sample article. Wire them to your own posts.

Get the notes by email.

One message when something substantial ships. No newsletter cadence.