TranscendenceTechnologies
Start a Project
Insights

Notes on building AI that ships.

Practical writing on evaluation, MLOps, and the strategy behind AI that actually makes it to production.

FeaturedEngineering

Shipping LLM features that survive contact with production

Demos are easy; production is where LLM features fall over. A field guide to evaluation, guardrails, latency, and cost — the unglamorous work that decides whether a feature ships or stalls.

Jul 20269 min read
Read article
Live from Medium & Substack

Latest from our blog

Fresh posts pulled straight from our publication — updated automatically.

Follow along
Strategy

The 5% problem: why most AI never ships

Most AI projects die between the prototype and production. Here is where they get stuck — and how to plan around it.

Jul 20266 min read
Engineering

Evaluation is the moat

If you cannot measure a model, you cannot improve it. A practical approach to building evaluation into the workflow.

Jun 20267 min read
Engineering

RAG in production: what actually matters

Retrieval is the easy part. Chunking, ranking, and grounding are where quality is won or lost.

Jun 20268 min read
Engineering

A pragmatic MLOps starter stack

You do not need a platform team to be reproducible. A lean stack that scales from first model to fleet.

May 20265 min read
Strategy

How to scope an AI project

Scope for learning, not certainty. How we structure first engagements to de-risk the unknowns fast.

May 20266 min read
Industry

On-device vs cloud inference

Latency, privacy, and cost pull in different directions. A framework for deciding where inference should live.

Apr 20267 min read

Get the occasional deep dive

No noise. Just the engineering and strategy notes we'd want to read ourselves.