Field notes

What we think.

Notes on enterprise AI from the delivery side.

Reference pattern

Governed RAG on a medallion architecture

A retrieval system inherits the access rules of the table it reads. This pattern keeps those rules attached to the data through every layer, from ingest to the vector index.

Read
Engineering note

Why AI programs stall after the pilot

The prototype is rarely the constraint. Programs stall on identity, data access, and the absence of a team that owns the system in production.

Read
Position

Don't automate the workflow you have

The process you are about to accelerate was shaped by the limits of the people who ran it. Those limits have changed.

Read
Position

Choosing a model is the last decision, not the first

Most of the quality in a working system comes from the components around the model. That is also the case for staying vendor neutral.

Read
Engineering note

Building multi-agent systems with the OpenAI Agents SDK

Handoffs, guardrails, and tracing are the three primitives that decide whether a multi-agent system can be operated. Here is how we wire them, and what we have learned about where each one belongs.

Read
Economics

What a production AI system actually costs

Token pricing is the smallest line in the bill and the only one most estimates contain. Here is the unit that matters, and a worked example of what it exposes.

Read
Reference pattern

AIoT: inference where the network is not a given

A plant does not stop because a link to a region is down. That single constraint decides most of the architecture for industrial AI.

Read
Engineering note

Evaluations that gate a deploy

An evaluation suite that nobody can fail is a dashboard. This is how we build one that blocks a release, and what it costs to keep it honest.

Read
Position

Prompt injection is an authorization problem

You cannot prompt your way out of prompt injection. The fix is to stop giving the model authority it can be talked into using.

Read
Reference pattern

The control plane an agent estate needs

One agent is a project. Twelve agents is an estate, and an estate needs identity, policy, and observability that do not live inside any of them.

Read
Engineering note

Chunking is a retrieval decision, not a preprocessing step

Most retrieval quality problems we are called in for are chunking problems wearing a model costume. The fix is upstream of anything you can prompt.

Read
Position

Human in the loop is an architecture decision

Review everything and you have built a slower version of the old process. Review nothing and you have built a liability. The gate belongs on the effect.

Read
Delivery note

Getting a pilot through change control

The gap between a working prototype and a deployed system is mostly paperwork you can prepare for. Most teams meet it for the first time at the end.

Read
Economics

The metrics a steering committee will accept

Model accuracy does not survive contact with a business review. These are the measures that do, and the baseline problem that undermines most of them.

Read

Bring us the problem.

Tell us the outcome you are trying to create, what you have already attempted, and where the constraints are.

Contact nuperX