2026-05-01 · ai-engineering · Zhianrui Research

Why agentic systems need provenance more than humans do

A human researcher with weak provenance discipline produces poor research. An agentic LLM system with weak provenance discipline produces confident hallucinations at scale.

2026-04-24 · ai-engineering · Zhianrui Research

Building eval harnesses that survive contact with production

A benchmark score is what a model achieved on a frozen dataset. An eval harness is what you trust to decide whether a new model can ship. The two are not the same thing.

2026-04-17 · ai-engineering · Zhianrui Research

RAG isn’t search — and treating it like search is why most implementations fail

Retrieval-augmented generation looks like search-with-an-extra-step. It is not. It is generation-with-a-retrieval-substrate. The architectural implications are different at every layer.

2026-04-15 · methodology · Zhianrui Research

Why provenance is a delivery practice, not a deliverable

Provenance is not a section at the end of a report. It is a practice that shapes how research is conducted from day one.

2026-04-10 · ai-engineering · Zhianrui Research

The LLM-augmented research workflow we use internally

Most consultancies hide their internal AI use behind a curtain of human authorship. We think the curtain is doing more harm than good — to clients, to the discourse, and to our own work.

2026-04-08 · regulatory · Zhianrui Research

Reading NIS2 as an engineering specification

Most compliance guides treat NIS2 as a checklist. We read it as an engineering spec — and the design implications are different.

2026-03-28 · operating-model · Zhianrui Research

The cost of arms-length offshoring in applied research, and the alternative

The failure mode of offshoring is not cost — it is the translation layer between the bench and the client.