Insight · Plateer AI Labs

Article series

The GS Certification Diary

Three weeks of reading 80 defect reports and rebuilding the code, the errors, and the manual

5 articles

The Harness Diary

Designing the execution environment an AI agent works in, from the ground up

10 articles

The Ontology Diary

Starting from the questions, building a knowledge graph, then working on quality and search

10 articles

All articles

Tech NoteThe Harness Diary2026.04.29

Why we separated the engine core from the product integration layer (Part 2)

How the generic execution order and XGEN's data, permission, and canvas translation were divided across ServiceProvider, a registry, and a product bridge.

김진수

Tech NoteThe Ontology Diary2026.04.24

Why we took the questions out of the ontology build (Part 1)

Questions stay in evaluation, and the source documents decide what knowledge gets discovered. Redividing responsibility in the build pipeline.

김진수

Tech NoteThe Harness Diary2026.04.20

Why we split the validation loop into execution states (Part 1)

Designing generation, validation, tool execution, and retry as explicit states and transitions instead of hiding them inside one loop.

김진수

Field Report2026.04.17

How could AI agents change the way a company operates?

Questions from consulting and commerce operations — which work to hand to AI, how internal and customer-facing AI differ, how to turn legacy data into a knowledge structure, and how to govern a growing fleet of agents.

PPlateer AI Labs

Field Report2026.03.16

What should churn-prediction AI actually look at in B2B food distribution?

Why consumer e-commerce analytics do not transfer directly, how a design carries through from prediction to sales action, and which questions a short PoC should settle first.