Insight · Plateer AI Labs

Article series

The core ideas you need to make sense of an LLM, taken one at a time.

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

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

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

Login, API wiring, tool registration, testing — not a line of code. PathFinder turns dormant legacy APIs into tools an agent can use.

An A/B said multi-turn search was slower and less accurate. The evaluation was querying an empty graph and answering from vector search alone.

Building an automatic config search, we added promotion thresholds and a validation set. The component proposing candidates was reading that record.

The era of fitting data into a screen is over. Meet FloUI, a responsive UI that builds the screen in real time the moment a user asks.

Auto-deleting classes short on instances and relations removed about 1,500 healthy ones. Post-processing judged what extraction had not yet built.