This page brings together selected system directions developed within the PROTEX project.

The work focuses on how AI systems can operate on structured knowledge, under explicit constraints, within real organisational environments.

Rather than treating AI as a general conversational layer, these systems are designed around bounded roles, controlled access to knowledge, and clearly defined responsibility structures.

Ongoing research. Applied in real environments.

Across all system directions, the main concern is how knowledge is structured for AI systems, how access to that knowledge is controlled, and how system behaviour changes when AI is embedded into real workflows, procedures, and decision environments.

A second important layer is psychological. The project examines how AI systems should be designed when human interpretation, cognitive load, trust, narrative framing, and decision responsibility remain central.

This includes role-specific systems, procedural guidance layers, expert knowledge interfaces, and structured retrieval architectures.

Procedural AI systems are explored as bounded support systems for environments in which people rely on documented procedures and repeatable operational logic.

These systems are not designed to decide on behalf of users. They retrieve and organise approved procedural knowledge, supporting action within defined organisational boundaries.

Expert AI systems are studied as role-specific knowledge interfaces built around verified products, services, and domain rules.

The purpose of these systems is structured explanation of complex knowledge within explicit response boundaries.

A central part of the project focuses on knowledge backends, retrieval layers, and ingestion pipelines for AI systems.

Many system failures originate not from models, but from poorly structured or uncontrolled knowledge.

This work focuses on structured modelling, metadata preservation, controlled retrieval, and deterministic knowledge access layers.

The blueprint is treated as a design framework for thinking about AI systems before they influence real decisions.

It examines how systems interact with knowledge, procedures, and responsibility structures, and where their role should begin and end.

Governance is approached as a question of responsibility, decision authority, and risk boundaries.

It includes responsibility mapping, knowledge ownership, human oversight, and system-level enforcement.

• criminology and behavioural case analysis
• hospitality and operational environments
• expert advisory systems

These domains are used to observe how system behaviour changes under different knowledge structures and decision constraints.

Email
karol@protex-profiler.ai