// ARCHITECTURE

The cognitive architecture, open to inspection.

IRIS is not a black box. Every decision passes through a layered architecture with explicit purpose: reasoning, memory, verification, synthesis, language and action. Every layer observes, records and can be audited.

This is what makes it possible to build enterprise systems on AI without losing traceability or control.

// LAYERS

Six layers with explicit purpose.

L1
Razonamiento
Cognitivo
L2
Memoria
Persistente
L3
Verificacion
Factual + Adversarial
L4
Sintesis
Consolidacion
L5
Lenguaje
Salida auditable
L6
Accion
Data Shield
INPUT
OUTPUT + AUDIT
// COGNITIVE MODES

The six cognitive modes

01

Cognitive

Structured reasoning over the problem. Identifies entities, relations, constraints and goals.

02

Reactive

Immediate response when context is clear and verified. No over-deliberation.

03

Proactive

Detection of relevant events before the user requests them. Continuous watch.

04

Deliberative

Activation when the problem has ambiguity or risk. Multiple agents confront hypotheses.

05

Adaptive

Strategy adjustment based on feedback and memory. Does not repeat known errors.

06

Iterative

Progressive improvement over previous conclusions when new information appears.

// SWARM

Specialized agents working in parallel.

The swarm is not a metaphor: it is architecture. Reasoner, critic, verifier, director and memory operate in parallel, confront hypotheses and reach consensus before emitting any output.

DirectorRazonadorCriticoVerificadorMemoria
// INFRASTRUCTURE

External LLMs as tools, not as brain.

IRIS orchestrates models like Claude, GPT or Gemini as technical infrastructure. Deliberation, memory and decisions belong to the engine. External models are swappable; the cognitive architecture is not.

Architecture questions

Cognitive, reactive, proactive, deliberative, adaptive and iterative. Each mode activates based on the nature of the problem.