01 · The core framework
Everything Prodigy builds runs on one architecture.
AiRox is our proprietary AI framework: the foundation beneath every system we build and operate. Each project it carries extends it, so the capability proven on one mission becomes the starting point for the next.
The definition
AiRox is the technology foundation behind complete AI systems.
It brings together models, agents, governed knowledge, operational data, interfaces, workflows and human oversight within a single architecture.
AiRox is not positioned as a standalone product. Clients engage Prodigy for a specific capability or operational system; AiRox is the proprietary foundation that allows us to design, adapt and deploy those systems faster, while continuously reusing and extending capabilities developed across previous projects.
Our attribution follows a simple principle: repeatable commercial solutions are presented as a Prodigy product, powered by AiRox. Client-specific operational systems are built by Prodigy on AiRox.
Every system described on this site is built on it, which is why capability developed for one mission is available to the next.
02 · Framework capabilities
Ten capability groups, one architecture.
Each group is a reusable layer rather than a fixed module. A system takes the layers its mission requires and leaves the rest, with each one configured for that project’s data, security model and operating conditions.
00
AiRox LLM + proprietary models
At the core of AiRox is our proprietary language model, designed for controlled, adaptable and private AI deployments. It can be specialised through fine-tuning and domain knowledge, deployed on-premise when required, and orchestrated alongside other leading models within the broader AiRox ecosystem.
01
Third-party models
Different tasks require different intelligence. AiRox can work across language, reasoning, vision, voice and specialised models, selecting the right capabilities for each system and use case.
02
Agents + orchestration
Models become coordinated systems. AiRox manages agents, roles, routing, evaluation, tool use and interactions between specialised components rather than relying on a single model for every task.
03
Knowledge + RAG
Organisational knowledge becomes accessible to AI through approved sources, documents, retrieval, semantic search and structured knowledge bases.
04
Context + memory
Intelligent systems need continuity. AiRox maintains contextual and persistent information across interactions, users and workflows, so systems can operate with more than the information contained in a single prompt.
05
Voice + vision
AiRox extends beyond text with speech, image and video capabilities - including speech-to-text, text-to-speech, computer vision and multimodal intelligence.
06
Data + tools
AiRox connects intelligence to the systems around it. APIs, operational data sources, databases and external tools become available to models and agents as part of the same architecture.
07
Workflows + automation
AI output can become operational action. AiRox supports workflows, approvals, automations and integrations that connect intelligence directly to organisational processes.
08
Governance + human control
Access, traceability, evaluation, cost visibility and human validation are built into the system. AI can generate context, recommendations and actions while defined controls remain with the organisation and its users.
09
Deployment + AI infrastructure
AiRox can operate across public, private, hybrid and on-premise environments. Its architecture can be designed around the models, compute, GPU infrastructure, networking, storage, latency and data-control requirements of each deployment.
Deployment
The deployment model is chosen from the sensitivity of the data and the operating constraints of the organisation, not from preference. Where data cannot leave a boundary, the system is deployed inside that boundary and operates there.
One framework. Many missions.
03 · Technology accumulation
The technology grows with every generation of projects.
Research → prototypes → real projects → new capabilities → reinvestment in AiRox.
2018
A research nucleus in cybernetics, data and software engineering.
2025
AiRox reaches a level of maturity close to the original vision.
2026
The shift from building the technology to scaling it.
Each project validates the framework in a real operating environment and extends it with whatever that mission required. The result is that development time falls with each generation, because the next system starts from a larger base of proven capability.
Every substantial project leaves reusable capability behind in the framework, and the following project begins from that larger base. What is never carried across is client data, security configuration or mission context - those remain isolated to the system they belong to.
04 · Proven in the field
From observation to operational intelligence.
AiRox was extended for sensors, video analysis, maps, trajectories, asset coordination and assisted decisions.
The same framework underpins work across public administration, critical missions, enterprise operations and knowledge systems, delivered in Romania, India, Saudi Arabia and the United States.
See the portfolioContact
Start with the problem, not the technology.
Send us the challenge, the constraints you are working within and the outcome that has to improve. We will come back with what a working system would involve, how it would be built and operated, and whether AI is the right tool for the problem at all.
Start the conversation