Deterministic orchestration
Structured workflow states, predefined decision boundaries, and clearly scoped execution paths.
Early-stage, self-funded technology project · Argentina
AI workflows.
Accountability by design.
NAOF — the Nahuel AI Orchestration Framework — is being developed to make AI-assisted workflows more traceable, controlled and auditable. Our first product direction is accountable AI-assisted software engineering, with a long-term vision for enterprise and educational applications.
Independent founder · Santiago del Estero, Argentina · Pre-commercial development
Deterministic controlsTraceable evidenceHuman oversightIndependent review
Our approach
AI workflows need more than automation.
NAOF is being developed around explicit constraints and verifiable evidence, rather than treating model outputs as automatically trustworthy.
Traceability first
Records and checkpoints designed to make workflow decisions and outcomes inspectable.
Human authority
Separating automated processing, independent review, and decisions that require explicit human approval.
Product direction
Built for accountable AI-assisted work.
Our initial focus is software engineering. Other applications represent longer-term opportunities to explore—not products available today.
Software engineering workflows
A proposed foundation for controlled AI-assisted development, code review, testing and technical documentation—with explicit checks, evidence and human approval boundaries.
Enterprise process automation
Potential orchestration of bounded business workflows, keeping actions observable and authorization separate from execution.
Research and document analysis
Possible workflows for structured investigation, document comparison, information extraction and traceable research outputs.
Data validation and decision support
Exploring ways to verify outputs, record supporting evidence and keep consequential decisions under human responsibility.
These are development directions. NAOF does not currently offer commercial deployments or production-ready autonomous AI workflows.
AI provider research
Exploring a controlled Claude API prototype.
We plan to evaluate Claude as one potential model provider for bounded AI-assisted software engineering workflows. A proposed proof of concept would receive a structured task, invoke an AI model under defined limits, capture outputs, apply validation checks and prepare evidence for human review.
This integration is planned research, not a feature currently implemented or deployed. NAOF is designed to remain extensible across model providers.
Education & regional impact
A longer-term vision for Santiago del Estero.
Beyond enterprise applications, NAOF's founder hopes to explore responsible AI tools that could help teachers and students in Santiago del Estero, Argentina.
Possible uses include adaptive explanations, practice exercises, science and mathematics learning support, and tools that assist educators in identifying recurring difficulties. AI should support teachers, not replace them.
Any future educational pilot would require institutional involvement, appropriate safeguards for minors, student privacy, accessibility and curricular alignment. There are no school deployments or institutional partnerships at this stage.
Development status
Research-led. Tested. Still evolving.
NAOF is an early-stage engineering project, not a production-ready commercial service. The initial deterministic, local read-only kernel and router have been implemented. Further shadow-workflow capabilities are under incremental development and evaluation.
- Documented and version-controlled architecture
- Read-only kernel, deterministic router and local CLI
- Automated tests and separate technical review
- Shadow-workflow development with bounded increments and explicit acceptance
Long-term vision
Trustworthy AI workflows for business—and a path toward educational impact.
Our aim is to turn a rigorously developed engineering framework into useful technology for teams and organizations. We intend to validate software engineering workflows first, then explore broader enterprise applications where traceability, accountability and human control matter.
Alongside a sustainable technology business, our founder hopes to contribute to educational innovation in Santiago del Estero. These remain long-term goals, not current commercial offerings or educational deployments.
Connect
Get in touch with NAOF
NAOF is an independent, pre-commercial AI orchestration project. We welcome conversations with researchers, engineering teams, educators and prospective collaborators. Contact us at contacto@naof.com.ar.