×
About me ACP Services Stack Contact

TraslaIA

by Marcelo Fernandez

Agent Governance · ACP Author · arXiv 2603.18829 · AWS AI Practitioner

Designing the governance layer between
agent intent and institutional accountability

Author of the Agent Control Protocol (ACP)the admission control infrastructure for autonomous agents operating in institutional environments. TraslaIA is where that architecture meets production.

Who I am

About me

Autonomous agent systems architect · ACP Author · Founder of TraslaIA

Marcelo Fernandez

I'm Marcelo Fernandez, an AI and intelligent automation consultant with 15+ years of experience in strategic leadership and digital transformation. Founder of TraslaIA, where I design and implement the infrastructure connecting AI systems to real-world operations.

I'm the author of the Agent Control Protocol (ACP), the open governance standard for autonomous agents published on Zenodo and arXiv. ACP defines who authorized an agent, what it executed, and who is accountable for the outcome — cryptographically verifiable, across systems and institutions.

My work spans from multi-agent system architecture to operational workflow implementation with n8n, generative AI, OCR, and vector databases. I've worked with over a dozen organizations achieving up to 80% reduction in manual process time.

15+
Years in strategic leadership
10+
Organizations in digital transformation
80%
Reduction in process time
99.7%
Data extraction accuracy
📍 Córdoba, Argentina · Available globally
Native Spanish · English (professional)
v1.15 · Zenodo DOI 10.5281/zenodo.19150239 · arXiv 2603.18829

Agent Control Protocol

Governance infrastructure for autonomous agents.

ACP defines who authorized an agent, what it executed, and who is accountable for each outcome — cryptographically verifiable, across systems and institutions. It operates as an admission control layer on top of existing RBAC and Zero Trust, without replacing them.

🔐

Authorization

Cryptographic proof chain of who authorized each agent action. Ed25519 signatures bind every operation to an authenticated human or institution.

🗂️

Capabilities

Scoped capability-based access: an agent only holds the permissions explicitly granted. No implicit inheritance, no privilege escalation.

📜

Policy

Deterministic, auditable mapping from action to the exact policy rule that permitted it. No ambiguity — every execution leaves a verifiable policy trace.

Verification

Independent third-party auditability of every operation. Immutable audit logs enable compliance, post-incident analysis, and institutional accountability.

v1.15
Specification
36
Technical Documents
L1–L5
Conformance Levels
73
Signed Test Vectors
17
OpenAPI 3.1 Endpoints
Ed25519
+ JCS Canonicalization
What I build

Architecture & Implementation

From governance design to operational deployment — built on the principles behind ACP

Governance Architecture
🏗️

Autonomous Agent Governance

Design of permission models, delegation chains, and audit trails for autonomous agent systems. Based on ACP. Whether you're deploying your first agent or governing a fleet — we design the institutional control layer.

  • Scope: Authorization models, capability scoping, policy design
  • Output: Verifiable delegation chains + immutable audit infrastructure
  • Standard: Based on ACP specification (Zenodo 10.5281/zenodo.19150239)
ACPGovernanceDelegationAudit Trails
ACP Implementation
⚙️

ACP in Production

Deploy the Agent Control Protocol in your infrastructure. From L1 identity anchoring to full L4 multi-institutional delegation. Includes Go reference implementation and conformance test suite validation.

  • Levels: L1 → L4 conformance implementation
  • Stack: Go packages + OpenAPI 3.1 endpoints
  • Delivery: 73-vector conformance test suite
GoOpenAPIConformanceMulti-Agent

Multi-Agent Orchestration

Design and implementation of intelligent multi-agent workflows with n8n. Memory management, tool routing, and contextual execution for complex agent pipelines.

Workflow Automation

Design and deployment of scalable n8n workflows that convert manual operations into structured, observable, and maintainable automation layers.

API Integration

Connect disparate systems via REST APIs, webhooks, and cloud services to build efficient and observable digital ecosystems.

OCR & Document Processing

Intelligent data extraction from invoices and documents with adaptive OCR, structural validation, and traceable output pipelines.

Technical evidence

Automations in Production

Real workflows built with n8n solving complex problems

Multi-Agent Conversational Agent

Multi-Specialized Conversational Agent

Multi-agent architecture with audio and image processing, contextual memory, and specialized action execution coordinated by a central orchestrator.

RAG System

RAG System for E-commerce

RAG pipeline with Pinecone vector search, OpenAI embeddings, conversational memory, and product catalog query from Google Sheets.

MCP Server

MCP Multi-Entity Server

MCP server orchestrating 14 business entities over Supabase: users, products, stock, orders, invoices, and payments. Tool architecture for LLM agents.

Automated Reports

Automated Daily Reports

Multi-source RSS ingestion, semantic classification with AI, Airtable persistence, and automatic newsletter generation.

Architecture

Infrastructure & Systems Designed

Systems built to run in production.

Main Project

Agent Control Protocol — Open Governance Standard

  • Type: Open governance protocol for autonomous agents
  • Publication: Zenodo 10.5281/zenodo.19150239 · arXiv 2603.18829
  • Version: v1.15 — 36 technical documents
  • Vectors: 73 signed with Ed25519 + JCS (22 positive / 51 negative)
  • Invariant: ValidIdentity ∧ ValidCapability ∧ ValidDelegationChain ∧ AcceptableRisk

Foundation for any system delegating actions to agents with real accountability.

ACPGovernanceOpen StandardGoEd25519Zenodo

Multi-Agent Architecture (MCP / A2A)

  • Control: Agent Control Protocol
  • Interop: Model Context Protocol
  • Base: Model / memory / tool separation
  • Orchestration: n8n + structured persistence

Foundation for intelligent SaaS with verifiable task delegation.

Multi-AgentMCPA2An8n

Adaptive OCR Pipeline

  • Routing: Dynamic fallback between OCR providers
  • Validation: Structural control before persistence
  • Execution: Automatic conditional retries

Scalable document processing with effective reduction of human errors.

OCRn8nModular

OnePyme — SaaS Platform

  • Type: Modular SaaS for mid-size companies
  • Orchestration: Centralized flows with n8n
  • Governance: States, validations, and traceability

Structured digitization of internal operations for SMBs.

SaaSSMBIntegration
Credentials

Stack & Certifications

Active tools, technologies, and accreditations

Tech Stack
n8n
No-code workflow automation
🤖
OpenAI · Claude · Gemini
Generative AI, agents and RAG
☁️
Google Cloud · AWS
Scalable cloud infrastructure
📊
Supabase · Airtable · PostgreSQL · Pinecone · Redis · S3
Data, vectors, and storage
🔍
Advanced OCR · Computer Vision
Intelligent document extraction
💻
JavaScript · Python · Go
Development, scripting, and protocol implementations
⛓️
Ethereum · Smart Contracts · Web3
Tokenization, DeFi, and blockchain architecture
Languages
🇦🇷Spanish· Native
🇺🇸English· Professional
Active Certifications
AWS Certified AI Practitioner
Amazon Web Services
↗ View certificate
Valid until 2029
Google AI Essentials
Gen AI Foundational Concepts · Google
↗ View certificate
Diploma in Blockchain & Digital Finance
Universidad Tecnológica Nacional (UTN)
↗ View certificate
Diploma in Artificial Intelligence
Universidad Tecnológica Nacional (UTN)
In progress
Diploma in Digital Transformation
Universidad Tecnológica Nacional (UTN)
In progress
n8n No-Code Automation Technician
Udemy
↗ View certificate
Let's work together

Design Your Governance Layer

Are you deploying autonomous agents, need governance infrastructure, or want to implement ACP in your organization? Let's talk.