You will get my AI editorial system tailored for repeatable editorial tasks
Project details
EdOr, The Editorial Orchestrator, is a Composable AI-based Editorial Workbench with over 30 combinable and loopable operations.
I started developing EdOr a few years ago to optimize my repetitive and complex editorial tasks. Since then, EdOr has evolved into an incredibly powerful and versatile editorial workbench with more than 30 composable actions - Roles, Modes and Steps (specialists), that can be combined in endless ways.
Together we can build some rad workflows for you: write system prompts of any kind; turn an idea, keywords or a rough draft into finished content; oppose your own statements to reveal weak assumptions and counterarguments; inspect, audit, translate, code, expand, distill, consolidate or orthogonalize material; or anisotropically expand a concept to reveal hidden structures, new dimensions and perspectives.
For this project, I write an original EdOr stack composed of a Role (i.e. Writer), a Mode (i.e. Creative) and 3 Steps (i.e. Write, Critique, Consolidate) around a real task from your work.
You receive the configured system, templates, setup files, a usage guide and the source code. EdOr is open source and freely available.
I started developing EdOr a few years ago to optimize my repetitive and complex editorial tasks. Since then, EdOr has evolved into an incredibly powerful and versatile editorial workbench with more than 30 composable actions - Roles, Modes and Steps (specialists), that can be combined in endless ways.
Together we can build some rad workflows for you: write system prompts of any kind; turn an idea, keywords or a rough draft into finished content; oppose your own statements to reveal weak assumptions and counterarguments; inspect, audit, translate, code, expand, distill, consolidate or orthogonalize material; or anisotropically expand a concept to reveal hidden structures, new dimensions and perspectives.
For this project, I write an original EdOr stack composed of a Role (i.e. Writer), a Mode (i.e. Creative) and 3 Steps (i.e. Write, Critique, Consolidate) around a real task from your work.
You receive the configured system, templates, setup files, a usage guide and the source code. EdOr is open source and freely available.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
AI Content Creation, Natural Language Generation, Natural Language UnderstandingAI Tools
Azure OpenAI, Hugging FaceAI Models
ChatGPT, GPT-3, GPT-4, LLaMAWhat's included
| Service Tiers |
Starter
$600
|
Standard
$1,200
|
Advanced
$3,900
|
|---|---|---|---|
| Delivery Time | 5 days | 7 days | 14 days |
Number of Revisions | 2 | 3 | 4 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | - | - |
Detailed Code Comments | - | - | - |
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | |
Model Monitoring | - | - | - |
Model Testing & Optimization | |||
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | |||
Source Code |
Frequently asked questions
About Pablo
AI Governance & Workflow Architect | LLM/RAG | Team Enablement
Kings County, United States - 7:14 pm local time
My work is for organizations that are already using AI, experimenting with AI, or preparing to scale AI workflows, but need more structure before those systems become fragile, opaque, or politically difficult to manage.
I work across AI governance, workflow architecture, LLM/RAG systems, model-output evaluation, and team enablement. In practice, that means I enter a system, observe how it actually works, map the visible and hidden layers, surface bottlenecks, assumptions, drift, weak handoffs, unclear review points, and decision constraints, then help turn the system into something people can understand, operate, and improve.
My background combines 25+ years across infrastructure, automation, executive communication, decision systems, service design, and human systems. Since 2023, my focus has been AI systems: LLM workflows, RAG and knowledge systems, prompt architecture, model behavior, evaluation methods, governance rules, and implementation patterns that teams can actually use.
My original work includes:
System Initialization Specification — a governance protocol for bounded, inspectable AI behavior.
Continuation Gate — a method for deciding when an AI system should stop, ask, escalate, or continue.
Editorial Orchestrator / Structured Input — a workflow architecture for turning complex inputs into repeatable, reviewable AI-assisted outputs.
Pressure Compression Audit Method — a stress-testing method for exposing hidden semantic loss, fake compliance, drift, and reasoning degradation.
Expand / Distill — a transformation-fidelity method for preserving meaning during elaboration, summarization, and compression.
AI Iteration Density Theory — a model for understanding how AI compresses feedback loops and changes organizational adaptation speed.
Typical engagements include:
AI workflow audits
AI governance and review frameworks
LLM output evaluation
RAG / knowledge-system review
Prompt and instruction architecture
Human-in-the-loop workflow design
AI readiness and decision support
Failure-mode and drift analysis
Workflow documentation and team training
Custom implementation of governance or workflow frameworks
I am especially useful when the problem is not simply “build an AI automation,” but making the full AI situation legible: what enters the system, what the model does with it, what the output means, where it can fail, who reviews it, what should be automated, what should remain human-controlled, and what the team needs in order to trust and maintain the workflow.
I also enjoy working directly with teams. A large part of my value is not only creating frameworks, but helping people inhabit them: teaching the operating logic, making the system understandable, reducing friction, and giving teams language for what they are already experiencing but have not yet made explicit.
Before AI, much of my work was in executive communication and decision systems. I worked with Oracle, Marriott, Veolia, Mastercard, and 150+ other organizations translating complex technical, strategic, and operational material into decision-ready structures. That experience carries directly into AI work: the problem is often not only the model, but the structure around the model, the people using it, and the decisions it is expected to support.
I work best with founders, CTOs, executive sponsors, AI leads, product teams, and operations teams who need someone to make the system visible, name the constraints, design the workflow, and help the team move from ad hoc AI use to structured AI practice.
Steps for completing your project
After purchasing the project, send requirements so Pablo can start the project.
Delivery time starts when Pablo receives requirements from you.
Pablo works on your project following the steps below.
Revisions may occur after the delivery date.
I review your task, materials and goals
I study the process you want to improve, what you will give EdOr to work on, who the result is for, and what you want the result to achieve.
We define the scope
We meet on Zoom to identify the best "stack" with Role, Mode, Steps, loops, user pauses and output format.