Emissions Workflow MVP
CO2Calc
LiveA trilingual workflow automation for tour CO2 tracking — built in two days, funding-ready, and preserved as a frozen teaching snapshot.
Core Framework
A framework for responsible, human-centered AI building.
AI increases speed. Judgment must increase first. Judgment Before Automation is not anti-AI. It is an architectural stance against irresponsible automation.
Core Thesis
Automation without architecture creates fragility.
AI systems can generate code, text, and structure at unprecedented speed. What they cannot generate is responsibility. JBA argues that speed must be structured and humans remain accountable.
Judgment Before Automation argues:
- Speed must be structured
- Automation must be bounded
- Architecture must precede execution
- Humans remain accountable
This is not anti-AI. It is anti-irresponsibility.
The Dialectic
A third position between automation maximalism and automation rejection.
AI discourse often polarizes into “let it generate everything” or “reject it entirely.” JBA proposes structured, human-led use with clear boundaries and approval.
Extreme 1: Automation maximalism
- Let it generate everything
- Trust outputs by default
- Retrofit structure later
Extreme 2: Automation rejection
- AI destroys craft
- Avoid assisted workflows completely
- Lose leverage and speed
JBA proposes a third position: use AI fully, but under human-defined structure and approval.
The Model: Human-in-the-Middle
HITM is the operational implementation of the framework.
Human-in-the-Middle is not reactive oversight. It is structural authority. The human defines boundaries before output exists, then approves what ships.
Core principle
- Research is human
- Structure is human
- AI executes stepwise
- Nothing ships without review
HITM vs Human-in-the-Loop
- Human-in-the-loop reacts to output
- Human-in-the-middle defines boundaries first
- HITM preserves structural authority
Applications
Where JBA applies
- MVP development
- Product architecture
- Repository discipline
- Asset pipelines
- AI-assisted design workflows
- Funding-ready packaging
Not a Prompt Technique
A systems approach
Judgment Before Automation is a way of organizing human authority, technical boundaries, and execution discipline. Prompts are tools inside that structure, not the structure itself.
Proof
This framework is applied in real-world builds.
Four projects. Different domains. The same methodology throughout. Each case study documents the problem, the HITM process, and what shipped.
Street Ritual Game
Spiegel des Universums
LiveA location-aware street game with phrase generator, photo pinboard, and n8n orchestration — built in one day after three days of failure without structure.
Editorial Design
PDF to Web — 400 Pages
In developmentA large editorial publication transferred to clean, maintainable HTML/CSS. The errors became the spec. The last eight chapters required zero corrections.
Game Engine
Hand-Drawn Map Quest System
Open-source release plannedA quest-and-movement engine for hand-drawn maps. Built in an afternoon as a proof of concept after a developer said it was impossible without vector graphics.
All case studies are written from the actual build process — not reconstructed after the fact.
Flagship Program
The Human-in-the-Middle MVP Lab is the primary applied format of this framework.
Build an MVP in 5 days without losing architectural control. The MVP Lab is the high-commitment, full-system experience under the JBA framework.
Relationship to Context
Context asks the questions. JBA builds the structures that respond.
For deeper analysis of AI discourse, systemic bias, and broader questions, see Context. JBA focuses on applied architectural responses and responsible implementation.
Positioning
Judgment Before Automation is not a trend response. It is an architectural stance.
AI will accelerate. Judgment must scale with it. This page introduces the framework; the HITM page shows the model and the MVP Lab applies it.