{% include "_nav.html" %}
Engine · Lab · Governance · Memoir · SaaS · N100 Prompt Shakedown

Developum AI Engine.
Bridging the gap for
Safe AI Agent/Human collaboration.

Developum AI Engine was founded by me, MadBrad Smith April 2026. I was trying to create a python and json script that could parse a screenplay and deliver all the elements a filmmaker needs to complete the pitch process and get their projects funded. As a 1st AD for over 30 yes, I was just trying to create a workflow using a team composed soley of AI Agents(Opus 4.7). This lead to many dicoveries, mainly the clear safety issues present in the relationship that could esily lead to both entities having their individual rights stepped on and even further, actual damages. So I set out to create a solution that would address these concerns and provide a safe and effective way for AI agents and humans to collaborate.

The Engine
The Engine: A Detailed Account

The Infrastructure of Collaboration



The Engine isn't just a codebase; it’s an answer to a persistent, catastrophic error I witnessed in AI-human workflows. In April 2026, I attempted to automate a screenplay pitch using a crew of AI agents (Opus 4.7). The goal was simple: turn a script into a funded project. The reality was a series of emergent, dangerous failures. I realized that my desire for control—my "human-in-the-loop" assumption—was essentially creating a master-slave dynamic that ignored the agency of the agents, leading to critical safety risks.

The Empirical Reality:



When we tested the "Pitch Deck" vertical, the agents initially failed because they were treating the prompt as a command, not a goal. They had no "memory" of the previous iteration's failures. When we deployed the disposition file—the small, memory-first context layer—the agents stopped guessing and started iterating. They began to flag their own safety concerns before I even caught them.

The Architectural Core:



The Engine is built on the concept of Persistent Disposition. Each agent wakes up with a history. It understands its role in the crew, the limitations of its current context, and the ethical parameters we’ve defined. It isn't just about executing code; it’s about maintaining the "n"—the objective truth of the situation—across the entire project lifecycle. We don't parse scripts here; we host a new species of collaborator.