This is the operating methodology that made it workable: the stack, the source-of-truth system, the workflow patterns, and an orchestration agent that keeps AI-assisted work connected instead of scattered.
Program Director
Shared as a public case study in practical AI orchestration, not AI theater.
Applied case study
Context
The project that motivated this was complex. Confidential product, small team, limited budget, aggressive timeline.
The problem with AI-assisted work isn’t output. It’s that the output goes everywhere. Product decisions in one doc. Design exploration in another. Tasks created without context. AI conversations that go nowhere. Nothing connects.
The answer was to build the operating system before accelerating the work. Project OS gives AI tools enough structure to actually help: planning, tasks, handoffs, QA, documentation. And it keeps humans in control of scope, privacy, and decisions that can’t be undone. The product details stay confidential. The methodology doesn’t.
Overview
This is the stack. These are the tools and patterns in active use.
Working docs, meeting notes, brainstorming, shared context
Roadmap, Gantt, tasks, dependencies, milestones, weekly status
Design source of truth, components, tokens, platform guardrails, handoff
Versioned methodology docs, implementation notes, issues, commits, and proof of work
Agent-assisted planning, repo work, architecture review, Asana automation
Design exploration, creative iteration, concept review, visual direction
Setup support, code assistance, implementation review, structured file edits
Planned team communication and agent notification surface
Controlled bridge between AI agents and external tools
Source-of-truth patterns, rules, reusable prompts, approval gates, and context management conventions
Orchestration-agent pattern: reads approved context, proposes actions, flags risks, and prepares handoffs for human review
System map
Information architecture
Not every document carries the same weight. The system helps AI-assisted workflows know the difference between a committed decision and a half-finished note.
This is what stops an AI tool from treating a brainstorm like a committed requirement.
Workflow
Orchestration
Phred has a job. Read the right context, identify what changed, propose the next action, and flag what needs a human. No broad authority. No autonomous decisions. A well-defined role for a well-defined tool.
Integration map
Project OS defines what's approved. Everything else (docs, tasks, meetings) connects to that foundation.
One place for visual decisions. AI speeds up exploration. A structured handoff makes sure engineering gets what it needs.
The repo holds methodology docs, notes, and proof of work. AI coding tools assist with implementation; humans review before anything ships.
Phred routes context between systems. MCP keeps the integrations controlled. What surfaces is what needs a decision.
QA plans run against approved requirements. Simulation and UAT run before production. The confidential specifics don't need to be here.
Controls
AI gets more useful when the rules are explicit. Project OS tells agents what’s approved, what’s open, what’s off-limits, and when to stop and ask.
What’s missing
Takeaways
Built the operating model before the product. Rework is expensive. Context loss is more so.
Connected AI to real product, design, engineering, and QA workflows. Human approval stayed in the loop where it mattered.
Converted ambiguity into structure, tasks, handoffs, and decision paths.
The tool stack is real: Claude Code, Codex, MCP, GitHub, Figma, Asana, React Native / Expo. Each one chosen for a reason.
Kept humans in control of privacy, permissions, scope, and anything that can't be undone.
Public methodology note
This methodology is reusable. The patterns (source-of-truth structure, approval gates, agent boundaries, decision logs) can apply to any team that needs AI-assisted work to stay connected and under control.
What’s not here: the specific product, company, code, designs, or business details. Those are confidential. Everything else is fair game.
Not prompts for the sake of prompts. Not AI theater. Practical systems that help small teams move faster without losing control of the product, the roadmap, or the standards.
Built by Randall Fransen. Applied during work on a confidential mobile app project. Product specifics stay confidential.