AGENTS.md is a project-level configuration file that provides AI coding assistants with complete project context, development principles, and operational guidelines. It follows the agents.md standard and works across Claude, Cursor, GitHub Copilot, and other AI tools.

What is Jimmy's Workflow?

Jimmy's Workflow is a four-phase validation system (PRE-FLIGHT, IMPLEMENT, VALIDATE, CHECKPOINT) designed to prevent AI hallucination and ensure robust implementation. Each phase has specific gates and confidence levels (HIGH/MEDIUM/LOW) that determine when human review is needed.

How do I set up multiple AI instances as a team?

Assign each AI instance a role card with identity, responsibilities, personality traits, and success criteria. Use file-based handoff protocols for coordination. Personality orchestration at the system prompt level produces measurably better results than treating AI instances as generic tools.

Guides

Practical guides drawn from real-world experience running multiple AI instances across machines since October 2025. These cover the full development loop: research externally, document, review, implement.

The full workflow loop

Most people use AI as a code generator. This workflow treats AI as a development team — with research, documentation, review, and implementation as distinct phases.

The full development workflow loop — Research, Document, Review, Implement, Validate

Research (Claude AI)
    │
    ▼
Document (exec summary, spec, implementation plan)
    │
    ▼
Review (Gemini Pro — challenge, catch blind spots)
    │
    ▼
Implement (Claude Code — execute from documentation)
    │
    ▼
Validate (Jimmy's Workflow — PRE-FLIGHT → IMPLEMENT → VALIDATE → CHECKPOINT)

What’s in this section

The methodology

Guide	What it covers
Documentation-First	Why documentation comes before code. Executive summaries, specifications, and AI-optimised natural language.
Implementation Plans	Natural language, test-driven plans optimised for AI consumption. No pseudocode.
External Research	Two-pronged research using multiple AI systems — research with one, review with another.

The team

Guide	What it covers
Team Orchestration	Personality orchestration — why treating AI instances as colleagues produces better results than treating them as tools.
Multi-Agent Setup	Coordinating multiple instances across machines with role specialisation and resource delegation.
Writing Role Cards	How to define AI agent roles — responsibilities, personality, relationships, and success criteria.
Handoff Protocol	File naming, handoff templates, escalation, and status updates between agents.

The journey

Guide	What it covers
Evolution (v0-v4)	How the workflow evolved from copy-pasting ChatGPT into VS Code to a coordinated multi-agent team across 4 machines.

Where to start

Using one AI assistant on one machine? Start with the methodology — Documentation-First, Implementation Plans, and External Research. These work with a single Claude Code or Cursor instance. The multi-agent guides are for later, when you want to scale.

Already running multiple AI instances? Go straight to Multi-Agent Setup, then Role Cards and Handoff Protocol.

If you want to…	Start with
Understand the philosophy	Documentation-First
Write AI-ready plans	Implementation Plans
Use multiple AI systems for research	External Research
Scale to multiple AI instances	Multi-Agent Setup
Give AI instances identities	Team Orchestration
See how this evolved from ChatGPT copy-paste	Evolution