AVAILABLE FOR FULL-TIME ROLES OPEN TO FREELANCE CONTRACTS AI FULLSTACK ENGINEER · AGENTIC AI AGENT-READY · HUMANS WELCOME AI AGENTS · LLM TOOLING · EVALS NEXT.JS · TYPESCRIPT · REACT BASED IN LISBON · REMOTE WORLDWIDE
03 / Case study — agent orchestration

A delivery harness, not another chat window.

Ralph Starter packages the operating system around AI coding: specs, isolated worktrees, race and consensus modes, integrations, verification, and a clean path back into a real repository.

Role
Creator / AI engineering
Period
2026 — present
Surface
CLI + MCP
Status
Production
100+ Daily downloads Public npm adoption
3 Swarm modes Race · consensus · pipeline
4 Integrations Figma · GitHub · Linear · Notion
1 Delivery contract Spec → isolated work → verified merge
03.1 / The problem

Raw model capability was not the bottleneck. The hard part was making parallel agents useful inside repositories where collisions, stale context, unverifiable claims, and unbounded token use can erase the speed advantage.

03.2 / The system
  1. 01

    Specs define outcome, constraints, acceptance checks, and ownership before work starts.

  2. 02

    Each worker runs in an isolated git worktree so parallel attempts remain comparable and recoverable.

  3. 03

    Race, consensus, and pipeline modes match the collaboration pattern to the problem instead of treating every task alike.

  4. 04

    Repository checks and visual evidence decide what lands; the model does not grade its own output.

03.3 / Outcome

The result is a reusable operating layer for AI development: teams can increase parallelism without giving up repository discipline, reviewability, or the ability to reproduce how a change was produced.