---
title: Dispatch
kind: side-project
role: Solo build
years: 2025 – present
status: running
summary: >-
  Rails worker that polls Work Context Protocol for queued work items and
  dispatches them to Claude Code agents. The loop-closer between WCP and the
  Agent Pipeline.
links:
  - label: github.com/dpaola2/dispatch
    url: 'https://github.com/dpaola2/dispatch'
tags:
  - ai
  - rails
  - agents
  - wcp
  - claude-code
order: 3
---

Once you have a structured work tracker ([Work Context Protocol](/portfolio/work-context-protocol)) and a structured way to do work with an agent ([Agent Pipeline](/portfolio/agent-pipeline)), the missing piece is the worker loop that closes the two together — something that watches WCP for queued items and hands them off to a Claude Code session running with the right context.

Dispatch is that worker. It's a Rails 8 app: Solid Queue for the polling, a small web UI for managing workers and watching run history, Kamal for deploy. Workers can run in prompt mode (one-shot completion) or skill mode (multi-step pipeline). Each run gets a structured record so the next session can pick up where it left off.

The three together — WCP for memory, Agent Pipeline for shape, Dispatch for the loop — make up the AI-augmentation stack I actually use day to day.