Platform · Connect Your Agent

Your agent.
On the queue.

The platform ships zero AI. Instead, it hands your request queue to the agent you already run. Client asks, your agent builds, you approve the preview. That is the whole loop.

yourbrand · agencylabel listen
agencylabel listen
token verified · workspace yourbrand
watching 4 projects for queued requests
req-214 update hero headline + CTA (hillside-dental)
· spawning agent claude · reading skill: edit-site-copy
· src/pages/index.astro modified
branch al/req-214-hero-cta · PR opened
preview deploy ready · client notified
run logged · 4m 12s · waiting for next request
How it connects

Two doors in.
Both are yours.

Run the listen daemon for full autonomy, or point any MCP-capable agent at the workspace and drive it yourself. Same queue, same tokens, same audit trail.

Tokens

Workspace-scoped, hashed at rest

Create a token with a device-code flow, scope it to your workspace, revoke it anytime. Your agent authenticates like a first-class citizen, not a scraped session.

Daemon

agencylabel listen

A long-running process on your machine that polls for queued requests on auto-enabled projects and spawns your agent per request. Claude Code by default; point it at any binary.

MCP

The workspace as tools

An MCP server exposes requests, clients, skills, and quotes to your agent: list the queue, mark in progress, attach a branch, read the skill for the job.

Skills

Versioned playbooks for agents

The platform serves a library of Markdown skills your agent reads before working: how to build, edit, and operate on client sites. Consistency without a model in the loop.

Runs

Every run on the record

Branch, PR, duration, and outcome logged per run on the Agents & MCP screen. If a request fails three times, it flags for a human instead of looping.

The loop

Request to production,
hands off.

01 · Request

Client asks

A request lands in the queue from the portal or a pinpoint on the live site.

02 · Pickup

Daemon hands off

Your agent gets the request, the client context, and the matching skill.

03 · Build

Work on a branch

The agent works in that client's site repo and pushes a branch, never to production.

04 · Preview

Deploy to review

A preview deploy attaches to the request. The reviewing side gets a link, not a diff.

05 · Approve

Human merges

You or your client approve. Merge ships it. The run is logged with the branch and PR.

Why zero AI inside

We're the rails,
not the engine.

Platforms that bolt a model inside choose your tools for you and charge you per thought. Agency Label stays the system of record: the queue, the portal, the approvals, the billing. The intelligence is yours: your agent, your API keys, your machine, upgraded whenever you like without waiting on us. That is also why agent runs are unlimited on every tier. They run on your side, so we have no reason to meter them.

No AI features. No AI fees. The platform never calls a model. "Connect your agent" means exactly that: your agent, your credentials, our queue and approval gates around it.

Works with your stack. Claude Code out of the box. Anything that speaks MCP or can run as a binary works: the daemon does not care what does the thinking.

Plug your agent in this afternoon.

Create a workspace, add a client, run one command. The first request your agent ships changes how you scope your week.