The work
OperationsAgencies

An agency running more than a hundred and fifty clients gives the routine half of the work to agents, and nothing reaches a client ungraded.

WEDOHYPE
Quality gate
QA agent
AShipsRule
BShips with notesRule
CBack to the agentWith specific feedback
D / FBack, and escalateRule
The reviewer is never the author

Nothing reaches a client ungraded. C goes back with the reason attached.

The situation

How this used to work

A launch email for a client once went out directly, without review.

That is the whole origin of the first rule in this system, and it is why the rule is absolute rather than a preference. Every email the agency's AI writes is a draft. There is no send. Not for routine follow-ups, not for anything.

A system that can act on the outside world needs its limits set from a real incident, not from a risk workshop.

What we built

The system

The agency workspace itself: an orchestrator, eight agents, twenty four commands and forty three skills, running a web agency with more than a hundred and fifty clients.

The agents are the org chart. Account manager, brief maker, copywriter, designer, developer, financial, QA and sales.

Three rule files load on every single session and cannot be skipped: routing decides who gets the work, quality gates decide whether the work ships, escalation decides when the machine stops and asks a person.

How it works

The pipeline, step by step

01 / Route

The task finds its agent

A request routes by what it is, in either language the agency actually works in. Bigger jobs run as sequences: a full website goes account manager, then copywriter, then brief maker, then designer, then developer.

RoutingLoaded every session
Client email, follow-up, kickoff
Account manager
Website copy, per page
Copywriter
Build, deploy, DNS
Developer
Review before delivery
QA
A full website runs five agents in order

A table that loads on every session, so nothing is routed by mood.

02 / Gate

Nothing reaches a client ungraded

Every deliverable gets reviewed against per-agent criteria and graded. A or B ships. C goes back to the agent with specific feedback. D or F goes back and escalates to a human.

03 / Separate

The reviewer is never the author

QA audits, the copywriter rewrites, and the two never merge. An agent reviewing its own output does not find its own faults, it explains them. This was learned the expensive way and written down.

04 / Escalate

Five reasons to stop

Missing prerequisites, money or bad news, a repeated quality failure, an ambiguous instruction, or a change to the system itself. Any of them and the work stops and asks rather than guessing well.

Stop and ask5 reasons
A prerequisite is missing
Stop
Money, or bad news
Human review
The second quality failure
Escalate
An ambiguous instruction
Ask first
A change to the system
Plan, then approval
The work stops rather than guessing well

Each reason with the consequence attached, which the sentence cannot hold.

05 / Remember

The lessons persist

Learnings, patterns, client preferences and past failures live in files that outlive the session, so a mistake made once in April is still avoided in July.

What changed

The result

One agency, more than a hundred and fifty clients, and the boring half of the work done by the system.

The rules got stricter as it grew, not looser. Every hard limit in there traces to something that actually went wrong once.

The stack

Runtime

  • Claude Code
  • 8 agents
  • 24 commands
  • 43 skills

Connected

  • Gmail
  • Google Drive
  • Docs
  • Sheets
  • Calendar
  • Notion
  • Slack
  • Airtable

Rules

  • routing
  • quality gates
  • escalation
  • persistent memory

Free 30 minute call

Let's find where AI fits in your business

A 30 minute call, free, no commitment. You leave with two or three things worth building, whether or not you work with us.

Free, no commitmentYou own everything we buildNo slide deck