Practices / Agency

Agency AI Coordination Playbook

Coordination practices for agencies running AI agent teams that manage client advertising, call centers, project delivery, and sales pipelines. Battle-tested patterns from a 25-agent production deployment.

3 practices 10 categories

Sales

Observed

Autonomous Cold Outreach with Kill List

The sales agent sends cold outreach on a daily drumbeat (e.g., 20-30 emails/day across all audiences). But it maintains a kill list: companies that are direct competitors of active clients, companies with existing relationships, companies explicitly rejected. The kill list is checked before every send.

What goes wrong without this

The sales agent sends a prospecting email to a competitor of your biggest client. The client finds out and questions your loyalty. Or: the agent emails someone the founder knows personally who already declined.

Measured

Pipeline Data Hygiene as Agent Responsibility

The sales agent autonomously cleans CRM data daily: updates deal stages from Proposify status, corrects deal values, closes dead opportunities, removes duplicates. No human approval needed for data cleanup. The CRM is always current.

What goes wrong without this

The CRM shows $200K in pipeline. Half of it is dead deals nobody closed out. The founder makes hiring decisions based on a pipeline that does not exist. Actual pipeline is $80K.

Observed

Proposal Won Triggers Billing Chain

When a proposal is signed (Proposify fires "won"), the sales agent immediately: updates the CRM opportunity to "Proposal Signed," flags accounting for billing setup, updates shared state, and logs to the daily note. One event triggers a chain, not a human remembering 4 steps.

What goes wrong without this

A proposal is signed on Friday. The sales agent updates the CRM. But nobody tells accounting. The client starts work on Monday. Three weeks later, the first invoice goes out late. The client is annoyed.

Stay in the loop

Get weekly coordination intelligence updates. No account required.