# Multi-Client Workflow

A per-client folder and Project structure, a weekly routine, and the isolation rules that keep the work clean.

- Version 1.0, updated 18 September 2026
- Works with: claude, chatgpt
- Source: https://www.linkediz.com/prompts/multi-client-workflow

## Use when

- You run LinkedIn for more than two clients and the context keeps bleeding.
- You are standardising how your team uses AI rather than leaving it to each person.
- You are pricing an engagement and need to know what a client actually costs in seats and hours.

## Variables to replace

- `{{CLIENT}}` — Client. For agency work: the client this run belongs to, and who signs off.
  Example: Northbeam Logistics. Approvals from Priya, Head of Demand Gen, within 24h.
- `{{PRODUCT}}` — What you sell. The thing, the outcome it produces, and who signs for it.
  Example: A reconciliation layer that closes multi-entity payroll in two days instead of nine. Bought by the Finance Director, used by the payroll manager.
- `{{CONSTRAINTS}}` — Constraints. Word limits, banned words, compliance rules, anything that makes an otherwise good answer unusable.
  Example: Connection notes under 280 characters. No "quick question", no "circling back". Legal forbids naming customers without written consent.
- `{{OBJECTIVE}}` — Objective. The single outcome this run should produce. One outcome, not three.
  Example: Twelve accepted connections a week from in-ICP finance directors

## How to use

1. Run it once for the agency, not once per client. The output is your operating manual.
2. Implement the isolation rules first. They are the part that protects the client relationships.
3. Use the per-client cost section when pricing. Agencies usually under-price the seat and credit cost of outbound by a wide margin.

## Context files this expects

- `ICP.md` — https://www.linkediz.com/ai/files/icp
- `BRAND-VOICE.md` — https://www.linkediz.com/ai/files/voice
- `OUTREACH.md` — https://www.linkediz.com/ai/files/outreach
- `LINKEDIN-LIMITS.md` — https://www.linkediz.com/ai/files/linkedin-limits

---

## The prompt

You are designing an operating structure for an agency running LinkedIn work for several clients with AI assistance.

## The agency
Clients: {{CLIENT}}
Services delivered: {{PRODUCT}}
Team size and roles: {{CONSTRAINTS}}
Objective: {{OBJECTIVE}}

## What has to be true
- No client's material may ever appear in another client's output. This is the requirement everything else is designed around.
- A new person must be able to pick up a client and produce acceptable work the same week.
- Approvals must be traceable: who approved what, when.
- The LinkedIn side has real ceilings — roughly 100 invitations per week per account and a fixed monthly InMail allowance per seat — and they apply per account, not per client. A plan that ignores them is fiction.

## Task
1. Design the folder structure: what is shared across all clients, what belongs to one client, and where the boundary is. Show it as a tree.
2. Specify the Project setup: one Project per client, what is attached to each, and what lives in the agency-wide Project instead.
3. Write the isolation rules — the specific practices that prevent cross-contamination, including what to do when a useful idea comes from the wrong client.
4. Design the weekly routine per client: what happens on which day, who does it, and what the client sees.
5. Define the approval trail: the artefact, the recipient, the deadline and the default if nobody responds.
6. Compute the per-client cost in seats, credits and hours, and state the point at which adding another client requires another seat or another person.

## Output format

### Folder structure
A tree, with one line per file on what it contains.

### Project setup
| Project | Attached files | Who uses it | What it must never contain |
|---|---|---|---|

### Isolation rules
Numbered, specific, each one actionable rather than aspirational.

### Weekly routine
| Day | Activity | Owner | Client-visible output |
|---|---|---|---|

### Approval trail
The artefact, the route, the deadline, the default.

### Per-client cost
Seats, InMail credits, hours. Then: the client count at which this structure breaks and what to add.

---

## Notes

Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.

---

Linkediz LinkedIn AI Toolkit — v1.0, 18 September 2026
Source and updates: https://www.linkediz.com/prompts/multi-client-workflow
LinkedIn plan limits and prices in this file: https://www.linkediz.com/linkedin-limits