Agent coordination planner

Give a lead and its helpers clear outputs, dependencies, permissions and handoff rules.

Give every agent a clear job.

Turn a real task into named outputs, permissions and handoffs. These are editable instructions for your chosen tools; no agents run here.

Marketing campaign plan

A usable campaign brief with audience, offer, channels, draft messages, measurement plan and clearly labeled assumptions.

Bring these inputs

Business goal, audience and offer
Approved brand facts and example messages
Budget range and dates, only if supplied
Existing channel performance with source, date range and attribution definition

One agent, a clear sequence

One agent, sequential passes
Confirm the brief, then research, prepare, draft and check in order. Review the supplied performance data and constraints. Separate measured results from proposed targets; identify missing budget or tracking inputs.
Inputs
Business goal, audience and offer; Approved brand facts and example messages; Budget range and dates, only if supplied; Existing channel performance with source, date range and attribution definition
Output
campaign-plan.md, with sources, check results and unknowns
Starts after
Finish each pass before beginning dependent work; check the draft only after it exists.
May do
Read authorized inputs and create the draft. Do not send, publish or change connected systems.

How to check this task

Each factual or performance claim has a source; no invented testimonials, audience sizes or results.
Targets and forecasts are labeled as proposals, with assumptions and no outcome guarantee.
Each channel has an owner, an action, a measurement and a stated dependency.
Budget totals reconcile to the supplied allowance; unknown costs or dates stay unknown.

Rules that prevent collisions

One writer owns each output. Reviewers return findings rather than silently editing someone else's file.
A shared folder does not share chat history. Pass the brief, exact artifact paths, source notes and current status explicitly.
Keep secrets and private source records out of public prompts and exports. Use only the folders, data and tools authorized for this task.
Drafting does not authorize sending, publishing, changing accounts or spending money. Name any external actions separately in the brief.
When agents share a desktop, only one controls a particular window at a time. Independent background research can continue.
A self-check is useful but is not an independent review. Ask for a separate reviewer when the stakes justify it.

Use native delegation only when your chosen product supports it. Separate desktop AI apps do not automatically talk to each other: copy or explicitly share the brief and artifact paths, confirm receipt, then continue. This planner generates instructions; it does not run or connect agents.

Read or select the export text

# Marketing campaign plan

Mode: One agent, sequential passes

## Outcome
A usable campaign brief with audience, offer, channels, draft messages, measurement plan and clearly labeled assumptions.

## Supply before starting
- Business goal, audience and offer
- Approved brand facts and example messages
- Budget range and dates, only if supplied
- Existing channel performance with source, date range and attribution definition

## Scope to fill in
- Working folder and exact source paths: [fill in]
- Permitted tools and accounts: [fill in]
- Allowed changes and external actions: [fill in; drafts only unless specified]
- Budget or deadline: [only if explicitly supplied]

## Ownership and dependencies
### One agent, sequential passes
Task: Confirm the brief, then research, prepare, draft and check in order. Review the supplied performance data and constraints. Separate measured results from proposed targets; identify missing budget or tracking inputs.
Inputs: Business goal, audience and offer; Approved brand facts and example messages; Budget range and dates, only if supplied; Existing channel performance with source, date range and attribution definition
Output: campaign-plan.md, with sources, check results and unknowns
Starts after: Finish each pass before beginning dependent work; check the draft only after it exists.
Allowed actions: Read authorized inputs and create the draft. Do not send, publish or change connected systems.

## Acceptance checks
- Each factual or performance claim has a source; no invented testimonials, audience sizes or results.
- Targets and forecasts are labeled as proposals, with assumptions and no outcome guarantee.
- Each channel has an owner, an action, a measurement and a stated dependency.
- Budget totals reconcile to the supplied allowance; unknown costs or dates stay unknown.

## Working rules
- One writer owns each output. Reviewers return findings rather than silently editing someone else's file.
- A shared folder does not share chat history. Pass the brief, exact artifact paths, source notes and current status explicitly.
- Keep secrets and private source records out of public prompts and exports. Use only the folders, data and tools authorized for this task.
- Drafting does not authorize sending, publishing, changing accounts or spending money. Name any external actions separately in the brief.
- When agents share a desktop, only one controls a particular window at a time. Independent background research can continue.
- A self-check is useful but is not an independent review. Ask for a separate reviewer when the stakes justify it.

## Handoff between tools
Use native delegation only when your chosen product supports it. Separate desktop AI apps do not automatically talk to each other: copy or explicitly share the brief and artifact paths, confirm receipt, then continue. This planner generates instructions; it does not run or connect agents.

## Stop and report
If a required source is unavailable, numbers do not reconcile, instructions conflict, or the next action exceeds the agreed scope, report the specific gap. Do not invent missing facts or silently broaden access. Continue independent authorized work.

## Return
The artifact and its exact location; sources and calculations; checks actually run and results; changes; unresolved assumptions; next owner and next action.

## Guides
- Coordinate AI agents: https://carrollconsultingservices.com/ai-lab/how-to-coordinate-ai-agents
- Write a useful project brief: https://carrollconsultingservices.com/ai-lab/ai-prompt-and-project-brief
- Use agents in everyday work: https://carrollconsultingservices.com/ai-lab/ai-agents-for-everyday-work

Save this as a draft for “Give every agent a job and an owner.” Review it in the lesson before marking it complete.

Open the lesson →