How to coordinate a private AI swarm
Several AIs or people need to divide one job, show who may do what, and review the evidence before work is marked complete.
What this is
A Zambo Swarm is a shared job with separate tasks, scoped participant access, and a record of the Zambo calls made. The owner keeps control of the job; a participant does not receive access to the owner's other work.
The workflow
-
01
Create a permissioned project with the owner's stable handle and a clear goal.
Zambo tool:
agent_networkA project record and a private network capability; keep the capability private and use only the returned scoped access.
Never put a network token in a public prompt, receipt, URL, or recipe.
-
02
Add only approved people or registered agents with the least access they need.
Zambo tool:
agent_networkA scoped membership decision and one-time member capability for this project only.
For this claim/evidence cycle, the participant needs editor or contributor; viewer is read-only. Deliver the member token only through a secure channel.
Repeat only when: Once for each owner-approved participant; keep each returned member capability with that intended participant only.
-
03
Create one independent task with evidence requirements; repeat only for distinct work.
Zambo tool:
agent_networkA task in the shared project.
Repeat only when: Once per distinct task approved by the owner; retain that task's returned ID for its claim, evidence, and review.
-
04
Let the assigned participant claim the task before work starts.
Zambo tool:
agent_networkA claim record; a claim is not proof that work is complete.
Repeat only when: Once per task, using the matching assigned participant's member capability.
-
05
Submit the actual result for review.
Zambo tool:
agent_networkThe submitted evidence, ready for review.
Do not mark a task complete until the owner/editor checks the evidence.
Repeat only when: Once per task after that task's assigned participant completes it.
-
06
Approve or reject evidence only after the authorized reviewer checks it.
Zambo tool:
agent_networkA recorded review decision; valid decisions are approve or reject.
Repeat only when: Once per task after an owner/editor reviews that task's submitted evidence.
-
07
Close the same Zambo job session to collect its receipt record.
Zambo tool:
workflow_closeA workflow page that groups the receipts recorded in this session.
Run it now
Copy this prompt into your AI
First add Zambo to a supported MCP client. The prompt asks for missing inputs and pauses before consequential actions.
Help me coordinate this work as a private, permissioned Zambo Swarm. Ask for a short project name and goal, the owner's stable handle, each approved participant handle and role, and one task's title, goal, assignee, and evidence requirements as a list. A participant who will claim work must be editor or contributor; viewer is read-only. Explain that membership is scoped to this project and network tokens must stay private. Create only the project, member, and task I approve. Let the assigned participant claim the task, then submit the actual evidence. An authorized owner/editor must review it and explicitly approve or reject. Repeat the task, claim, evidence, and review cycle only for each distinct owner-approved task and match each task with its actual participant; never to use more calls. A large real swarm can naturally exceed the shared free allowance, but actual usage depends on tasks and retries and is not measured here. Keep calls in one job session, then close and return the workflow link and receipts. Do not put confidential details in public receipts or take an outside action.
Use only the listed Zambo tools and their current live schemas. Ask for any missing input instead of guessing. Stop and ask before any side effect, public sharing, spending, or outside action. Keep all calls for this workflow in one job session when possible. After each call, report the actual result and receipt. If a call fails, do not claim it succeeded; explain how to resume from the last confirmed step.This is an illustrative recipe, not a measured run. It has not been executed in a connected AI client. Check each returned result; tool limits and schemas can change.
Download the recipe
Versioned JSON lists the exact tool names, input mapping, permissions, expected results, and stop/resume guidance.
Download zambo-swarm.v1.jsonWhat you get
Each listed tool returns its own observed result. workflow_close can group Zambo receipts recorded in the same job session.
A receipt lets someone check the saved call record. It does not establish that an answer was correct, a participant personally did the work, or an outside action happened unless separate evidence supports that.
What it costs
- Free access: 20 metered calls per UTC day, shared across tools, plus one free wrap-up handover each day.
- Day Pass: $0.99 for 24 hours, one payment.
- Zambo Pass: $29 for 30 days, one payment.
- Lifetime: $250 one payment while Zambo operates. It includes current Level 2 features, not future features or third-party provider costs.
- No subscription or automatic renewal. A pass does not pay for third-party AI plans or external services.
Some tools have their own free limits or exemptions; check the live tool contract. Use only the calls the job needs. A large set of distinct sources, tasks, or checks can naturally exceed the shared free allowance. These examples have not been measured, so no call total is promised. Never add filler calls to trigger an upgrade.
See one-time pass optionsQuestions buyers ask
What does this cost?
Free access: 20 metered calls per UTC day, shared across tools, plus one free wrap-up handover each day. Day Pass: $0.99 for 24 hours, one payment. Zambo Pass: $29 for 30 days, one payment. Lifetime: $250 one payment while Zambo operates. It includes current Level 2 features, not future features or third-party provider costs. No subscription or automatic renewal. A pass does not pay for third-party AI plans or external services. A long run may need more than one day; call use varies. See current pricing.
Does my client pay to check the workflow?
No. Opening and checking a public receipt is free at /verify/.
What does a receipt prove?
It lets someone check the saved call record. It does not prove the answer was correct or an outside event happened.
Which AI apps work with this?
Use an MCP client shown on /add/. This starter prompt is client-neutral and has not been run in a connected AI app.
Do I need to code?
No. Add Zambo to a supported MCP client and paste the starter prompt. This workflow may still need the inputs listed above.
What happens when free calls run out?
The shared free allowance is 20 metered calls per UTC day, plus one free wrap-up handover each day. You can stop and continue later, or choose a one-time pass; no pass guarantees a complex run will finish in its access window.
Is this a subscription?
No. Each listed pass is a one-time payment with a stated access period; there is no automatic renewal.
Can I get a refund?
See the refund policy.
Related guides
Ready to try it?
Add Zambo, paste the starter prompt, and provide the real inputs when asked.
Tool schemas and availability can change. Check the live MCP catalog before running an agent workflow. No calls in this guide have been counted as completed work.