For AI service providers · Guide
How to onboard a managed AI client
Set up a managed AI client by agreeing on the result, ownership and review responsibilities before connecting tools. Create the client workspace, authorize the required accounts and test one complete delivery. Keep a signed-off acceptance checklist so the first scheduled run has a clear definition of done.
By Agentic Workers Team · Published · Updated
Responsibilities and evidence
Agree on the owner and retain a safe evidence reference for each responsibility.
- Service scope
- Provider drafts; client accepts. Evidence: agreed output and stop conditions.
- Account ownership
- Client and provider confirm owners. Evidence: account inventory without secret values.
- Configuration
- Provider sets up the intended workspace and agent. Evidence: reviewed settings.
- Action review
- Named reviewer checks supported actions. Evidence: request and decision.
- Acceptance
- Client or delegated reviewer checks the result. Evidence: accepted artifact.
- Exit
- Account owner and provider remove access. Evidence: handoff and denied-access check.
1. Agree on scope and owners
Write down the deliverable, source period, recipient, review owner and stop conditions. Record who owns the workspace, source apps and billing. Use the onboarding checklist to keep missing information visible.
2. Create and connect in the right workspace
Create the Team workspace on the eligible plan and select it before creating agents. Use the customer portal for supported uploads and app authorization. Verify the selected client account with a harmless read. A connected status is not proof of every needed permission.
3. Accept a complete trial
Run the workflow with approved test data. Exercise a supported approval, inspect the output and verify delivery to a controlled destination. Fix missing access or unclear output before scheduling recurring work.
Example provider workflow. Adapt it to the client’s agreed scope.
- 01
Step 1: Agree on scope and owners
- 02
Step 2: Create and connect in the right workspace
- 03
Step 3: Accept a complete trial
Fit and limitations
- Good fit
- Providers applying this process to an agreed client service.
- Poor fit
- Treating this checklist as an automatic product feature or a substitute for a client agreement.
- Known limits
- These are operating recommendations. Test each supported product path in the target workspace and plan. Examples are not performance, pricing or security benchmarks.
Sources and evidence
Documentation establishes the scope of a claim. It does not replace an acceptance test in your client’s environment.
| Source | What it supports | Checked |
|---|---|---|
| Team workspace setupProduct documentation | Teams organize agents and connected tools by workspace. Verify membership and the active workspace before setup. | |
| Customer portal operating notesProduct documentation | Upload and app-connection invitations are scoped to a selected agent. Revoking an invitation is separate from disconnecting an account. | |
| Agent tools and review guidanceProduct documentation | Supported tool actions can require approval. Test the exact tool and runtime; coverage is not universal. |
Questions providers ask
Who is responsible for the result?
The provider names an operator; the client names the person who can accept the deliverable. The platform does not replace those responsibilities.
What evidence should we retain?
Keep the source date, workspace and agent, expected output, review decision and artifact reference. Exclude credentials and unnecessary personal data.
When should we stop and review?
Stop when the account, recipient, output or permissions differ from the agreed scope, then resolve the exception before continuing.
Set up one client service
Set up the client workspace, connect its tools and review the first deliverable. Use a tested delivery path, such as Telegram, so the client can receive work in chat. Track operating costs and review effort before pricing a recurring service.
Sign up now