Loading...
Forceworks · Prerequisite Setup
RapidClaw
Prerequisite Setup · Before running the wizard
Prepare Azure before RapidClaw.
RapidClaw runs in the customer’s Azure tenant. For clean isolation, create a new dedicated Azure subscription for RapidClaw instead of mixing the runtime with unrelated workloads. Before starting setup, confirm the subscription, target region, and Microsoft Foundry / Azure OpenAI quota are ready.
01 / 02
Create a dedicated Azure subscription
Create a new Azure subscription for RapidClaw so the runtime, quota, cost, access, and policy boundary are easy to understand.
The subscription should belong to the customer tenant and be used specifically for RapidClaw. This keeps the deployment isolated from unrelated Azure workloads and makes billing, governance, and support conversations cleaner.
- Create a new customer-owned Azure subscription for RapidClaw.
Open Azure Subscriptions
If you cannot access this link, you will need higher permissions to deploy RapidClaw. - Use a clear name, such as RapidClaw Production or RapidClaw Pilot.
- Strongly recommended: Set a budget Alert.
- Confirm the subscription is active.
02 / 02
Request Microsoft Foundry quota
RapidClaw needs available Azure OpenAI quota in the dedicated subscription before deployment.
The request is made for the Azure subscription. You do not need to create a Foundry project or Azure AI resource first. RapidClaw creates its own Azure AI resource during deployment and checks the selected subscription, region, models, and available quota before it starts.
Open Microsoft quota request form
Use the subscription ID for the dedicated RapidClaw Azure subscription.
2.1Submit the request
- Have the dedicated RapidClaw subscription ID and intended deployment region ready.
- Complete the company and contact fields, then enter the suggested justification below.
- Use the current form selections listed below.
- Submit the request and wait for Microsoft's approval email. Approval can take several days.
- Return to the RapidClaw setup wizard and run the prerequisite check again.
Suggested justification
RapidClaw is a customer-owned Azure deployment that operates a governed team of AI agents for business workflows. It uses Azure OpenAI for interactive agent orchestration, scheduled tasks, Microsoft Teams and email workflows, with operator approvals and audit controls. We are requesting 100 kTPM of Global Standard quota for an initial RapidClaw deployment in our selected supported Azure region. Usage will be monitored through Azure, and a monthly cost alert is configured during setup.
2.2Supported deployment regions
Choose one of the currently supported RapidClaw deployment regions:
- Australia East
- East US 2
- South India
- Sweden Central
- West US 3
2.3Recommended form selections
- 11. Quota Type: Model Deployment (PTU/RPM/TPM)
- 12. Model Type: Azure OpenAI
- 13. (Azure OpenAI) Quota Request Type: Global Standard
- 14. (Azure OpenAI) Global Standard Model: gpt-5.6-sol
- 15. Global Standard Region: Select the supported region planned for RapidClaw deployment.
- 16. (Azure OpenAI) Global Standard Quota: Enter 100. The form requests the total required quota in kTPM, so 100 means 100,000 tokens per minute.
If the RapidClaw prerequisite check reports missing embedding quota, submit a second request for text-embedding-3-small with a total quota of 10 kTPM in the same supported region.
Quota is a rate limit, not a prepaid usage charge. Azure bills the subscription for model tokens actually used by RapidClaw. Review Microsoft's current quota guidance for the latest process.
Do not start deployment until the RapidClaw prerequisite check confirms that the required model quota is available.