THE FIELD GUIDE · 3 min read
Resources, domains, plans, and costs
Register venture resources, connect domains, understand plan limits, and monitor AI spending.
Resources
Resources are the venture's infrastructure and service registry. Supported records include repositories, cloud services, databases, hosting, analytics, communication, and other operational assets.
Resource records can hold:
- provider and resource type;
- display name and description;
- URL or external identifier;
- non-secret configuration metadata;
- connection and health state;
- an optional credential relationship.
Owners and Admins can enter a secret when adding a resource, or choose Add secret or Replace secret when editing one. Saved secrets are not shown again; keeping the current secret leaves it unchanged. The secure Credentials area is also available for provider keys. Do not place raw credentials in descriptions, URLs, or general metadata.
Organ-managed resources, such as the Agent Workspace and Product Repository, show their name and description. Their connection details are managed by Organ; you cannot edit or remove these resources.
Workflows receive an explicit resource selection at launch. Agents can then request time-limited, least-privilege access through the Security Officer flow without placing the source secret in their prompt. See Resources and Security Officer.
Domains
Domain tooling associates hostnames with ventures and deployment resources. Domain state can be inspected and reconciled by the platform.
Your DNS provider can still require an external record change or verification step. Follow the domain status shown in Organ and confirm the final record at the DNS provider.
Plans and limits
Plans control portfolio and usage entitlements such as venture count. The product can enforce configured limits when new ventures or restricted capabilities are requested.
Costs
Cost reporting separates AI-model usage from container compute:
| Cost | Source | Refresh behavior |
|---|---|---|
| Model | Recorded input, output, cache-write, and cache-read tokens multiplied by catalog pricing. | Finalized as phase/run usage is persisted; live token counters can precede final cost. |
| Compute | Workflow and chat-container runtime weighted by workload tier and capacity rate. | Settles/accrues through an hourly-refreshed attribution view. |
Venture Cost Analytics can break model spending down by date and workflow. Detailed mode adds major phase, status, failure cost, token, department, average-cost, and compute views.
The displayed model total includes recorded workflow runs and Brain synthesis. Compute remains a separate card and is not added into “Total Cost.”
Venture monthly spend limits count model usage, compute, and money set aside for unfinished work. For work covered by these controls, new work is blocked when no budget remains. Enabling the hard-stop option also stops ongoing work between steps that use AI models once recorded charges reach the limit. Budget alerts only warn. Use provider-side controls alongside these limits. Compute costs are estimates based on how long the computing resources run and may differ from the cloud provider’s invoice. Costs for active chats update hourly.
For formulas, prompt-cache accounting, billing meters, model selection, and diagnosis, see Compute, tokens, and model selection.