Usage controls

AI spend you can plan for.

Set budgets for each team, agent and workflow. Get a warning before a budget runs out, and pause work when it does.

Models Usage controls
Live
Monthly budgets By team
  • Support 42% of budget
  • Marketing Alert sent at 80%
  • Research Paused at limit

Limits can be set for a team, an agent or a single workflow.

No surprise bills.

Budgets where they matter

Set limits for a team, a single agent or one workflow.

Early warnings

Owners get an alert before a budget is used up, with time to act.

Hard limits when needed

Runs pause at the limit instead of quietly running up cost.

Budgets by team, agent and workflow

Give each team a monthly budget, and add tighter limits for a busy agent or an expensive workflow.

Models Usage controls
Live
Monthly budgets By team
  • Support 42% of budget
  • Marketing Alert sent at 80%
  • Research Paused at limit

Limits can be set for a team, an agent or a single workflow.

Alerts and hard stops

Owners are warned as spend gets close to a limit. If a limit is reached, new runs pause until someone raises it.

  • Alerts before the limit
  • Runs pause at the limit
  • Owners decide what happens next
Live run Refund case 4821
Live
  1. Read the refund request
  2. Check the order history
  3. Refund above team limit
Escalated Needs a decision from Priya, Support lead

The agent paused this step. Reminder sent after 2 hours.

Approve Pause run Cancel

Usage you can read

See runs, tokens and cost by team, workstream and agent, so you know where AI spend is going.

ROI and operations AI impact dashboard
Live
184 Runs
37m Turnaround
92% Approval clarity
$428 Model cost
Time saved Rework reduced Skill adoption
How it works

From request to recorded result.

  1. Set a budget

    For a team, an agent or a workflow.

  2. Work runs as normal

    Every run counts toward its budget.

  3. Owners get an alert

    Before the budget is used up.

  4. Runs pause at the limit

    Until someone raises it.

Every feature runs inside the same six controls.

Identity, access, approvals, supervision, audit and policy apply to every agent and every run, whichever part of the workspace it happens in.

See governance and audit
  • Identity
  • Access
  • Approvals
  • Supervision
  • Audit
  • Policy
FAQ

Usage controls: questions and answers

Short answers to what teams ask before they put this part of SoftworkerAI to work.

Contact us directly
What can we set a budget for?

A team, a single agent or one workflow.

What happens when a budget runs out?

New runs pause and the owner is told. Work starts again when someone raises the limit.

Who gets the alerts?

The owner of the budget, such as the team lead or the agent owner.

Can we see where the money went?

Yes. Usage is broken down by team, workstream and agent, with runs, tokens and cost.

The multiplayer workspace for humans and AI agents is how teams move beyond prompting and safely hand AI real work. It gives people one place to plan, approve, and oversee execution, so they can run work with AI agents they can govern and trust.
The SoftworkerAI Team