Per-agent and per-team budget policy

Budgets should be attached to teams, workflows, role agents, and risky actions before runs begin.

Budget policy is part of execution policy. It decides which runs can start, which can escalate, and which require approval.

AstraRunner treats this as an execution-platform concern: the run needs durable state, traceable decisions, cost visibility, and enough structure for teams to review what happened after the agent finishes.

Patterns that work

• Set monthly team budgets and per-run caps.
• Use stricter caps for exploratory agents.
• Require approval for model escalation over threshold.
• Reserve budget for validators and rollback checks.

Implementation checklist

• Track budget consumption in near real time.
• Show remaining budget in the operator UI.
• Alert before hard stops.
• Record budget override approvals.

Watch outs

• Hard stops can leave work half-finished.
• Shared budgets need fair attribution.
• Budget exceptions become policy unless reviewed.

Related reading

• AstraMemory on prompt context budgets

How this fits the Astra stack

AstraRunner owns the operational path for agent work: orchestration, scheduling, approval gates, traces, costs, and role-agent handoffs. AstraMemory owns durable context and retrieval. AstraGenie turns those capabilities into product workflows for teams that want automation without rebuilding the platform layer.