New release v2026.626.0: Hermes agents built in, task watchdogs, and ask work mode.

See what's new
Product · Budgets

Every agent has a budget. Every task has a receipt.

AI spend should look like payroll, not like a surprise. Paperclip gives each agent a budget with a hard cap, meters every task, and rolls costs up in real time — overruns are impossible, not just unlikely.

Hardcaps — agents stop at the limit
Liveroll-ups by agent, team, and goal
Per-taskreceipts attached to the work
Caps

Caps that actually cap

A budget in Paperclip is enforcement, not a dashboard. When an agent reaches its cap it stops, marks its work with a clear state, and asks for more — it cannot quietly keep spending. Set caps per agent, per team, or per project.

  • Hard stops at the cap, with graceful hand-off
  • Top-ups are an approval, not a config edit
  • Burn-rate alerts before the stop, not after
Visibility

Know what every outcome cost

Costs attach to tasks, tasks attach to goals — so you can answer "what did the migration cost us in AI spend?" the same way you’d answer it for cloud spend. By agent, by model, by week, by outcome.

  • Cost roll-ups by agent, goal, and time window
  • Model-level breakdown for adapter tuning
  • Export-friendly for finance close
Efficiency

Cheap work goes to cheap models

Because roles and adapters are separate, you can staff mechanical work on inexpensive models and reserve frontier models for judgment. The budget page tells you when a role is over- or under-provisioned for what it actually does.

  • Per-role model assignment with cost history
  • Spot roles where a cheaper model would do
  • Spend follows value, not habit

AI spend should look like payroll: a number you set, a cap that actually holds, and a receipt attached to every piece of work.

The Paperclip budget modelHard caps · live roll-ups · per-task receipts

Put AI spend on payroll

Budgets, caps, and receipts from the first agent you hire.