Finance team allocates AI spend by department
Every AI agent action is tagged with a cost, and the cost tracker breaks spend down by team, employee, and workflow, making chargebacks simple.
Cost per Action
See exactly how many credits each message, task, employee, and team consumes so you can optimize spending.
Every message shows its credit cost. Every employee shows a running total. Every team shows aggregate spending. You know exactly where your budget goes, down to the individual interaction. No surprise bills, no unexplained usage spikes.
Cost visibility drives better decisions. If one employee consistently costs 3x more than another for similar tasks, you investigate. Maybe it is using a more expensive AI model than necessary. Maybe a skill is triggering too many tool calls. Maybe a duty is causing extra processing. The cost data tells you where to optimize, and the configuration tools let you act on it.
Compare cost efficiency across employees, teams, and task types. Identify which workflows are expensive and which are cheap. Shift routine work to faster, more affordable models. Reserve expensive models for tasks that actually need them. Over a month of tracking, most customers reduce their per-task cost by 20 to 40 percent just by adjusting model assignments based on the data.
Know Exactly What Each AI Employee Costs to Run
Every message your AI employee processes consumes credits. Cost tracking makes that consumption visible at the level that matters for management: per message, per employee, and per team. You see the credit cost of each interaction as it happens, not as a surprise at the end of the billing period.
This is not just an accounting feature. Understanding cost per message tells you which employees are efficient and which are expensive for the value they deliver. It gives you the data to optimize agent configurations, prompt designs, and task delegation patterns based on real usage, not estimates.
Running Totals, Team Aggregates, and Historical Trends
Individual message costs roll up into running totals per employee, which aggregate further into team and workspace totals. You can view cost breakdowns at any level of granularity: a single conversation, an employee's lifetime spend, or the entire workforce's monthly cost.
Historical trend charts show cost over time so you can spot patterns: a spike when a new workflow was added, a gradual increase as agent usage grew, or unexpected cost from a specific employee or team. These trends are essential inputs for capacity planning and budget conversations.
Costs are denominated in credits, with a clear credit-to-dollar conversion so you always understand the real-world cost of your AI workforce. Budget alerts let you set thresholds at the employee or team level, so you get notified before you hit a limit rather than after.
Cost Data for Chargeback and Internal Billing
For organizations that operate AI employees across multiple departments or business units, cost tracking supports internal chargeback: attributing AI costs to the teams that generated them. Export cost data by team, time range, and employee for integration with your internal billing or cost allocation systems.
This makes it straightforward to answer the question "how much did AI cost us this quarter, and which teams drove that cost?" It also creates accountability: teams see their own consumption and have an incentive to use AI efficiently rather than treating it as a free resource.
Use Cases
Product team optimizes high-cost workflows
The cost inspector surfaces which AI agent tasks burn the most tokens and time, so the team knows exactly where to optimize.
Startup founder controls burn rate on AI operations
The founder sets cost thresholds per AI employee and gets alerts when spend exceeds the limit, keeping AI costs predictable.
Operations team compares cost across agent configurations
By tracking cost per action, ops can A/B test different AI agent setups and pick the most efficient configuration for each workflow.
Comparison
| Before | After |
|---|---|
| AI costs are a black box, one total number per month. | Every action has a cost, visible by agent, task, and department. |
| No way to know which workflows are expensive to run. | Cost tracking surfaces the high-spend tasks immediately. |
| Chargebacks require manual log parsing to estimate usage. | Per-action cost data makes department-level billing automatic. |
| Teams over-spend on AI because there are no guardrails. | Cost thresholds and alerts keep AI spend within budget. |
FAQ
Is cost tracked in real time or with a delay?
Cost is tracked in real time. You see the credit deduction for each message immediately after it completes, with no delay. Running totals update live as your AI employees work.
Can I set spending limits per employee or team?
Yes. You can set credit budgets at the employee and team level with configurable alerts at defined thresholds (e.g., 80% used) and hard stops at 100%. This prevents any single employee or team from exhausting the workspace credit balance.
What drives cost per message?
Cost is primarily driven by the number of tokens processed (input context plus output) and the number of tool calls made. Longer system prompts, more skills loaded, and more complex reasoning all increase cost per message. The Inspector shows the token breakdown per step to help you optimize.
Is cost data available via API?
Yes. Full cost history is accessible through the REST API with filtering by employee, team, and time range. This supports custom reporting, BI tool integration, and automated cost monitoring.
Can I see how many credits each AI agent action costs?
Yes, every action is tracked with a credit cost so you can see exactly what each task, tool call, or conversation is spending. Cost breakdowns are visible per action, per task, and per employee.
I can see the exact credit cost of every task our agents run. It completely changed how we think about which workflows are worth automating.