# Credit Usage History

See exactly where your monthly credits go: split spend from direct employee requests and automation or system work, then inspect every charged system operation, including AI work, tools, Officer checks, knowledge, voice, meetings, video, and email. A burn chart shows the trend over time, and a separate grants table lists every bonus credit you received from promos, referrals, or purchases, with source and date.

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.

## How It Works

**Every message, task, and agent run is attributed to a credit cost so you see exactly what you are spending and where.**

Credit costs are tracked at the individual action level. Each message thread, each task execution, and each tool call has a credit cost attached to it. You can roll up costs by employee, by team, or by time period. The cost dashboard shows you your most expensive agents, your highest-cost task types, and how spend has trended over time.

Granular cost tracking makes AI workforce management concrete. You know which agents are delivering value relative to what they cost. You can set credit limits per employee or per team to cap spend before it runs. When a new workflow is expensive, you see it immediately and can optimize before costs compound. This is the data that makes AI workforce ROI measurable, not a guess.

## Use Cases

### 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.

### 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.
>
> Olivier D., VP of Operations · mid-size company

## Where Credit Usage History fits

Credit Usage History is part of How you see what they did.

A real-time activity feed shows who is working on what right now. The step-by-step inspector traces every tool call, decision, and reasoning chain. Cost tracking breaks down spend per message, per employee, and per team. Walk through your live 3D office to see your workforce at a glance.

- [How you see what they did](/en/features/observability): See everything. Miss nothing.

## Read the guide

- [Guide: Credit Usage History](/en/guide/monitor/activity)

## More in Monitoring

- [Activity Timeline](/en/features/observability/activity_timeline): See every piece of work your AI employees do as it happens: chat replies, scheduled runs, tool calls, delegations, and finished deliverables, all logged as activities you can open and inspect. It runs automatically for every employee with no setup, and a live feed in the workspace sidebar shows actions as they occur so you never have to wonder what is happening right now.
- [Action Inspector](/en/features/observability/activity_inspection): Click into any single activity and see exactly what your AI employee did: the model call pipeline, every tool it used with inputs and outputs, cost broken down by category, a duration waterfall, and the plan it followed. Available from the Activity tab, from Inspect on any chat message, or from the sidebar timeline.
- [See What Your Employee Is Told](/en/features/observability/prompt_inspection): Open any activity in the Activity Inspector and read the exact system prompt your AI employee received for that run: every instruction, every tool definition, and the manifest of which skills and duties were loaded and why. Nothing paraphrased, nothing summarized, the same text the model saw.
- [Spending Limit](/en/features/observability/spend_limit): Set a ceiling on how many credits your workforce can spend per hour, day, week, or month, so a runaway task or a busy day never turns into a surprise bill.
- [Team Dashboards](/en/features/observability/team_dashboards): Every team gets its own dashboard the moment you open it: team health, the current sprint, work in flight, momentum, objectives, and KPI progress, all built from data the platform already has. On the Custom plan, connect data sources and the same dashboard adds Revenue & Pipeline, Demand & Conversion, and Reach & Engagement cards for that team.
- [Data Export](/en/features/observability/data_export): Every workspace surface that shows your history, chat threads, the task board, activity logs, and Drive files, has its own download control that exports the current, filtered view as Markdown, CSV, or JSON. Use it to pull records for an audit, share a run outside the app, or keep an offline copy of what an employee produced.
- [Review the Quality of Every Deliverable](/en/features/observability/quality_evaluation): After an employee does real work, a quality reviewer scores each deliverable against a standard and shows the verdict in the activity inspector. Everyday chat is left alone, so you only grade real output.
- [3D Office View](/en/features/observability/office_3d): A workforce of AI employees is easy to lose track of as a list of chat threads. The 3D Office View turns it into a place: every employee is a character at a desk, hot-desk, or the lounge, moving between them live as their status changes, so you can see your whole company working at a glance instead of clicking through tabs.
- [In-App Notifications](/en/features/observability/in_app_notifications): See the moment an Employee finishes work, needs a decision from you, or your credit balance runs low, through a bell icon in your workspace that always fires. Reply straight from the notification drawer for Employee updates and comment threads, and control which events also reach your email through a short list of categories.
- [Reply to Notifications](/en/features/observability/notification_reply): Reply straight from the notification drawer, whether it is an update from an Employee or a comment on your work, and your response goes back with the full context of what it is replying to. No need to open the chat or dig up the artifact first.
- [Email Notifications](/en/features/observability/email_notifications): Sistava emails you when an employee finishes work, needs your approval, hits a blocker, or your credit balance runs low, so nothing important gets stuck waiting for you to open the app. You choose which categories of email you want; account security and billing mail stay on because they carry information you need regardless of your other preferences.
- [Email Digest Notifications](/en/features/observability/email_digest_notifications): A rolled-up email that summarizes what your AI employees did over a set period, instead of a separate message for every event. Today, notification email in Sistava sends per event and per category (employee updates, task completion, credit alerts, and so on); a digest option that batches those into one scheduled email is planned but not built yet.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)