> For the complete documentation index, see [llms.txt](https://kb.theloops.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://kb.theloops.io/agentstudio/resource-library/explainers/usage-tracking-optimizing-visibility.md).
# Usage Tracking: Optimizing Visibility
### What is Usage Tracking?
Usage Tracking gives visibility into how Digital Workers are actually being used: every invocation, the outcome it produced, and the underlying model activity behind it; captured consistently across the platform rather than left to each Digital Worker to report on its own.
Rather than building a separate, platform-specific analytics layer, IFS Loops connects this telemetry to Paid.ai, a business engine purpose-built to turn agent activity into usage and billing records. IFS Loops focuses on capturing accurate, complete telemetry from every Digital Worker; Paid.ai turns that telemetry into the usage insight, invoicing and revenue reporting that follow from it.
### Why It Matters
As Digital Workers take on more of a process, understanding what they are actually doing and what it costs to keep them running, becomes as important as understanding what a human team is doing. Without consistent usage data, it is difficult to answer simple questions: how often is a Digital Worker actually invoked, what does an outcome cost to produce, and how does usage change as adoption grows.
* Every Digital Worker is measured the same way, so usage is comparable across workers, crews and processes rather than reported ad hoc by each one.
* Turning usage into billing and commercial insight is handled by a platform built for that purpose, rather than a bespoke analytics build that has to be maintained alongside everything else.
* Usage data becomes a foundation other platform capabilities can build on, from governance and audit to commercial reporting, instead of a one-off report.
### How Usage Tracking Works
* **Telemetry at the source:** every Digital Worker invocation is tracked at runtime, as part of the same Monitor/Observe stage of the agent lifecycle that tracks tokens and LLM outputs with complete event traceability, so usage data reflects what actually ran, not an estimate.
* **Invocation and outcome telemetry:** what is captured goes beyond a simple call count, to the outcome an invocation produced, connecting raw activity to the business result it delivered.
* **A dedicated billing integration:** this telemetry flows to Paid.ai, an all-in-one business engine built specifically for AI agents, through a connector purpose-built for that hand-off.
* **Usage-based commercial models:** Paid.ai supports several ways of turning agent activity into a billable or reportable unit: per agent, per action, per workflow, or per outcome; so usage can be understood in the terms that make sense for a given process.
### What Usage Tracking Covers
Because telemetry is captured centrally rather than by each Digital Worker individually, Usage Tracking covers the same ground consistently for every worker on the platform:
* **Invocation activity:** how often each Digital Worker runs, and in response to what trigger.
* **Model and token activity:** the underlying LLM usage behind each invocation, tracked with full event traceability back to the interaction that produced it.
* **Outcomes:** what each invocation actually produced, not just that it ran.
* **Commercial usage signal:** activity translated into the unit of measure a business needs, whether that is per agent, per action, per workflow, or per outcome.
### The Usage Dashboard in IFS Loops Studio
This telemetry surfaces as a live cost and usage dashboard directly inside IFS Loops Studio. Each tenant sees only its own usage, and within a tenant, usage is separated by workspace — so a workspace only ever shows the agents and activity that belong to it.
The dashboard opens with a summary of AI spend across Loops for the selected period — total cost, calls, interactions, the number of agents involved, and the input and output tokens behind them — alongside a daily cost trend and a breakdown of cost by agent and by customer.
Below the summary, the same period can be explored at the level of an individual agent or customer, with cost, call and session counts, and average input and output tokens for each:
* **Cost by agent and cost by customer:** the highest-cost agents and customers for the period, ranked so the biggest drivers of spend are visible at a glance.
* **Agent detail:** cost, calls, interactions, sessions, and average input and output tokens for every agent, not just the highest-cost ones.
* **A selectable time period** (for example, the last 30 days) so spend and volume can be reviewed over whatever window is relevant.
### Getting Started
Usage Tracking runs automatically as part of the platform's Monitor/Observe stage — there is nothing separate to configure on a Digital Worker to start capturing its telemetry. The Paid.ai integration carries that telemetry through to usage and billing reporting, and the same data is available immediately as a dashboard in IFS Loops Studio, scoped to each tenant and workspace.
### Summary of Benefits
* Every Digital Worker's usage is captured the same way, at the source, with complete traceability back to the interaction that produced it.
* Usage and billing analytics are handled by Paid.ai, a platform purpose-built for that job, instead of a bespoke build IFS Loops would otherwise have to maintain.
* Activity can be understood in the commercial terms that fit the process: per agent, per action, per workflow, or per outcome.
* Consistent usage data becomes a foundation for governance, audit and commercial reporting alike, not a one-off report.
* Usage and cost are visible directly in IFS Loops Studio, scoped per tenant and per workspace, without needing a separate reporting tool.
