Agent Usage & Credits

This document explains how usage is calculated inside the AI Agent.

All pricing is based on credits, and every credit corresponds to one tool call.

The Agent works by calling different internal tools to complete a user’s request. Each tool performs one action — like querying data, generating a visualization, or searching the web.

1 tool call = 1 credit
A typical question may trigger 3 to 5 tool calls, depending on complexity.

Type of tools

Tool Type	Description	Examples
Query Data	Fetching and transforming internal data	Metrics, breakdowns, comparisons
Visualization	Generating charts or plots	Bar, line, scatter, pie, etc.
Web Search	Benchmarking or live competitive research	Pricing pages, CPM averages, market trends
Image Analysis	Evaluating creative assets	Emotional tone, contrast, layout classification
Custom Tools	Anything built specifically for your workspace	Proprietary logic, external APIs, workflows

Examples

Example №1

Prompt: “Show me ROAS by campaign type over the last 90 days, and visualize it.”

This would typically include:

Tool Call 1: Query data
Tool Call 2: Transform data
Tool Call 3: Generate a chart

Total: 3 credits

Example №2

Prompt: “Find average CPM for B2B SaaS in the US and compare to my campaigns.”

Tool Call 1: Web search for CPM benchmark
Tool Call 2: Query internal campaign data
Tool Call 3: Merge and compare datasets
Tool Call 4: Visualize comparison

Total: 4 credits

Example №3

Prompt: “Which Facebook creatives had the highest CTR last month?”

Tool Call 1: Query ad performance data
Tool Call 2: Filter by platform and date
Tool Call 3: Rank by CTR
Tool Call 4: Visualize Data

Total: 4 credits

Tracking Usage

You can track and audit your usage at any time in the Settings → Usage section of the platform. This dashboard shows how many credits have been consumed, broken down by date range, tool type, and workspace.

For each workspace, you’ll see visual charts that reflect how usage is trending over time. You can also identify which users are generating the most tool calls, and which types of prompts are driving credit consumption.

The AI Agent’s usage model is simple: every tool call equals one credit. Most real-world questions involve multiple steps — querying data, transforming it, visualizing it, or enriching it with external context — and typically consume between 3 and 5 credits.