Skip to Content
GuidesCore Concepts

Core Concepts

Understand the key concepts behind Intentra CLI.

Events

An event is a single hook invocation from an AI tool. Each time you:

  • Send a message in Cursor chat
  • Request code completion
  • Run a Claude Code command
  • Execute a Gemini CLI prompt

…an event is captured.

Scans

A scan groups related events into a logical unit. For example:

  • A chat conversation with multiple back-and-forth messages = one scan
  • Code completion attempts while typing = one scan
  • Separate, unrelated prompts = multiple scans

Scans make it easier to understand your AI usage patterns.

Normalization

Different AI tools report data in different formats. Intentra normalizes all events to a unified schema:

ToolNative FormatNormalized
CursorinputTokens, outputTokenstokens.input, tokens.output
Claudeusage.input_tokenstokens.input, tokens.output
GeminitokenCounttokens.input, tokens.output

This allows consistent analysis across tools.

Patterns

Intentra detects usage patterns that might indicate issues:

  • Retry loops - Tool retries failed actions repeatedly
  • Token bloat - Excessive context sent to model
  • Timeout chains - Sequential timeouts wasting resources

Patterns are flagged on scans for review.

Local Buffer

All events are stored in a local SQLite buffer:

  • Works offline
  • No data leaves your machine by default
  • Fast queries for local analysis
  • Optional sync to remote server

Cost Estimation

Intentra estimates costs based on:

  • Token counts (input + output)
  • Model pricing (configurable)
  • Usage over time

Note: Estimates are approximate and may not match actual provider bills.