Skip to content

AI Telemetry

AI Telemetry captures usage data from AI coding tools across your engineering organization — token consumption, costs, session activity, and CapEx classification — without changing how engineers work.

What It Does

  • Automatic session capture from 9 supported tools
  • Token and cost tracking per engineer, team, and project
  • CapEx/R&D classification for tax relief reporting
  • Zero-config for engineers (CLI installer handles setup)

Supported Tools

ToolCollection MethodPrompt Capture
Claude CodeOTel (native)Opt-in (--prompts)
GitHub CopilotOTel (VS Code)Opt-in (--prompts)
CursorEditor hooksAlways on
WindsurfEditor hooksAlways on
Gemini CLIOTel (native)Opt-in (--prompts)
Codex CLIOTel (native)Opt-in (--prompts)
AiderOTelAlways on
Qwen CodeOTel (native)Opt-in (--prompts)
OpenCodeOTel (native)Always on

What Gets Tracked

For every AI coding session:

  • Token counts — input, output, and cache-read tokens per model
  • Cost — estimated USD cost based on provider pricing
  • Session metadata — duration, tool calls, files modified, lines added/removed
  • Git context — branch, repository, commit messages (when available)
  • Classification — project attribution and CapEx eligibility (automated)

WARNING

For Claude Code, Copilot Chat, Gemini CLI, Codex CLI, and Qwen Code, prompt capture is opt-in via the --prompts flag. For Cursor, Windsurf, Aider, and OpenCode, prompt content is captured by default when telemetry is configured.

How It Works

  1. Engineers install flowstate-telemetry CLI or configure their tool manually
  2. AI tool usage emits OpenTelemetry data to the Flowstate telemetry service
  3. Sessions are aggregated, classified (project + CapEx category), and stored
  4. Data appears in the Flowstate AI Workforce dashboard

Next Steps

Flowstate Documentation