# Cost & Productivity Control LLM spend with model policy and autonomy defaults, and measure Droid's productivity impact with the measurement surfaces you already have. Measure Droid usage with the hosted Analytics dashboards, [OTEL metrics exported](/enterprise/telemetry) to your own observability stack, or the [Analytics API](/api-reference/analytics). Use these surfaces to control spend and measure what the spend produces. ## Cost management strategies LLM cost control is a combination of **model policy**, **usage patterns**, and **observability**. ### Constrain the model catalog Use org-level policies to limit which models are available. - Prefer smaller models for everyday tasks; reserve large models for complicated refactors or design work. - Disable experimental or high-cost models by default. - Enforce model choices per environment, such as cheaper models in CI. See [Models](/models) for the current model catalog. ### Tune autonomy and context usage Higher autonomy and larger context windows consume more tokens. - Set reasonable defaults for autonomy level and reasoning effort. - Use hooks to cap context size or block unnecessary large prompts. - Encourage teams to iterate with tighter scopes, such as specific directories instead of entire monorepos. ### Monitor activity and cost Combine hosted analytics with your own monitoring: - Feed [exported activity metrics](/enterprise/telemetry/data-reference), including tool invocations, code activity, and git activity, into your observability stack to build per-team and per-tool dashboards. - Use the [Analytics API](/api-reference/analytics) for token consumption and cost estimates, which are not exported as customer OTEL metrics. - Alert on unusual spikes and compare trends before and after policy changes. ### Track tool adoption In the current Analytics dashboard, Enterprise **Managers** and **Owners** can open **Tools** and select **Skills**, **MCP**, or **Slash commands** to see invocation trends, usage rankings, and per-user usage. MCP usage is grouped by server, not individual tool. **Inactive** means an item was observed in the 90-day window ending on the selected end date, with no recorded calls in the last 30 days. This is recorded usage, not an installed-tool inventory; missing telemetry does not prove non-use. Categories can overlap, so do not add their totals together. ## Measuring productivity impact Cost only matters in the context of outcomes. You can correlate Droid usage with **software delivery and quality metrics** you already track. Common approaches: - Build dashboards from exported activity metrics (files and lines modified, commits, pull requests, tool invocations) per team and repository. - Pull aggregated adoption and productivity signals from the [Analytics API](/api-reference/analytics) for leadership reporting. - Measure how often Droid is involved in changes that reduce incidents, resolve alerts, or improve test coverage. - Use [Agent Effectiveness](/agent-effectiveness/overview) to connect agent spend to cycle-time changes on the issues, projects, and pull requests it touched. Correlate these usage signals with delivery and quality metrics in your existing observability and analytics stack. Measure how much faster your organization ships with Factory. Query credits consumption, tool usage, and per-user productivity metrics. Export OTEL metrics to your own observability stack. Every metric and attribute available for your dashboards.