> ## Documentation Index > Fetch the complete documentation index at: https://docs.weaveos.com/llms.txt > Use this file to discover all available pages before exploring further. # AI > Track AI coding tool usage, spend, and output for Claude Code, Cursor, GitHub Copilot, Codex, and more, by tool, team, and engineer, including AI cost per output. The AI report shows how your engineers use AI coding tools, what those tools cost, and how much code output they produce, broken down by tool, team, and engineer. It covers the AI tools you [connect to Weave](/ai-tools/overview), such as Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, Amazon Q, and Devin, plus tools Weave detects automatically, such as the AI code reviewers CodeRabbit and Greptile. Open it from **AI** in the sidebar, where it starts on the **Overview** tab. ## Who can see it? Anyone with the **Team lead**, **Manager**, or **Admin** role can access the AI report. Its data follows your [report visibility](/settings/report-visibility) settings, so by default a team lead sees the teams they lead and those teams' members. The **Compute** tab only appears for roles with **Organization metrics** access, which managers and admins have by default. ## Sections The report is split into tabs: **Overview**, **ROI**, **Observability**, **Code review**, **Models**, **Tools**, **Skill library**, and **Compute**. Each tab has a [filter bar](/features/filters) for the date range and, depending on the tab, team, person, AI tool, and repository. Repository and project filters don't narrow AI spend. ### Overview A summary of AI spend and AI-attributed output for the selected period. * **AI output & spend**: AI output on the left axis and usage-based token spend on the right, for each period. Seat-based plan costs aren't included; **Cost by fidelity** on the **ROI** tab is the view with the full total. See [AI output attribution](/analysis/ai-output-attribution) for how output is attributed to AI. * **Cost per output over time**: AI tool cost, including prorated seat costs, divided by AI code output, for all tools and for each tool. The **Pre-AI cost per output** line shows the price of one unit of output before AI: one hour of expert engineering work at your hourly rate. Use the title dropdown to switch to **AI cost over time**, which shows spend by tool or by model. * **Cost per person**: each person's AI usage cost for the period, with their cost per output and how much of it is billed versus estimated. Click **View details** to see the usage rows behind a person's cost. * **Cost by tool**: **AI cost by tool** shows each tool's total cost, and **Cost per output by tool** compares tools on cost per unit of AI output, where lower is better. Flat-rate tools without an [included allowance](/metrics/ai-tool-costs#included-allowance-for-flat-rate-tools) show list-price consumption rather than plan cost. ### ROI The **ROI** (return on investment) tab shows where your total AI spend goes. **Cost by fidelity** splits AI spend, including seat cost, by how each dollar is sourced; **Team spend flow** shows how spend flows from your organization to its top teams; and **Projected annual AI spend** annualizes AI tool cost at the current spend rate. Admins can also upload a Copilot spend sheet or a ChatGPT Enterprise workspace report from the **Upload** menu. See [AI ROI](/reports/ai-roi). ### Observability Prompt quality, agent effectiveness, friction, and shipped work for AI agent sessions. * **Prompt analytics**: overall conversation quality on a 0 to 100 scale, with tabs that break conversations down by complexity, work type, domain, topics, effectiveness, and outcomes, and **Conversation prompt quality** for each engineer. See [conversation prompt quality](/metrics/conversation-prompt-quality). * **Developer AI effectiveness**: one row per engineer with sessions, autonomy, prompt quality, first-shot success, completion rate, friction rate, an overall effectiveness score, token efficiency, and cost efficiency. * Session charts: **Goals**, **Outcomes**, **Friction types & what helped**, **Languages**, **Time of day**, **Tool errors & shipped work**, **Parallel sessions**, **Response time**, **Steering lag**, and **Work type output**. Prompt analytics needs a connected AI tool. **Developer AI effectiveness** and the session charts need the [Weave plugin](/tutorials/weave-plugin-installation) for Claude Code, Cursor, GitHub Copilot, or Grok Build. ### Code review How AI tools review code, resolve comments, and introduce bugs. The tab covers review-only tools such as CodeRabbit, Greptile, and Cursor Bugbot, plus the review activity of Copilot, Codex, and Gemini Code Assist. * Summary tiles: **Recorded review-tool spend**, **Suggestions shipped**, **Cycles replaced**, **Review output**, and **\$ per cycle replaced**. * Charts by tool: **Code review output** (switchable to output per dollar), **Human review cycles replaced**, **AI comments addressed by authors**, **AI suggestions addressed (%)**, **Review cycles by AI tool**, and **Bugs per 1K AI LOC by tool**, which counts bugs attributed to AI-associated code per 1,000 AI lines of code (LOC). See [code review output](/metrics/code-review-output), [comment resolution](/metrics/comment-resolution), [review cycles](/metrics/review-cycles), and [bugs introduced](/metrics/bugs-introduced). ### Models **Model spend flow** shows how total AI spend breaks down across model providers and their top models. The **Model comparison** table compares each tool and model on sessions, average cost per session, total tokens, autonomy, first-shot success, token efficiency, average AI output per session, and AI [code turnover](/metrics/code-turnover). ### Tools A table of the AI tools that write code, such as Claude Code, Cursor, Copilot, Codex, and Devin, with each tool's **Output**, **Output / engineer**, **% of AI output**, **AI LOC**, **Cost**, **Bug ratio**, and **Feature ratio** for the period. Review-only tools appear on the **Code review** tab instead. Click a tool to open its own report, which adds **AI code vs. output over time**, **AI adoption over time**, **Agent autonomy**, **First-prompt success rate**, and lines of code modified with AI per engineer. ### Skill library Every skill, command, and built-in tool Weave detects across your organization, with prompt quality and invocation counts. **Skill session stats** shows how the sessions that used each skill performed, as a correlation rather than a measure of causal ROI. See [skill library](/reports/skill-library). For how effectively engineers work with AI, see [AI skills](/reports/ai-skills). ### Compute **Modal compute spend** shows organization-wide metered Modal usage, which you can filter by workspace, app or object, environment, and Modal tag, along with coverage and freshness, a metered breakdown, and monthly Modal billing. It needs a connected [Modal](/data-sources/modal) workspace, and the tab only appears for roles with **Organization metrics** access. ## Provider-specific notes Copilot usage comes through your [GitHub integration](/code-platforms/github). If GitHub reports that your organization has disabled Copilot Metrics API access, enable it by following GitHub's [Copilot policy documentation](https://docs.github.com/en/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization#enabling-copilot-features-in-your-organization). When GitHub returns per-user Copilot usage metrics for your organization, Weave attributes Copilot lines of code to each engineer whose GitHub account is linked. On days without per-user data, Weave falls back to totals for each team synced from GitHub, or else to an organization-wide total. Neither fallback is broken down by person. Copilot lines removed aren't counted. In the team and organization totals, GitHub reports Copilot Chat code insertions as a count rather than as lines, so Weave counts each insertion as 10 lines added. Once Copilot billing is connected, Copilot cost can be broken down per engineer from GitHub's billing usage report. See [GitHub Copilot](/ai-tools/copilot#cost-tracking) for how it's collected. The Sourcegraph usage CSV reports accepted characters rather than lines added or removed, so Weave counts Sourcegraph lines as additions only and converts characters to lines at 50 characters per line. ## Common questions ### Which AI coding tools does the AI report cover? The AI tools you connect to Weave, plus tools Weave detects automatically. That includes Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, Amazon Q, Kiro, Augment, Gemini Code Assist, Devin, and Sourcegraph, and AI code reviewers such as CodeRabbit, Greptile, and Cursor Bugbot. Tools that write code are listed on the **Tools** tab and review-only tools on the **Code review** tab. See [supported tools](/ai-tools/overview#supported-tools) for setup. ### Can I see AI usage per engineer and team? Yes. **Cost per person** on the **Overview** tab lists each person's AI usage cost and cost per output, **Developer AI effectiveness** on the **Observability** tab has a row per engineer, and each tool's report on the **Tools** tab ranks engineers by lines of code modified with AI. To focus on one team, add a team filter; **Team spend flow** on the **ROI** tab shows how AI spend splits across your top teams. ### How do I see AI cost per unit of output? Use **Cost per output over time** on the **Overview** tab. It divides AI tool cost, including prorated seat costs, by AI code output for all tools and for each tool, and compares the result with a **Pre-AI cost per output** line: one hour of expert engineering work at your hourly rate. **Cost per output by tool** compares tools over the whole period, and **Cost per person** shows each person's cost per output. Review-only tools are left out so they don't skew the ratio. ### Can I tell agent work from developer-assisted work? Yes. Weave labels each AI tool as foreground AI, which engineers work with directly (such as Claude Code, Cursor IDE, and Copilot), or background AI, which works on its own (such as Devin, Cursor Agent, Jules, and AI code reviewers); see [foreground vs background AI](/ai-tools/overview#foreground-vs-background-ai). Background agents such as Devin and Cursor Agent appear as their own rows on the **Tools** tab, and the **Background vs. foreground AI** chart, which you can add to a [custom dashboard](/features/custom-dashboards), splits AI lines of code between the two groups. For sessions captured by the Weave plugin, the **Autonomy** column in **Developer AI effectiveness** shows how autonomously each engineer's agent sessions ran. ### Does the AI report show which models engineers use? Yes. On the **Models** tab, **Model spend flow** breaks AI spend down by model provider and top models, and the **Model comparison** table compares each tool and model on sessions, cost, tokens, autonomy, first-shot success, token efficiency, output, and code turnover. Add a team or person filter to see the models one team or engineer uses. On the **Overview** tab, the **AI cost over time** view can also group spend **By model**. ### Does the AI report include AI code review tools? Yes. The **Code review** tab covers review-only tools such as CodeRabbit, Greptile, and Cursor Bugbot, plus the review activity of Copilot, Codex, and Gemini Code Assist. It shows recorded review-tool spend, suggestions that authors shipped, estimated human review cycles replaced, and cost per cycle replaced, then compares tools on review output, addressed comments, and review cycles. Review-only tools are kept off the **Tools** tab and out of cost per output, so they don't skew comparisons between tools that write code. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.