> For the complete documentation index, see [llms.txt](https://docs.hivel.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hivel.ai/ai-adoption/claude-console-analytics.md).
# Claude Console Analytics
The Claude Adoption feature in Hivel provides valuable insights into how your engineering teams are using Anthropic’s Claude Console. It tracks who is using Claude, how effectively they engage with its suggestions, and how that usage maps to real code delivery - helping you measure ROI and drive adoption across your organization.
Data shown includes only billed users and reflects activity/data until the previous day.
#### Summary Metrics
Three headline KPIs are displayed at the top of the Overview tab, giving an at-a-glance view of Claude engagement for the selected filters and date range:
| Total Active Users
71
Users with at least 1 token used
| Total Inactive Users
23
Users with zero token usage
| Total Cost
$12,699.5
Sum of AI-generated cost (Claude Code)
|
| --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |
#### Users Breakdown
The Users Breakdown chart segments all billed users into four behavioral categories based on their Claude token usage during the selected period. Users are classified dynamically using a percentile-based formula applied to token consumption - so segments adjust automatically as the date range or team filter changes.
| **Segment** | **Classification** | **Definition** |
| ----------------------- | ---------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
| **Power Users** | Top 25% by token usage (percentile ≥75%) | Top 25% of users by Claude token usage. Most deeply embedded in AI-assisted workflows. |
| **Steady Users** | 50th–75th percentile token usage | Regular Claude usage, within the 50-75th percentile. Reliable adopters with room to grow. |
| **Opportunistic Users** | <50th percentile, but >0 tokens | Occasional Claude usage, below the 50th percentile. Ad-hoc engagement; good candidates for targeted enablement. |
| **Inactive Users** | 0 tokens used in period | User who has a licence but has no Claude usage during the selected period. |
> *Clicking any segment in the chart opens a drilldown showing the list of users in that category and their individual token usage.*
#### Suggestions Acceptance
This section tracks the total number of times users have accepted AI-generated suggestions from Claude. It answers key questions like:
* How often are developers acting on what Claude proposes?
* Which interaction modes are seeing the most acceptance?
* Are acceptance rates changing over time, and if so, why?
#### Graph
Displayed as a line chart (or bar chart - toggle available) over the selected date range. The Y-axis shows Acceptance Rate (%) and the X-axis shows the date. Toggle between three modes using the buttons in the top-right corner of the chart:
| **Mode** | **Definition (on hover)** |
| -------------- | ---------------------------------------------------------------------------------- |
| **Edit** | Percentage of suggestions accepted while editing an existing code. |
| **Write** | Percentage of suggestions accepted while writing a new code. |
| **Multi-Edit** | Percentage of suggestions accepted while making multiple code changes in parallel. |
{% hint style="info" %}
**Formula:** Acceptance Rate = Accepted Suggestions ÷ Total Suggestions (per mode)
{% endhint %}
#### Commits & PRs Opened
This section correlates Claude usage with developer throughput. It answers the key question: in periods of high Claude usage, is developer throughput - measured by commits and pull requests - also higher? Use this chart to understand whether Claude adoption is positively impacting the pace at which developers ship code.
Compare the Commits volume against the Suggestions Acceptance and Tokens charts to see whether periods of higher Claude engagement correspond with higher delivery output.
#### LOC Added & Removed
Shows how many lines of code were added or removed by developers in a given period, allowing you to correlate code volume with Claude usage during that same period. If Claude usage is high, does code output also increase? This chart helps answer that question.
Use this alongside Commits & PRs to understand both the frequency and the scale of code changes relative to Claude activity.
#### User Tags
Each user row can carry one or more tags based on their activity profile. Tags appear on individual rows and are filterable at the top-right of the Usage table (Usage > Output · High Delivery · New User).
| **Tag** | **Definition** |
| ------------------ | ---------------------------------------------------------------------------- |
| **New User** | First Claude session occurred within the selected time range. |
| **High Delivery** | Users who are part of the top 25% by commits and pull requests created. |
| **Usage > Output** | High Claude activity compared to peers, with lower relative delivery output. |
Clicking a tag button at the top-right of the table filters the entire list to show only users matching that cohort. Multiple filters can be combined.
| Why this matters |
|---|
| Together, these metrics give you a complete picture of Claude’s impact - from who is genuinely engaged and how they are classified, to whether suggestions are trusted, to whether that trust is translating into real code delivery and at what cost. Use this data to make informed decisions about where to drive deeper adoption, where to provide additional training, and whether your Claude investment is delivering the productivity gains you expect. |
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.hivel.ai/ai-adoption/claude-console-analytics.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.