Documentation Analytics: How to Improve Your Docs with DocStar

DocStar tracks how readers use your published docs: which pages they read, whether each one helped, and where they came from. With DocStar you can hand that data to your AI coding agent, ask it to find the pages that are failing readers, and get fixes back as drafts you review. This guide shows the full workflow, from connecting your agent to a monthly docs check-up that keeps working after the first pass.

Every DocStar collection has its own Analytics dashboard. There's nothing to install and no script to add. Publish a page and DocStar starts counting.

The top of the dashboard shows collection totals: Total Reads, Total Pages, Positive Feedback, Negative Feedback, Total UTM Counts and Total Feedback. You can filter by All Time, Last Month, Last Week or a custom range (custom ranges are rounded to full Monday-to-Sunday weeks), and by live or unpublished pages. The full reference is in our Analytics help page.

Every published page and API endpoint shows Was this helpful? at the bottom. Yes counts as positive. No opens a short form, "Sorry to hear that. What can we do better?", where the reader writes a comment and can leave an email address. Readers don't need an account, and feedback is on by default. See Reader Feedback for the details.

When someone opens a published page from a link with query parameters, such as ?utm_source=newsletter&utm_campaign=june-launch, DocStar records them. Any parameters count, not only utm_ ones, and a repeat visit with the same parameters in the same browser session is counted once. DocStar also tags outbound links: when a reader clicks from your docs to your main domain (for example from docs.example.com to example.com/pricing), it adds utm_source with the docs page URL, so your website analytics show which docs page sent the visitor.

Most teams have some numbers about their docs. Few act on them. Reading a dashboard, cross-checking comments against the page, and then rewriting the page is slow work that loses to every other priority.

DocStar changes who does the slow part. The same data the dashboard shows is available through the DocStar API, including per-page analytics and a collection's reader feedback with weekly Yes and No counts and the comments. An AI agent connected to DocStar can read all of it, open the pages, and draft the fixes. Your job becomes the part that needs a person: deciding what's right.

This is the main workflow we recommend. It takes one connection and one prompt.

Add DocStar to Claude Code, Cursor, Codex or another assistant. If DocStar is in your assistant's connector directory, connect it from there. Otherwise, add it as a custom remote MCP server with this URL:

https://mcp.docstar.io/mcp

The first time the agent needs your workspace, you sign in to DocStar in your browser. There's no API key to copy. The agent works only with the workspaces and collections your account can access, with your permissions. Full steps are in Connect Your AI Assistant.

Paste something like this, changing the collection name:

Use the DocStar MCP. In our "Help Docs" collection, pull the last 4 weeks of reader feedback and page analytics. Rank pages by reads and No votes, and read every comment. For the top 5 problem pages, open the page, explain what readers are missing, and draft a fix. Turn questions that keep coming up into pending FAQs. Show me your plan before you change anything, save every edit as a draft, and don't publish.

With that prompt, the agent:

1. Finds the collection in your workspace and lists its pages.

2. Reads the numbers. It pulls reader feedback (Yes and No counts by week, plus comments) and page analytics (reads by week, UTM records).

3. Prioritizes. It follows the same advice we give people: a popular page with many No votes comes first.

4. Reads the comments against the page. Comments often point to a missing step, an outdated screenshot or an unclear term, and the agent can check the current page text to confirm.

5. Proposes a plan and waits for your OK. The agent asks before it changes anything.

6. Drafts the fixes. Rewrites go in as drafts, and repeated questions become pending FAQs that show up on the right pages once approved.

[Screenshot: Coding agent showing its docs-review plan built from DocStar feedback]

Every change the agent makes is saved as a draft. Nothing reaches your live docs until it is published, so readers keep seeing the current version while you review. Open the drafts in DocStar's editor, adjust anything you like, and publish, or tell the agent which pages to publish for you.

The agent handles the reading, matching and drafting. A few calls belong to a person, and we built DocStar so they stay with you:

• Judgment on fixes. A comment may ask for something you don't support. You decide whether the page should explain it, or not promise it at all.

• What stays private. Workarounds, pricing exceptions and internal details shouldn't land in public docs because one reader asked.

• Tone and naming. You keep the voice of your docs consistent.

• Replying to readers. If a reader left an email, follow up and let them know you fixed it. That small step builds a lot of trust.

Analytics isn't only about fixing confusing pages. Two more prompts we find useful:

• Low SEO scores. Sort by SEO Score in the dashboard, then ask the agent to "rewrite the titles and meta descriptions for these pages so they match what people search for, as drafts".

• Which channels work. Add UTM parameters to the links you share in emails, release notes, social posts and in-app help. Then ask the agent to "summarize last month's UTM sources by page and tell me which channels bring readers to our setup guides".

If your docs live on a custom domain, the same analytics apply. Our guide on launching a help center on your own domain covers that setup.

A single cleanup helps for a month. A habit helps for good. With DocStar, keeping docs healthy is a routine your agent runs, not a project.

• Monthly check-up. Re-run the prompt each month with "compare with last month and tell me whether No votes on the pages we fixed went down". This is our "fix and republish, then watch the negative count" advice, done for you.

• After each release. When your code changes, ask the agent: "Read what changed in this release, find the DocStar pages it affects, and update them as drafts." It updates the docs before readers find the gap.

• FAQs from feedback. Repeat questions in comments become pending FAQs you approve, the same loop we describe in How to Reduce Support Tickets with DocStar FAQs and AI.

You can do the same review by hand. Open a collection and click Analytics in the left sidebar. Click the Negative Feedback card to show only pages with No votes, sort by Reads, and click a page's Feedback count to read the comments. You can also click the viewed count in any page's header to see its views, UTM sources and feedback while you edit. To hide the feedback widget, turn off Feedback under Settings > Theme & Customization.

• Analytics in the same place as the docs. Reads, feedback, SEO scores and UTM sources sit next to the pages, FAQs and changelog they describe. No separate analytics tool to wire up.

• Feedback on every page and endpoint. Help articles and API reference pages both collect Yes/No votes and comments.

• Agent-ready by design. The DocStar MCP lets Claude Code, Cursor or Codex read your analytics and draft the fixes, with browser sign-in and your own permissions.

• Safe by default. Agent edits are drafts, the agent asks before changing anything, and nothing goes live until it's published.

• One workspace for everything. API docs, help docs, FAQs, changelog and blog, each with its own MCP server for your users' AI assistants.

Do I need to install anything to get analytics in DocStar? No. Every collection has an Analytics dashboard, and reads, feedback and UTM visits are recorded once pages are published.

Do readers need an account to leave feedback? No. Anyone can click Yes or No. A No opens a short comment form, and the reader can add an email address if they want a reply.

Can my AI agent publish the fixes itself? Only if you ask it to. By default every agent edit is saved as a draft, the agent asks before it changes anything, and you decide what to publish.

Does feedback work on API reference pages? Yes. Feedback is counted per page for both pages and API endpoints.

Can I turn the feedback widget off? Yes. In the collection's Settings, go to Theme & Customization, turn off Feedback and save.

Your docs already know which pages are failing readers. With DocStar, your AI agent reads the signals and drafts the fixes, and you make the final call. Get started free and connect your agent to DocStar in a few minutes.