# How to Use the Insights Tab
## How the Insights Tab Works
The Insights tab is a right-hand side panel that gives you a deeper view of any article you're working on. It surfaces similar articles you may want to merge with, and scores your article's accessibility across readability, structure, and completeness — with actionable suggestions for improvement.
***
**1. Open the Insights Tab**
Open any article in Ariglad and click the **Insights** tab on the right-hand side of the editor.
The panel has two sections: **Merge Insights** and **Accessibility Insights**. Each loads independently — if one fails to compute, the other will still appear.
***
**2. Review Merge Insights**
Merge Insights shows up to **three similar articles** in your knowledge base that may overlap with the one you're editing. Each result includes:
* **Article title** — the name of the similar article
* **Similarity score** — how closely the two articles match (higher means more similar)
From here you can:
* **View the similar article** to compare content side-by-side
* **Copy content** from the similar article into the one you're working on
* **Create a merge approval** to combine the two articles into one
Use this to catch duplicate coverage early and keep your knowledge base lean.
***
**3. Review Accessibility Insights**
Accessibility Insights gives your article an **overall score from 0–100**, broken down into three weighted dimensions.
***
**Overall Score**
A weighted average of the three dimensions below:
* Readability (45%)
* Structure (35%)
* Completeness (20%)
Aim for 70 or higher for a polished, easy-to-consume article.
***
**Readability**
Measures how easy your article is to read. Includes:
* **Flesch Reading Ease** — a 0–100 score where higher means easier. Aim for 60+ (plain English).
* **Flesch-Kincaid Grade Level** — the U.S. school grade needed to understand the text. Aim for grade 8–10.
* **Average words per sentence** — sweet spot is 12–18 words.
* **Complex word ratio** — the percentage of words with three or more syllables. Lower is better; over 15% is flagged.
Very short articles are penalised here because readability metrics aren't meaningful with too little text.
***
**Structure**
Measures how well your article is organised for scanning. Looks at:
* **Headings** — whether the article uses any, and how many
* **Lists** — bullet or numbered lists
* **Images** — screenshots or illustrations
* **Code blocks** — for technical content
* **Long paragraphs** — paragraphs over 80 words are flagged as walls of text
Articles over 300 words are expected to have at least two headings; articles over 600 words benefit from more.
***
**Completeness**
Measures whether the article has the building blocks of a useful resource:
* **Title** — present and descriptive (3+ words is ideal)
* **Word count** — at least 50 words to be useful, 150+ for substance, 300+ for depth
* **Headings** — credited once there's enough content to structure
* **Links** — to related articles or external resources
***
**4. Apply the Suggestions**
Below the scores, Ariglad lists specific, actionable suggestions for improving the article. Each suggestion includes:
* **Dimension** — which score it affects (readability, structure, or completeness)
* **Severity** — high, medium, or low priority
* **Message** — what to change and why
Common suggestions include adding a title, expanding short content, simplifying long sentences, adding headings to break up walls of text, breaking up long paragraphs, and adding lists, images, or links where they'd help.
Some suggestions can be auto-fixed directly from the panel; others (like adding images or links) require manual edits.
***
**Tip**
Use Merge Insights early in your workflow — before investing time refining an article, check whether a similar one already exists. Then use Accessibility Insights as a final pass before publishing to catch readability and structure issues your eye might miss.
---
# Agent Instructions: 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://support.ariglad.com/interactive-modes/how-to-use-the-insights-tab.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.