> For the complete documentation index, see [llms.txt](https://operations.clausebase.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://operations.clausebase.com/updates-september-2025/7-september-2025.md).
# 7 September 2025
## All-new, GenAI-driven Statistics module
New feature There's a brand new statistics module in ClauseBuddy. It allows you to ask questions about your usage statistics in natural language. Behind the scenes, GenAI will then reformulate your question and have your data analysed and shown on the screen.
On the opening page, you get some inspiration of what you can ask:
You can click any of these examples, or formulate your own prompt. The results you see, can also be presented as a list, or exported to Microsoft Excel.
{% hint style="info" %}
To be clear: the GenAI-data only reformulates your prompt, it never gets access to your actual data. We also took many different layers of precautions to avoid that the data is properly "sandboxed", so prompts can never deliver the wrong data.
{% endhint %}
## Save partial answers in Smart Templates & Clause9
New feature It's now possible for end-users to store the answers to a specific subsection ("card") of a questionnaire. Any number of answer-sets can be created per subsection; they are stored for individual users.
## @strikethrough, @subscript and @superscript special functions
New feature These new special-functions allow delineated parts of a text to have ~~strikethrough~~, subscript and superscript formatting. Combined with the conditionality-options offered by Smart Templates and Clause9, this allows to dynamically decide about the formatting of text-fragments.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://operations.clausebase.com/updates-september-2025/7-september-2025.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
