> For the complete documentation index, see [llms.txt](https://guide.allibee.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.allibee.ai/en/clm/ai-contract-review/playbook.md).

# AI Contract Review

### Key Summary

{% @arcade/embed flowId="rzbe97K9epPb4qF1IT1D" url="<https://app.arcade.software/share/rzbe97K9epPb4qF1IT1D>" %}

* The AI automatically summarizes the key points of the contract.
* The summary results allow you to quickly understand the key points of the contract.
* Click the \[Summarize Again] button to generate a new summary.

***

{% hint style="info" %}
\[Detailed Review] and \[Clause Improvement] are linked, allowing you to check and apply improvements directly during the clause review process.
{% endhint %}

### Detailed Review

{% @arcade/embed flowId="dCGy1z2zQ5sQYCL92EWs" url="<https://app.arcade.software/share/dCGy1z2zQ5sQYCL92EWs>" %}

* Select your Party's Position to review the contract based on the criteria for that role.
* The AI analyzes whether each clause meets the checklist criteria and provides the results.
* Tabs are separated by status, allowing you to view only unmet or only met clauses.
* Each review item is linked to its location in the contract body, so you can jump directly to the relevant clause to check and review the content.
* The review results are summarized in a Q\&A format, enabling you to quickly identify key issues.
* Notes on contract execution are also provided, which you can reference or use in practice.
* For clauses that do not meet the guidelines, click \[Edit] to go directly to the Clause Improvement screen.
* If a clause required by the guidelines is missing from the contract, it will also be marked as unmet, with a Q\&A-style explanation and notes on contract execution provided.
* You can choose to display or hide the location markers of review items in the contract body.
* To restart the review from the beginning, click the \[Regeneration] button.

***

### Clause Improvement

{% @arcade/embed flowId="D8soD7uuksUq5NQpLzsZ" url="<https://app.arcade.software/share/D8soD7uuksUq5NQpLzsZ>" %}

* You can review the AI-suggested Clause Improvements for unmet clauses based on the AI Contract Review results.
* The improvements are separated by clause for easier review.
* You can also view only the improved sentences without comparing them to the original clauses.
* Click the \[Reflect changes in the text] button to apply the AI-suggested improvements directly to the contract body.
* Click the \[Regeneration of proposals] button to receive new suggested revisions.
* Use \[Copy proposal] to easily copy and use the improvements.
* Click the \[Search for similar clauses] button to find and compare similar clauses from other contracts for reference.
* After applying the changes, click the \[Save new version] button to save the updated contract.

{% hint style="warning" %}
AI Contract Review requires AI credits.
{% endhint %}


---

# 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, and the optional `goal` query parameter:

```
GET https://guide.allibee.ai/en/clm/ai-contract-review/playbook.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.