ClauseBuddy
Quality LibTruffle HuntSmart TemplatesDoc AnalysisCompareAdmin
  • Welcome!
  • Getting Started
    • Quick Start Videos
    • System Requirements
    • Installation
    • Accessing the app
    • Enterprise deployment
    • Logins
    • Frequently Asked Questions
    • Encountering problems?
    • Help & Support Center
  • Quality Library
    • Searching Clauses
      • Overview
      • Searching by keywords
      • Browsing Folders
      • Filtering clauses
      • Inspecting clauses
    • Using Clauses
      • Inserting clauses
      • Configuration
    • Drafting Clauses
      • Creating clauses
      • Drafting the body of a clause
      • Smart placeholders
    • Custom styling
      • ClauseBuddy layout structure
      • Heading pane
      • Body text pane
      • Document title pane
      • Template detection pane
    • FAQ
      • How to create a new folder when you add a new clause?
      • How do I fill out a placeholder when adding a clause to a document?
      • How do I change a folder name?
      • How can I change the location of a clause in the library?
      • How do I delete a folder?
      • What’s the difference between green and purple clauses?
      • Why are not all attributes visible as filters?
      • When do I apply a status to my clause instead of an attribute?
      • How can I create my own attributes?
      • What is the difference between the Quality Library and the Truffle Hunt?
      • How can I avoid duplicating clauses when adding to the library?
  • Inspiration
    • Introduction
    • Truffle Hunt: clauses
    • Truffle Hunt: documents
    • Managing Truffle Hunt baskets
    • Process results with AI
    • Compliance
    • Samples Hunt
    • AutoSuggest
    • FAQ
      • Samples Hunt
        • From which database does Samples Hunt get its info?
      • Truffle Hunt
        • Can ClauseBuddy read and retrieve clauses from scanned documents?
        • How do I go to the document containing the found clause?
        • What is the difference between the strict and non-strict option when searching for clauses?
        • What's the best way to search for clauses in Truffle Hunt?
        • Is a clause modification in Truffle Hunt permanent?
        • Can you search multiple baskets at once?
        • Can you edit properties of documents in bulk such as doc title or year?
        • Can I store multiple clauses from Truffle Hunt in the Quality Library at once?
        • Is there a quick way to upload an open document to Truffle Hunt?
        • How can I update party names in a clause without manually overwriting?
        • What happens when I upload a duplicate clause or duplicate document to Truffle Hunt?
      • AutoSuggest
  • Generative AI
    • Introduction to GenAI
    • Write & Rewrite
    • Smart Merge
    • Doc Chat
    • Multi-document Table
    • Semantic Search
    • Compose Document
    • Custom LLMs
    • FAQ
      • Doc Chat
      • Compose Document
      • Write & Rewrite
        • Where does the AI get its inspiration?
        • Can I train the AI to match our company's spelling and style?
        • Can I save frequently used prompts to apply them faster?
        • How do I write good AI prompts?
      • Summarise
  • Document Analysis
    • Definitions
    • Proofreading
    • Reviewing: introduction
    • Reviewing: building rules
    • Running reviews
    • Checklists
    • Bracketeer
    • FAQ
      • Proofreading
        • Can I add my own custom checks to Proofreading?
      • Definitions
      • Document Reviewing
        • How come the Review document feature is not visible in my overview?
        • What do I name my review category?
        • What exactly do the questions do and what are they for?
        • Do requirements within a review category affect each other?
  • Operations
    • Text Compare
    • Bulk Compare
    • Bulk Operations
    • Deep Compare
  • FAQ
    • Text Compare
    • Bulk Compare
    • Bulk Operations
  • Smart Templates
    • Quick Tutorial: Smart Templates
    • Smart Templates in depth
      • Highlighting Word documents
      • Creating cards and questions
      • Conditions for cards & questions
      • Conditional text
      • Conditional rows, columns, sections & blocks
      • Template settings
      • Sharing templates
      • Tips when using Word
      • Comparison with Clause9
      • Integrations
      • Bulk create
      • Advanced drafting techniques
    • FAQ
      • Why is it that some users cannot see the ‘Templates’ feature?
      • Are Templates cross-platform?
      • Can I insert conditional images?
      • How do I update a template?
      • Why does the interactive preview sometimes fail to show numbering correctly?
      • How can I make a clause with multiple paragraphs conditional more efficiently?
      • How can I change the type of a question when creating a Smart Template?
  • Administration
    • Preferences
    • Managing folders
    • Managing attributes
    • Managing users
    • Linked Accounts
    • Managing access-bundles
    • Write & Rewrite
    • Export templates
    • External subscriptions
    • Access Matrix
    • Consult ClauseBuddy Usage Statistics
    • FAQ
      • I lost my login code!
      • Can I set-up a personal library for an individual user?
      • How do I delete a user?
      • Can I give someone else access to the admin account?
      • If I add a subscription, can this person see it and is my subscription also added to him?
      • I have access to ClauseBuddy, do I also have access to Clause9?
      • Is there 2 factor authentication for ClauseBuddy?
      • Can we choose which LLM is applied in ClauseBuddy?
Powered by GitBook
On this page
  • Why should rules be explicitly specified?
  • 1. Limited information available publicly
  • 2. Internal rules
  • 3. Deal-specific information
  • 4. Building your knowledge
  • Scope of the legal documents
  • How does the reviewing module technically work?
  • Word of warning
Export as PDF
  1. Document Analysis

Reviewing: introduction

PreviousProofreadingNextReviewing: building rules

Last updated 3 months ago

Through the power Large Language Models (LLMs), ClauseBuddy allows you to review legal documents against pre-specified rules.

Why should rules be explicitly specified?

Taking into account the knowledge already baked into LLMs such as GPT, you may be wondering why you would need to still specify reviewing rules.

1. Limited information available publicly

A first reason is that LLMs are trained on information found on the public internet. Through months of training (digesting millions of web pages), they acquire knowledge about various domains of life — from biology to politics, sports and celebrities to legal information. Unfortunately, the legal information acquired by an LLM primarily consists of theoretical information, such as:

  • legislation, which is by definition public

  • case law, which is mostly public in most jurisdictions, even though a lot is also behind paywalls of publishers

  • limited legal doctrine, mostly in the form of blogs and newsletters from law firms, with a limited amount of publicly available in-depth articles.

What LLMs lack, however, is practical information on how to review contracts. As every legal expert knows, relatively little practical information on this topic is available in written form, let alone publicly available online. While a decent amount of tips & tricks are available for common contracts (such as NDAs), most practical information is:

  • orally communicated, learned "on the job" and taught by experienced by lawyers

  • found in small nuggets of wisdom spread across legal articles and books on specific types of contracts, almost always behind publisher paywalls

  • individually acquired through years of experience

LLMs have no access to this information, and will therefore have to be explicitly instructed on how to review contracts.

2. Internal rules

A second reason why the rules must be explicitly told, is that LLMs obviously have no access to your internal rules, i.e. mostly the written "playbooks" of legal departments in large organisations. However, in both law firms and in-house legal departments, there are also many unwritten rules on what you always or conditionally accept or reject.

Theoretically it would be possible to "feed" artificial intelligence a vast amount of examples documents (e.g., contracts with markup from both counterparties and internal experts). However, in order for the artificial intelligence to automatically deduct the internal rules of on the basis of this examples, it would require hundreds of relatively "clean" examples, which most legal teams simply do not have available. Furthermore, in practice, most examples are not "clean", in the sense that internal rules are frequently implicitly ignored in specific deals, for various non-obvious reasons (e.g., specific deal size, ignorance of the expert reviewing it, deviating instructions from management, etc.)

Even though many reviewing rules will be shared between legal teams, you will be surprised how many different approaches exist, particularly for the hotly debated areas (e.g., the liability limitation or notice period for a commercial deal). For law firms, many rules will obviously also differ between clients, types of clients and types of deals. For example, when negotiating with a large incumbent with significant market power in a certain sector, the position taken will be completely different then when negotiating with a small vendor.

3. Deal-specific information

A third reason why the rules must be explicitly conveyed to an LLM, is that it cannot read your mind. Similar to how a client or internal business user would explain various types of information to a legal expert, you must instruct the LLM on the type of deal, how management feels about this deal, how much bargaining power you have, what type of counterparty you are dealing with, which specific risks exist, etc.

This is the reason why "questions" can be asked in ClauseBuddy's reviewing conditions. Those questions will be asked to the end-user, and the answers will be submitted to the LLM, so it can do a better reviewing job.

4. Building your knowledge

A last reason why it's a good idea to store internal rules in ClauseBuddy, is that it can serve as an alternative form of "playbook" for legal teams. ClauseBuddy is not intended to replace your formal playbook — so don't throw it out yet — but introducing automated legal reviews through ClauseBuddy can be a good moment to reflect on your internal rules.

You may be surprised how subtle some rules are, and how different colleagues will have different answers to the same legal question. Any information you store in ClauseBuddy's reviewing rules will therefore help in managing your internal knowledge, and will thus help in getting better uniformity across your team, accelerating the onboarding of new colleagues, and preventing knowledge drain when legal experts leave your team.


Scope of the legal documents

ClauseBuddy's reviewing module is primarily targeted at contracts, so in this manual we also talk primarily about contracts. However, there are no hard constraints that would prevent it from also applying to various other documents, such as memos, letters and submission forms in DOCX format.

How does the reviewing module technically work?

Even though LLMs often feel like magic, we want to de-mystify the way the reviewing module operates behind-the-scenes. It is important to understand this, because it will allow you to write better rules.

When you ask ClauseBuddy to review a document, it will first split your Word-document into individual pieces (paragraphs & clauses). Next, ClauseBuddy will compile all your rules into optimised textual content, through clever prompt-engineering.

The paragraphs & clauses and compiled rules are then together fed to the LLM, with the request to go through the document, and cross-check each applicable rule (i.e., a rule for which the condition is met). The LLM will then send back its findings, together with references to the relevant clauses. ClauseBuddy will then present these findings to the end-user.

The LLM is not "trained" on your reviewing rules, in the sense that it would store your rules in its permanent memory. Instead, the LLM will only temporarily store these rules (and the contents of your documents) in its memory during the few seconds that it is processing your request. Afterwards, it will immediately and completely forget what you fed it with.

Word of warning

You should be aware that document review through LLMs is very new territory, and that it's really stretching the limits of what today's Large Language Model is capable of.

At this moment, you should primarily consider it to be reviewing support, to help you get a first impression of your document, and automate some mundane aspects of the reviewing process.

In other words: do not blindly trust the output of the document reviewing process, no matter how detailed you make your rules.

It is probably also not a good idea to make the reviewing module available to users that cannot assess the legal merits of a user (such as most business users). Except for documents where the stakes are very low (e.g., a standard NDA for a low-value, low-risk contract), the risk associated with mistakes by the LLM are probably too high for most legal experts' appetite, or you really get the feeling that the LLM truly understands the rules and applies them in a pretty good manner.

The good news is that this performance will automatically improve over time, when improved engines appear on the market.

After all, ClauseBuddy offers the to review & rewrite your documents completely automatically. And, unlike all competing products on the market, the styling of your document will be left intact thanks to ClauseBuddy's layout-awareness...

So don't worry about the confidentiality of using the LLMs, as .

explained elsewhere
AutoCheck functionality