How to turn precedents into action within Microsoft Word

What is Document Memory?

Document Memory transforms how you interact with your contract repository by bringing enhanced AI-powered search capabilities to Robin's Word Add-in. This feature allows you to ask natural language questions about your contracts directly within Microsoft Word and receive comprehensive insights with specific citations to source documents. Unlike traditional search methods, Document Memory analyses the actual content of agreements, helping you synthesise provisions across your entire contract portfolio within Robin. This enables legal teams to make informed decisions during contract review without ever leaving your document.

Please note: Document Memory is currently in beta and only available to a limited group of customers. While powerful, all responses should be verified against source documents as we continue to improve this functionality.

What is Draft and Edit Mode?

Draft and Edit Mode are powerful new capabilities that enhance how you interact with Robin AI in the Word Add-in. These modes transform the assistant from an advisor to an active collaborator in your contract drafting and revision process.

Draft Mode allows you to generate new contract language directly in your document. With a simple prompt, Robin can create entire clauses, paragraphs, or sections based on your specifications and organisational precedent. This eliminates the need to copy-paste from the chat into your document, streamlining the drafting process significantly.

‍

Edit Mode enables Robin to directly modify existing text in your document. When you highlight a clause or section that needs improvement, Robin can rewrite, strengthen, or simplify the language without requiring you to manually implement the changes. This is particularly valuable when harmonising counterparty language with your preferred terms or fixing problematic provisions.

Both modes maintain your full control over the document while significantly accelerating the drafting and revision process, allowing you to focus on strategic decisions rather than routine language crafting.

‍

Effective Question Types for Contract Review

Comparing Your Current Document with Past Agreements

Benchmark individual clauses against your organisation's historical agreements to identify where they fall on the spectrum of previously negotiated terms.

Example Prompt: "How does this indemnification clause compare to similar provisions in our other vendor agreements? Are there any terms that deviate from our standard position?"

Analysing Redlines Against Historical Positions

Use Case: Evaluate whether proposed changes represent a departure from historically accepted terms with specific counterparties or for similar agreement types.

Example Prompt: "Are the redlines made to this payment terms section in line with what we've previously agreed to with tech vendors? What's standard for us in similar agreements?"

Drafting New Clauses Based on Precedent

Use Case: Create new contract provisions that align with your precedents without searching through multiple documents.

Example Prompt: "I need to draft a force majeure clause for this agreement. Can you suggest appropriate language based on our standard approach in similar contracts?"

Optimise Mark-up with Edit Mode

Use Case: Refine existing contract language to better align with your organisation's positions, remove ambiguities, or shift the balance of terms in your favour.

Example Prompt: "Cap our liability at fees paid in the last 12 months and make minor edits to ensure alignment with our Template MSA agreement."

‍

Prompting Tips for Better Results

Specifying Context

Provide clear context about your current document and what you're trying to accomplish. For example, "How does this liability cap compare to what we've accepted in similar software licensing agreements?"

Breaking Down Complex Reviews

Rather than asking for a comprehensive analysis of an entire agreement, focus on specific sections or clauses. This produces more detailed and accurate responses. For example, instead of "Review this entire contract," try "Analyse the intellectual property provisions in this agreement compared to our standard position."

Requesting Specific Outputs

Clarify what type of analysis you need: comparison, risk assessment, drafting suggestions, or historical context. For example: "Suggest edits to strengthen this limitation of liability clause based on more protective versions we've used in the past."

‍

Troubleshooting

Unclear or Incomplete Responses

If Document Memory provides an answer that seems incomplete or unclear, try rephrasing your question to be more specific. You can also break complex questions into simpler components and ask them sequentially.

Citation Issues

If citations don't open correctly or direct you to unexpected locations, this may be due to permission settings or document access limitations. Ensure that all referenced documents are properly uploaded to your Robin repository and that you have appropriate access permissions.

Clearing Chat

If you encounter any unexpected behaviour, try clearing the Word Add-in chat by pressing the three dots in the top right.

Verification Reminder

Remember that while Document Memory is powerful, it's essential to verify all AI-generated insights against the original source documents. The technology continues to improve, but human oversight remains crucial, especially for high-stakes contract negotiations.

‍