Craig Ball published a post last week about adapting requests for production (RFPs) for the generative AI age, which is interesting in at least two respects.

In Craig’s post (Adapting Requests for Production for AI GLLM Assessment, available here on his excellent Ball in Your Court blog) Craig starts by introducing us to a new acronym I hadn’t seen before: Generative Large Language Models (GLLMs). I’ve seen GAI and LLM, but not the two of them somewhat combined like that. I’m tempted to propose yet another new acronym – Generative AI & Large Language, but I don’t have the GALL to do so. See what I did there? 😉

Regardless, Craig takes a well-established practice in discovery – preparing requests for production – and states that RFPs “must evolve to reflect the unique capabilities and limitations of AI systems. Traditional language in RFPs, which relies heavily on human intuition, needs to be adjusted to accommodate AI’s reliance on clear instructions, context, and precision.”

Craig also sets the stage by discussing effective AI prompts in eDiscovery, as follows:

Effective AI Prompts in Discovery

AI systems like GLLMs function best with well-structured prompts. In the context of discovery, this means adjusting RFPs to emphasize clarity, specificity, and relevance. The key elements for constructing effective AI prompts in legal discovery are:

1. Clarity and Specificity: Ambiguity can cause AI systems to miss important documents or misclassify irrelevant ones. Specific requests guide the AI more effectively.
2. Contextual Guidance: AI relies on context to assess relevance. Providing additional background or specifying the purpose of certain requests helps refine the search.
3. Keyword Precision: GLLMs rely on keywords to understand and evaluate document content. Choosing precise terms helps reduce the retrieval of irrelevant documents.
4. Examples: AI systems can better identify relevant documents if examples are provided within the RFP, as they offer patterns for the system to follow.

Incorporating these principles into RFPs ensures that AI models can make the most accurate assessments during document review.

Craig then proceeds to provide an example for adapting requests for production using business dispute and tort claims, where he takes traditional RFP requests, adapts them for GLLM, and explains how the adaptation can address shortcomings in the traditional requests and lead to improved requests tailored for GLLM.

It’s a terrific walk-through of how legal professionals need to reconsider how to approach RFPs to take advantage of GLLM technology today. Check it out here!

I said that Craig’s post was interesting in at least two respects. I’ll address the other one this afternoon!

So, what do you think? Is your organization re-evaluating how it handles RFPs in light of generative AI? Please share any comments you might have or if you’d like to know more about a particular topic.

Image created using ChatGPT 4o, using the term “robot lawyer working at a computer on discovery requests”.

Disclaimer: The views represented herein are exclusively the views of the authors and speakers themselves, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.