Craig Ball says that if you’re drafting RFPs for robots to read, then you should write them with the robots in mind. Can’t argue with that!

Craig’s latest post titled (wait for it!) Drafting RFPs for Robots to Read (available here) reminds us that he was talking about this idea two years ago: that if the other side is going to hand your requests for production to a large language model and let the machine decide what’s responsive, then let’s draft those requests with the machine in mind. Two years on, it’s no longer something to merely think about; producing parties are ceding first-pass relevance review to LLMs.  The request in front of the model is now a prompt whether we know it or not. So, make it your own.

If you want your opponent’s AI to find what you need, then you have to tell it how to discriminate because it doesn’t know all the nuances that a human reviewer does.

As Craig notes, the Federal Rules are on your side here. “FRCP Rule 34(b)(1)(A) requires that a request ‘describe with reasonable particularity each item or category of items to be inspected.’ Particularity and prompt-craft pull on the same oar: both esteem the concrete over the conclusory. An AI-aware request isn’t a departure from Rule 34; it’s Rule 34 taken seriously by a lawyer who recognizes a model is on the other end.”

Of course, staying inside the guardrails is key. Craig points out these cautions:

• “[A]n AI-aware request steers relevance and particularity; it does not dictate the responding party’s platform. Write the request to tell the model, any model, what responsiveness looks like. Don’t write it so as to effectively tell opposing counsel which model to choose or how to configure it. The former is advocacy and fair game. The latter invites a well-founded objection.”
• “[P]air concrete guidance with a stated purpose and, okay, keep your cherished ‘including but not limited to,’ so your examples instruct the model without unduly shrinking the scope.”
• The decision in Conservation Law Foundation, Inc. v. Shell Oil Co. (where Connecticut Magistrate Judge Thomas O. Farrish “ordered production of the prompts an expert used to drive an AI tool, treating them as fair game for discovery into methodology”) “signals that courts have started to regard AI prompts as part of the discovery record. The prompt-craft we bring to our requests and the prompts our adversaries feed their review platforms are drifting toward daylight.”

Craig then proceeds to walk through an example using “a matter everyone remembers” – the Dominion Voting Systems’ defamation suit against Fox News. Craig provides both an example of a “conventional, human-oriented request in that case” and a rewritten request that “a reviewer will be sorely tempted to paste straight into a review tool”. I won’t steal his thunder – check out his post here!

If you’re drafting RFPs for robots to read anyway, you might as well write them with the robots in mind. Makes perfect sense.

When I started using AI to create images for blog posts and adopted the robot theme that I use for most of them, Craig famously said “enough with the robots”. Now that he’s referring to “robots”, I’m glad he’s seeing it my way! The robot graphic above is for you, Craig! 🤣

So, what do you think? Do you feel you’re drafting RFPs for robots to read? Please share any comments you might have or if you’d like to know more about a particular topic.

Image created using DALL-E-3, using the term “robot lawyer wearing a suit writing a request to opposing counsel”.

Disclaimer: The views represented herein are exclusively the views of the author, 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.