Yesterday, I discussed Craig Ball’s new “Leery Lawyer’s Guide to AI”. Today, I’m using it to generate a meet-and-confer letter regarding an ESI protocol.

As discussed yesterday, Craig’s blog post (available here) also introduces a new guide titled “Practical Uses for AI and LLMs in Trial Practice” (available here). One of the sections of Craig’s guide discusses prompt examples for ChatGPT. One in particular caught my eye:

Discovery and ESI Protocols:

• Prompt Example: “Draft a meet-and-confer letter outlining an ESI protocol for a federal employment discrimination case. Address data sources, search terms, metadata fields, and custodians.”
• Application: Save time drafting initial versions of formal discovery documents and ESI agreements. Tip: you might try uploading my free primer on ESI Protocols to ChatGPT along with your prompt: http://www.craigball.com/ESIProtocol.pdf

So, I decided to try it. With Craig’s ESI protocol guide already in hand (I covered it two years ago), I uploaded that guide to ChatGPT and slightly adjusted the prompt he gave, as follows:

“Using this guide, draft a meet-and-confer letter outlining an ESI protocol for a federal employment discrimination case. Address data sources, search terms, metadata fields, and custodians.”

And this is the response I got back from ChatGPT:

“Here is a draft for a Meet-and-Confer Letter regarding an ESI protocol for a federal employment discrimination case. It incorporates key elements from the uploaded annotated guide:

[Your Firm’s Letterhead]

[Date]

[Opposing Counsel’s Name]
[Opposing Counsel’s Address]

RE: Meet-and-Confer on ESI Protocol in [Case Name, Docket Number]

Dear [Opposing Counsel’s Name],

We write pursuant to Rule 26(f) of the Federal Rules of Civil Procedure to propose a protocol for the discovery of electronically stored information (ESI) in this matter. This protocol aims to ensure that ESI discovery proceeds efficiently, cost-effectively, and in a manner consistent with the Federal Rules. Below, we outline key areas for discussion and agreement.

1. Data Sources

• Custodial Data: ESI from key custodians identified as likely to have relevant information, including [list roles, e.g., plaintiff’s manager, HR personnel].
• Non-Custodial Data: Relevant data sources such as shared drives, email archives, and database systems like payroll or performance review systems.
• Excluded Sources: Agreement to exclude transient data such as RAM, temporary internet files, or system logs.

2. Search Terms and Methodology

• Parties will collaboratively develop a set of search terms. Each side may propose terms based on their understanding of the case, subject to iterative refinement.
• To ensure proportionality, testing of search term efficacy will occur, with hit reports provided for transparency.
• If search terms yield excessive or irrelevant results, the parties will meet and confer to refine the terms.

3. Metadata Fields

The following metadata fields shall be provided for all produced documents:

• Custodian: Identifying the origin of the document.
• File Name: Original file name where collected.
• Date Sent/Received/Modified/Created: Date metadata associated with document activity.
• Subject/Title: Email subject line or document title.
• Hash Value: Ensuring deduplication accuracy.
• Parent-Child Relationships: Preservation of email threads and attachment relationships. Refer to Addendum A (attached) for a comprehensive metadata list.

4. Forms of Production

• Preferred Format: Documents will be produced in native format where feasible, with metadata intact. Exceptions include redacted documents, which will be produced as TIFF images with searchable text.
• Special Formats: Spreadsheets, databases, and presentations will be produced in native format due to their unique features.
• Color Documents: Any documents where color conveys information will be produced in color (e.g., as JPG or in native format).

5. Deduplication

• Deduplication will occur at a global level using MD5 or SHA-1 hash values. All deduplicated versions will be logged in the production’s metadata, including custodian details.

6. Privilege and Redaction

• Redacted documents will indicate redactions on their face and in metadata. A privilege log will accompany each production, excluding post-complaint communications with trial counsel.

7. eDiscovery Liaison

• Each party will designate an eDiscovery liaison to facilitate technical discussions and resolve disputes efficiently.

We suggest scheduling a call or meeting on [proposed dates] to discuss these points and finalize the protocol. Please provide any edits or additions to this proposal before our discussion.

We look forward to your response.

Sincerely,
[Your Name]
[Your Title]
[Your Firm]”

A bit sparse maybe, but not bad! It hits several of the main considerations, while addressing some of the concepts and preferences that Craig discusses in his ESI protocol guide (such as “Documents will be produced in native format where feasible, with metadata intact”).

The key is to understand the concepts delivered by ChatGPT which include the teachings from Craig’s ESI protocol guide. ChatGPT can help you draft work product for things like this, but you’ll still need to understand it or get help from your “geek” to have the discussion with opposing counsel.

Again, Craig’s guide has great tips for newbie lawyers, leery lawyers, overconfident lawyers (i.e., those who trust the AI too much) and more! Check out the post here and download the guide here!

So, what do you think? Do you need a guide for practical uses of AI for litigation and trial? Then check out Craig’s guide! And please share any comments you might have or if you’d like to know more about a particular topic.

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.