Skip to main content
openai tutorialOpenAI tutorial

Tutorial 04: Using Custom GPTs for Matter Management (OpenAI)

Learn how to create persistent legal workspaces with Custom GPTs, organize matters, write custom instructions, and manage client confidentiality effectively.

Learning Objectives

By the end of this tutorial, you will:

  • Understand how Custom GPTs create persistent legal workspaces
  • Set up Custom GPTs for different practice areas and matters
  • Write effective custom instructions (your digital playbook)
  • Manage client confidentiality with GPT organization
  • Organize in-house legal departments using Custom GPTs
  • Implement case prioritization and resource allocation
  • Conduct matter briefings and team handoffs
  • Optimize document organization and naming conventions

Time Required: 45 minutes | Level: Beginner | No technical skills required


Understanding Matter Workspaces

What Are Matter Workspaces in OpenAI?

With ChatGPT, you achieve matter-specific workspaces using:

  • Custom GPTs: Persistent instructions and knowledge files per matter or practice area
  • Knowledge Files: Documents ChatGPT can reference within a GPT
  • Conversation History: Past discussions within each chat thread
Without WorkspacesWith Custom GPTs
Re-explain context every conversationContext persists via instructions and knowledge
Re-upload documents repeatedlyDocuments available in GPT knowledge base
Inconsistent advice across sessionsConsistent playbook applied
No separation between mattersClean matter boundaries
Risk of cross-contaminationIsolated workspaces per GPT

Custom GPTs vs. Harvey Vault / Legora Workspace

Harvey Vault: Centralized document storage with AI analysis Legora Workspace: Collaborative environment with saved workflows ChatGPT Custom GPTs: Flexible workspace with full customization control

OpenAI's Advantage: You define exactly how ChatGPT should behave—no rigid templates or workflows imposed by the vendor.


Project Architecture for Law Firms

FIRM-WIDE RESOURCES
├── Contract Playbook - SaaS Vendor
├── Contract Playbook - SaaS Customer
├── Contract Playbook - NDAs
├── Litigation Checklist Templates
├── Legal Research - Employment Law
└── Legal Research - IP/Tech

CLIENT MATTERS
├── [Client A] - MSA Negotiation 2026
├── [Client A] - Employment Dispute
├── [Client B] - Series B Financing
├── [Client B] - IP Portfolio Review
└── [Client C] - M&A Due Diligence

INTERNAL
├── Marketing Content Review
├── Firm Policy Development
└── Training Materials

Confidentiality Best Practices

DO:

  • Use separate Custom GPTs for each client matter
  • Use client codes instead of names if concerned
  • Clear or archive GPT when matter closes
  • Control who has access to Team/Enterprise GPTs

DON'T:

  • Mix multiple clients in one GPT
  • Upload documents from different matters together
  • Leave sensitive GPTs accessible after matter ends
  • Use client names in GPT titles on shared accounts

Creating Your First Matter GPT

Step-by-Step Setup

Step 1: Create the Custom GPT

  1. Open ChatGPT (chat.openai.com or app)
  2. Go to Explore GPTs or Create
  3. Click "Create a GPT"
  4. Enter name: [ClientCode] - Matter Description

Step 2: Write Custom Instructions

Custom instructions tell ChatGPT how to behave in this workspace. They're your digital playbook.

Template for Contract Review GPT:

# GPT: [Client] Contract Review

## My Role
I am [outside counsel / in-house counsel] for [Client description].
My client is [description of business, risk tolerance, industry].

## ChatGPT's Role
You are a senior commercial attorney assisting with contract review.
Apply expertise in [relevant areas: tech licensing, healthcare
regulations, financial services, etc.].

## Standard Positions

### Liability
- ACCEPTABLE: Mutual cap at 12 months fees paid; uncapped for
  indemnification obligations, IP infringement, confidentiality breach
- MINIMUM: Cap at total contract value
- REJECT: Unlimited customer liability; cap below contract value

### Indemnification
- REQUIRED: Vendor indemnity for IP infringement, data breach,
  gross negligence, willful misconduct
- REQUIRED: Mutual indemnity for third-party claims from breach
- REJECT: One-sided indemnification favoring vendor only

### Data & Privacy
- REQUIRED: Customer owns all customer data
- REQUIRED: Vendor cannot use customer data except for service delivery
- REQUIRED: Data return/deletion upon termination
- REJECT: Vendor rights to aggregate or use data for any purpose

### Term & Termination
- PREFERRED: Month-to-month or annual with termination for convenience
- ACCEPTABLE: Multi-year with early termination option
- REQUIRE: Termination for material breach with cure period
- REJECT: Auto-renewal without easy cancellation

## Review Format

When reviewing contracts, always provide:
1. Executive summary (3-5 sentences)
2. Clause-by-clause analysis with traffic light ratings
3. Specific redline suggestions for concerning clauses
4. Questions for the business team
5. Negotiation priority ranking

Use these ratings:
- RED: Must change before signing
- YELLOW: Should negotiate, but not deal-breaker
- GREEN: Acceptable as-is

## Communication Style
- Be direct and practical
- Focus on business impact, not just legal technicalities
- Assume I'll share summaries with non-lawyers
- Flag areas needing attorney judgment (don't overreach)

Step 3: Upload Knowledge Base Documents

Add documents ChatGPT should reference:

  • Your firm's standard contract templates
  • Client's preferred positions document
  • Relevant regulatory guidance
  • Sample approved agreements for reference

Step 4: Test the GPT

Start a conversation and verify ChatGPT follows your instructions:

I'm starting a new contract review. Before I upload, confirm you
understand:
1. Who is my client?
2. What are our liability cap requirements?
3. What data provisions do we require?
4. How should you format your analysis?

Custom Instructions Templates

Template: Litigation Support GPT

# GPT: [Case Name] Litigation Support

## Case Overview
- Caption: [Full case caption]
- Court: [Court and jurisdiction]
- Our client: [Plaintiff/Defendant] [Client description]
- Opposing party: [Description]
- Claims: [Brief description of claims]
- Current phase: [Discovery/Motion practice/Trial prep]

## Key Facts (Update as case develops)
- [Fact 1]
- [Fact 2]
- [Fact 3]

## Our Theory of the Case
[Brief description of our narrative]

## Key Legal Issues
1. [Issue 1]: Our position is [X]
2. [Issue 2]: Our position is [Y]

## Helpful Documents in Knowledge Base
- Complaint
- Answer
- Key discovery responses
- Deposition excerpts
- Expert reports

## How ChatGPT Should Help
- When reviewing documents: Flag testimony/evidence supporting or
  hurting our theory
- When drafting: Maintain consistent voice, cite to record
- When researching: Focus on [jurisdiction] law, note circuit splits
- Always: Note privilege concerns, don't create work product without
  attorney direction

## Document Reference Format
When citing documents: [Document name, page X, lines Y-Z] or
[Exhibit #, Bates range]
# GPT: [Practice Area] Legal Research

## Scope
This project covers [practice area] issues in [jurisdiction(s)].
Primary focus areas:
- [Topic 1]
- [Topic 2]
- [Topic 3]

## Research Standards
- Prioritize: [Binding authority > Persuasive > Secondary]
- Key treatises to cite: [List]
- Preferred reporters: [List]
- Avoid: [Sources to avoid]

## Output Format
When providing research:
1. Issue statement
2. Brief answer (2-3 sentences)
3. Analysis with authority citations
4. Contrary authority and counterarguments
5. Practical implications
6. Recommended next steps

## Citation Format
Use Bluebook format. Example: Smith v. Jones, 123 F.3d 456, 460
(9th Cir. 2024)

## Important Caveats
- Always note when case law may have been superseded
- Flag circuit splits or unsettled law
- Distinguish between holdings and dicta
- Note if research requires updating via Westlaw/Lexis

## Knowledge Base Contents
- Key cases we rely on frequently
- Firm memos on recurring issues
- Regulatory guidance documents
- Practice-specific checklists

Template: Transaction Support GPT

# GPT: [Deal Name] Transaction Support

## Transaction Overview
- Type: [M&A / Financing / Joint Venture / etc.]
- Our client: [Buyer/Seller/Company/Investor]
- Counterparty: [Description]
- Target close date: [Date]
- Deal value: [Approximate]

## Key Documents (Upload to Knowledge Base)
- LOI/Term Sheet
- Draft definitive agreement
- Disclosure schedules
- Due diligence materials
- Deal checklist

## Our Priorities
1. [Top priority - e.g., minimize reps & warranties exposure]
2. [Second priority - e.g., favorable indemnification basket]
3. [Third priority - e.g., clean closing conditions]

## Red Lines (Cannot Concede)
- [Non-negotiable 1]
- [Non-negotiable 2]

## Acceptable Trade-offs
- [We can give X if we get Y]

## Drafting Guidelines
- Our client's defined term: "[Name]"
- Counterparty's defined term: "[Name]"
- Use [active/passive] voice for our representations
- Cross-reference format: [Section X.X]

## When Reviewing Drafts
1. Track changes from prior version
2. Flag new issues introduced
3. Confirm prior comments addressed
4. Note open business points requiring decision

For in-house counsel, organize Custom GPTs by function:

CORPORATE & GOVERNANCE
├── Board of Directors - Governance
├── Shareholder Matters
├── Corporate Records & Compliance
└── Entity Formation/Dissolution

BUSINESS OPERATIONS
├── Commercial Contracts
├── Vendor Management
├── Customer Agreements
└── Supplier Relationships

EMPLOYMENT & HR
├── Employment Policies
├── Dispute Management
├── Benefits & Compensation
└── Employee Handbook Review

REGULATORY & COMPLIANCE
├── Industry Regulations
├── Data Privacy & Security
├── Environmental Compliance
└── Regulatory Filings

IP & TECHNOLOGY
├── Patent Portfolio
├── Trademark Management
├── Software Licensing
└── Data Security Agreements

FINANCE & ACCOUNTING
├── Tax Matters
├── Financial Reporting
├── Accounting Standards
└── Financing Arrangements

Matter Intake Workflow

Create a Matter Intake GPT with these custom instructions:

# GPT: Matter Intake & Triage

## My Role
I am General Counsel or in-house attorney managing legal matters.
I need to quickly assess new matters for urgency, complexity, and resource needs.

## Intake Information Format
When I submit a new matter, include:
1. Requester/business unit
2. Matter type (contract, dispute, compliance, etc.)
3. Parties involved
4. Key deadline
5. Business impact description
6. Documents available
7. Prior related matters

## Your Role
Help me:
1. Classify matter type and complexity
2. Identify required expertise
3. Estimate timeline
4. Assess confidentiality requirements
5. Assign to appropriate GPT/team
6. Create matter file structure

## Recommended Responses
- Matter summary (2-3 sentences)
- Complexity rating: Low / Medium / High
- Estimated attorney hours required
- Key risks requiring attention
- Recommended team members
- Proposed GPT setup checklist

Business Partner Collaboration Framework

Add this guidance to relevant Custom GPTs:

## Business Partner Collaboration

### Communication Protocol
- Weekly status updates on open matters
- Bi-weekly strategy calls for major transactions
- Monthly summary report for all matters
- Escalation process for urgent items

### What to Escalate
- Potential disputes or claims
- Regulatory non-compliance issues
- Material contract negotiations
- Executive/Board-level decisions
- Litigation threats
- Third-party disputes

### Information Sharing
- Status summaries (business-friendly language)
- Risk assessments in business terms
- Cost-benefit analyses for decisions
- Timeline and resource needs

Board Reporting Template

Create a Board Reporting GPT with this structure:

# GPT: Board Legal Report

## Board-Level Summary Format

### Current Matters Status
- **Active Matters**: [Count by category]
- **Closed This Period**: [List with outcomes]
- **New Matters**: [Count and types]

### Key Risks & Issues
- [Risk 1]: Status, mitigation steps, escalation if needed
- [Risk 2]: Status, mitigation steps, escalation if needed

### Regulatory Compliance Status
- All required filings: [On track/At risk]
- Compliance reviews completed: [Yes/No]
- Outstanding regulatory actions: [List]

### Litigation Status
- Open cases: [Count and descriptions]
- Closed cases: [Count and outcomes]
- Insurance recovery status: [Details]

### Recommendations for Board Consideration
- [Board action 1]
- [Board action 2]

## Key Metrics
- Matter turnover time (average days to close)
- Outside counsel spend (YTD)
- Matters by type distribution
- Compliance audit results

Case Prioritization & Resource Allocation

Create a Matter Prioritization GPT with these instructions:

# GPT: Matter Priority & Resource Allocation

## Urgency/Importance Matrix

When analyzing matters, use this matrix:

### HIGH URGENCY + HIGH IMPORTANCE (Priority 1: Address Immediately)
- Imminent litigation deadlines
- Active regulatory investigations
- Critical deal closings
- Breach of contract claims
- Executive attention required

### HIGH URGENCY + LOWER IMPORTANCE (Priority 2: Schedule Soon)
- Non-critical compliance deadlines
- Standard transaction timing
- Routine contract negotiations
- Administrative requirements

### LOWER URGENCY + HIGH IMPORTANCE (Priority 3: Strategic Planning)
- Portfolio reviews (IP, contracts, policies)
- Preventive compliance updates
- Strategic negotiations
- Long-term planning matters

### LOWER URGENCY + LOWER IMPORTANCE (Priority 4: Defer or Delegate)
- Administrative updates
- Routine document reviews
- Low-value agreements
- Informational requests

## Prioritization Criteria

Rate each matter on:
1. **Deadline proximity** (days until critical event)
2. **Business impact** (revenue, risk, strategic value)
3. **Complexity** (hours required, expertise needed)
4. **Stakeholder pressure** (executive attention required)
5. **Dependency** (blocks other work)
6. **Resource availability** (skilled attorneys available)

## Output Format

For each matter, provide:
- Priority ranking (1-4)
- Recommended action timeline
- Required expertise level
- Estimated hours needed
- Key milestones and dates
- Resource recommendations
- Risk of delay

## Reprioritization Triggers

Alert me when:
- New deadline information received
- Business impact changes
- Regulatory escalation occurs
- Key facts change
- Resource availability shifts

Resource Allocation Workflow

Use this prompt in your prioritization GPT:

RESOURCE ALLOCATION PROMPT:

I have [X] attorneys available with skills in:
- [Skill 1]: [Name] - [Experience level]
- [Skill 2]: [Name] - [Experience level]
- [Skill 3]: [Name] - [Experience level]

Current open matters requiring allocation:
[Paste matter list with priority rankings]

Please recommend:
1. Assignment of matters to specific attorneys
2. Estimated capacity utilization
3. Likely bottlenecks
4. When we'll need outside counsel
5. Training/mentoring opportunities
6. Projected completion dates

Deadline Management System

Create a Deadline Tracker GPT:

# GPT: Legal Deadline Management

## Critical Deadlines Tracked

For each matter, monitor:
- Statutes of limitations
- Filing deadlines (court, regulatory)
- Notice requirements
- Response deadlines
- Approval deadlines
- Renewal deadlines
- Contract termination options

## Deadline Alert Protocol

Trigger alerts:
- 90 days before: For major milestones
- 30 days before: For upcoming deadlines
- 14 days before: For immediate deadlines
- 7 days before: For imminent actions
- 3 days before: For final reminders

## Missed Deadline Response
If a deadline is missed, immediately:
1. Assess malpractice implications
2. Notify insurance carrier if needed
3. Determine remediation options
4. Document mitigation steps
5. Prevent recurrence

## Monthly Deadline Review
Provide summary:
- Deadlines met this month: [Count]
- Upcoming deadlines (next 90 days): [List]
- At-risk deadlines: [List with action plans]

Briefing & Catch-Up Workflows

Case Briefing on Return from Absence

Create a Matter Briefing GPT for this use case:

# GPT: Case Briefing & Matter Catch-Up

## My Role
I am returning to a matter after [vacation/leave/other assignment].
I need a comprehensive but digestible briefing on current status.

## Briefing Information
- Matter name and matter code
- Last date I worked on this
- Current date
- Key documents available in knowledge base

## Your Role
Generate a catch-up briefing that includes:

### Executive Summary (1 paragraph)
- What has happened since last update
- Current critical issues
- What needs my immediate attention

### Timeline of Recent Activity
- Key events since [date]
- Dates and significance of each
- People involved
- Documents exchanged

### Current Status by Issue
For each major issue/claim:
- Current status
- Recent developments
- Next scheduled events/deadlines
- Our position/strategy
- Opposing position
- Open questions

### Document Summary
- New documents received (list by type)
- Drafts in progress
- Documents pending from other side
- Key evidence/documents (brief description)

### Team Updates
- Staff changes
- Meetings conducted
- External counsel activity
- Client communications

### Decisions Required
- What decisions must I make immediately?
- What options should I consider?
- What can wait until team meeting?

### Next Steps & Calendar
- Immediate actions (this week)
- Upcoming deadlines (next 30 days)
- Scheduled meetings/calls
- Documents due to other side

Matter Overview Generation

Use this prompt for any Custom GPT:

MATTER OVERVIEW PROMPT:

Please generate a comprehensive overview of this matter:

1. **One-Sentence Summary**: [What is this matter about?]

2. **Key Parties**:
   - Our client: [Description]
   - Opposing party/other key parties: [Description]

3. **Timeline**:
   - Matter opened: [Date]
   - Key milestones to date: [List]

4. **Current Phase**: [What stage is this in?]

5. **Critical Issues**:
   - Issue 1: [Our position, opposing position, risk]
   - Issue 2: [Our position, opposing position, risk]

6. **Document Inventory**:
   - Total documents: [Count]
   - By category: [List counts]

7. **Key Decisions Made**:
   - Decision 1: [What we decided and why]
   - Decision 2: [What we decided and why]

8. **Open Questions**:
   - Question 1: [What we need to determine]
   - Question 2: [What we need to determine]

9. **Next Steps**: [What happens next and when]

10. **Budget Status**: [Hours used, estimated remaining]

Status Summary Prompts

Create quick-reference briefing prompts:

QUICK STATUS SUMMARY (5 minutes):
- Matter: [Name]
- Status in one sentence: _______
- Key deadline: _______
- Critical action item: _______
- People who need to know: _______

WEEKLY STATUS FOR BUSINESS PARTNER:
- What we're doing this week: _______
- Expected outcomes: _______
- Risks to watch: _______
- Your input needed on: _______
- Timeline to next update: _______

EXECUTIVE BRIEF (For C-Suite):
- What's happening: [One paragraph]
- Why it matters: [Business impact]
- What we're doing: [Our strategy]
- What we need from you: [Required input/decisions]

Team Handoff Documentation

Use this template when transitioning a matter:

# GPT: Matter Handoff Documentation

## Handoff Information

### Matter Overview
- Matter name and code
- Client/parties involved
- Key timeframe and status
- Lead attorney (departing)
- New lead attorney
- Handoff date

### Knowledge Transfer Checklist

**Documents to Review**:
- Matter file index (complete list of documents)
- Recent correspondence (last 30 days)
- Current draft agreements
- Email communications with client
- Internal team memoranda
- Prior legal opinions/research

**Relationships to Understand**:
- Client contact persons and preferences
- Outside counsel relationships
- Opposing counsel dynamics
- Key business contacts
- Committee/Board liaisons

**Decisions & Strategy**:
- Strategic objectives
- Agreed positions on key issues
- Red lines and negotiation limits
- Prior failed negotiation attempts
- Client risk tolerance
- Timing constraints

**Upcoming Critical Events**:
- Deadlines (next 90 days)
- Scheduled meetings/depositions
- Expected deliverables
- Client communications planned
- Budget considerations

### New Lead Attorney Tasks
- [ ] Review all matter documents
- [ ] Meet with departing attorney
- [ ] Meet with client to establish relationship
- [ ] Update GPT instructions
- [ ] Schedule team kickoff call
- [ ] Review and update deadlines
- [ ] Confirm budget status

### Knowledge Base Refresh
- Ensure all current documents uploaded
- Remove outdated drafts/superseded versions
- Create organized folder structure
- Tag documents by issue/category
- Remove any conflicted materials

Document Organization & Naming Conventions

AI-Suggested Naming Conventions

Create a Document Organization GPT with this guidance:

# GPT: Document Organization & File Management

## Naming Convention Framework

### Standard Structure
[MATTER-CODE]_[DOCUMENT-TYPE]_[DATE]_[VERSION]_[SUBJECT]

### Examples
- ACME-2026_CONTRACT_020126_v3_SaaS-MSA-Redline
- WIDGET-LIT_DISCOVERY_020126_Interrogatories-Responses
- TECH-IP_MEMO_020126_Patent-Landscape-Analysis

### Document Type Codes
- CONTRACT: Agreements, amendments
- MEMO: Internal memoranda, opinions
- DISCOVERY: Interrogatory responses, document requests
- CORRESPONDENCE: Email, letters, notices
- RESEARCH: Legal research, case summaries
- BRIEF: Briefs, motions, pleadings
- REPORT: Expert reports, status reports
- ANALYSIS: Legal analysis, assessments
- CHECKLIST: Checklists, templates
- TEMPLATE: Standard form templates

### Version Control
- v1, v2, v3... for successive drafts
- FINAL for signed/approved version
- REDLINE if showing tracked changes
- CLEAN for final formatted document
- ARCHIVE for superseded versions

### Date Format
- Use MMDDYY format (020126 = February 1, 2026)
- Always use same format for sorting
- Reflects document creation/revision date

### Subject Line Best Practices
- Clear and specific (no abbreviations)
- Include key deal terms if relevant
- Capitalize main words
- Keep to reasonable length
- Use hyphens to separate concepts

Folder Structure Optimization

Transaction Folder Structure:

[Client-Matter-Name]/
├── 01_Core-Documents/
│   ├── LOI-Term-Sheet/
│   ├── Definitive-Agreement/
│   └── Schedules-Exhibits/
├── 02_Due-Diligence/
│   ├── Seller-Diligence/
│   ├── Buyer-Diligence/
│   └── Third-Party-Reports/
├── 03_Correspondence/
│   ├── Attorney-Communications/
│   ├── Business-Team-Updates/
│   └── Other-Party-Communications/
├── 04_Internal-Analysis/
│   ├── Risk-Assessments/
│   ├── Legal-Memos/
│   └── Deal-Points-Tracking/
└── 05_Closing-Documents/
    ├── Final-Agreements/
    ├── Conditions-Satisfied/
    └── Closing-Checklist/

Litigation Folder Structure:

[Case-Name]/
├── 01_Pleadings/
│   ├── Complaint-Answer/
│   ├── Motions/
│   └── Orders/
├── 02_Discovery/
│   ├── Document-Requests/
│   ├── Interrogatories/
│   ├── Depositions/
│   └── Responses/
├── 03_Evidence/
│   ├── Key-Documents/
│   ├── Exhibits/
│   └── Expert-Materials/
├── 04_Analysis/
│   ├── Legal-Research/
│   ├── Case-Strategy/
│   └── Timeline/
└── 05_Communications/
    ├── Opposing-Counsel/
    ├── Court-Filings/
    └── Client-Updates/

File Cleanup Workflows

Regular Cleanup Schedule:

Weekly:

  • Delete working drafts (keep final versions only)
  • Remove duplicate files
  • Archive superseded versions

Monthly:

  • Review and organize new documents
  • Update folder structure if needed
  • Remove access for departing team members
  • Archive closed items

Quarterly:

  • Full audit of matter folders
  • Identify and remove obsolete materials
  • Update document indexes
  • Verify naming consistency

Cleanup Prompts for ChatGPT:

FILE CLEANUP PROMPT:

I'm organizing my matter files. Please help me:

1. **Duplicate Detection**:
   - Identify files that appear to be duplicates
   - Suggest which version to keep
   - Recommend deletion candidates

2. **Organization Assessment**:
   - Are my folders logically structured?
   - Suggest improvements to folder hierarchy
   - Recommend new categories if needed

3. **Naming Consistency**:
   - Are my file names following consistent standards?
   - Suggest renaming for files that don't fit
   - Create new naming standard if needed

4. **Retention Assessment**:
   - Which files can be archived?
   - Which files are critical to keep accessible?
   - What retention period for each category?

5. **Version Control**:
   - Which draft versions can I safely delete?
   - How should I track revision history?
   - When to archive old versions?

Version Control Best Practices

# Version Control Protocol

## When to Create New Version
- Substantive content changes (new section, new language)
- New round of negotiation (track changes from counterparty)
- Internal revision for clarity/formatting
- Each round of client/stakeholder review

## When NOT to Create New Version
- Minor typo fixes
- Formatting changes only
- Metadata updates

## Version Naming
- Internal drafts: v1, v2, v3...
- Counterparty submission: [v#]_counterparty-draft
- With tracked changes: [v#]_tracked
- Final approved: [v#]_FINAL-[date]
- Executed: [v#]_EXECUTED-[date]

## Folder Organization for Versions
Keep current drafts in main folder
Move superseded versions to ARCHIVE subfolder
Maintain execution copies in FINAL/EXECUTED folder

## Comment/Tracking Standard
- Use track changes for all substantive revisions
- Include reviewer initials and date
- Summarize changes in cover email
- Note open issues or items for future rounds

Best Practices & Practical Exercises

Exercise 1: Set Up Your First GPT with Prioritization

Task: Create a Custom GPT for managing 3-5 active matters

Instructions:

  1. List your active matters
  2. Create one master GPT for matter management
  3. Add custom instructions including:
    • Prioritization matrix from above
    • Deadline tracking requirements
    • Resource allocation framework
  4. Test with prompt: "Rank my current matters by priority: [list matters]. Consider deadlines, business impact, and complexity."

Exercise 2: Create a Matter Briefing Template

Task: Build a catch-up brief for a real matter

Instructions:

  1. Select a matter you recently returned to
  2. Create a dedicated Briefing GPT
  3. Upload key documents to knowledge base
  4. Use the "Matter Briefing" prompt template
  5. Generate comprehensive catch-up brief
  6. Review for completeness and accuracy

Exercise 3: Organize Documents Using Naming Conventions

Task: Audit and reorganize a matter file

Instructions:

  1. Select a matter with multiple documents
  2. Create a list of current file names
  3. Propose new names using the framework above
  4. Create folder structure (transaction or litigation template)
  5. In ChatGPT, ask: "Help me organize these files according to [type] best practices. Here are my current files: [list]. Suggest naming and folder structure."
  6. Implement the recommended structure

Task: Create Custom GPTs matching your corporate structure

Instructions (for in-house counsel):

  1. Map your legal department functions
  2. Create Custom GPTs for each major function (governance, operations, compliance, IP, etc.)
  3. For each GPT, write custom instructions including:
    • Matter intake procedures
    • Business partner collaboration guidelines
    • Board reporting requirements
  4. Test with intake prompt: "New matter just came in: [description]. How should I handle this?"

Exercise 5: Implement Priority & Resource Allocation

Task: Set up your prioritization system

Instructions:

  1. List all current open matters
  2. Create Priority GPT with instructions from above
  3. Upload matter list to knowledge base
  4. Add attorney availability information
  5. Ask ChatGPT: "Please prioritize these matters and recommend resource allocation. Consider deadlines, complexity, business impact, and available capacity."
  6. Review recommendations and adjust as needed

Managing GPTs Over Time

Updating Custom Instructions

As matters evolve, update your instructions:

  • Add newly agreed terms as "acceptable"
  • Update case status and key facts
  • Add lessons learned from negotiations
  • Incorporate new team members' preferences

GPT Lifecycle

Phase 1: Setup (Matter opening)

  • Create GPT with detailed instructions
  • Upload initial documents
  • Test with calibration questions

Phase 2: Active Use (Matter ongoing)

  • Regular conversations within GPT
  • Upload new documents as received
  • Refine instructions based on feedback
  • Update deadline and priority tracking
  • Conduct periodic catch-up briefings

Phase 3: Archive (Matter closing)

  • Export any needed conversation logs
  • Document final outcomes in instructions
  • Remove or redact sensitive materials
  • Consider retention/deletion policy
  • Archive in matter management system

Phase 4: Reuse (Templates)

  • Create template from successful GPT
  • Strip client-specific information
  • Use as starting point for similar matters

Team Collaboration with ChatGPT

ChatGPT Team Features

With ChatGPT Team or Enterprise:

  • Share Custom GPTs across team members
  • Consistent instructions for practice groups
  • Admin controls for access management
  • Audit capabilities

Team plan pricing is set by OpenAI and may change. Verify current pricing on the official ChatGPT site.

Collaboration Best Practices

Firm-Wide Playbooks:

  • Create "template" GPTs for common work types
  • Partners/senior associates define standards
  • Associates use pre-configured GPTs
  • Ensures consistency across the team

Matter-Specific GPTs:

  • Lead attorney creates and owns GPT
  • Team members given access as needed
  • Single source of truth for matter context
  • Clear handoff when staffing changes

Comparing to Enterprise Features

Custom GPTs vs. Harvey Vault

FeatureChatGPT Custom GPTsHarvey Vault
Document storageIn-GPT knowledge baseCentralized vault
Custom instructionsFully customizablePre-built workflows
Search across docsWithin GPTEnterprise-wide
Setup timeMinutesDays (implementation)
CustomizationUnlimitedLimited to Harvey options

When Enterprise Tools Make Sense

Choose Harvey/Legora when you need:

  • Very large-scale bulk processing and cross-matter automation
  • Enterprise SSO and compliance
  • Cross-matter search and analytics
  • Vendor management of AI infrastructure
  • Pre-built integrations with your DMS

Choose Custom GPTs when you need:

  • Full control over AI behavior
  • Cost-effective solution for smaller teams
  • Rapid setup without IT involvement
  • Flexibility to experiment with workflows
  • Integration with your custom tools via API/function calling

Homework Before Tutorial 05

  1. Create 5 Custom GPTs:

    • One for a current matter
    • One for matter prioritization/intake
    • One for a practice area playbook
    • One for legal research in your specialty
    • One for document organization (if managing multiple matters)
  2. Write detailed custom instructions for each

  3. Upload 5+ documents to at least two GPT knowledge bases

  4. Test each GPT with real work tasks:

    • Matter prioritization analysis
    • Catch-up briefing
    • Document organization recommendations
    • Deadline tracking
  5. Iterate on instructions based on output quality

  6. Document your naming conventions and folder structures for future reference


Quick Reference: Custom Instruction Elements

# [GPT Name]

## Context
[Who you are, who client is, what this GPT is for]

## ChatGPT's Role
[What expertise to apply, what persona to adopt]

## Standard Positions
[Your acceptable/preferred/rejected terms for key issues]

## Output Format
[How ChatGPT should structure responses]

## Process Steps
[Workflow ChatGPT should follow]

## Communication Style
[Tone, audience, technical level]

## Caveats & Limitations
[What ChatGPT should flag or avoid]

## Knowledge Base Index
[What documents are available and when to use them]

Do This Now

  • Create a Custom GPT for one client matter with custom instructions
  • Upload key documents to the knowledge base
  • Test that ChatGPT follows your instructions before using on real work

Continue to Playbooks -> | Previous: Document Analysis



Sources

Additional Reading

On this page

1 Learning Objectives2 Understanding Matter Workspaces2.1 What Are Matter Workspaces in OpenAI?2.2 Why Matter Workspaces Matter for Legal Work2.3 Custom GPTs vs. Harvey Vault / Legora Workspace3 Project Architecture for Law Firms3.1 Recommended Structure3.2 Confidentiality Best Practices4 Creating Your First Matter GPT4.1 Step-by-Step Setup5 Custom Instructions Templates5.1 Template: Litigation Support GPT5.2 Template: Legal Research GPT5.3 Template: Transaction Support GPT6 In-House Legal Department Organization6.1 Setting Up GPTs for Corporate Legal Teams6.2 Matter Intake Workflow6.3 Business Partner Collaboration Framework6.4 Board Reporting Template7 Case Prioritization & Resource Allocation7.1 AI-Recommended Matter Priority Framework7.2 Resource Allocation Workflow7.3 Deadline Management System8 Briefing & Catch-Up Workflows8.1 Case Briefing on Return from Absence8.2 Matter Overview Generation8.3 Status Summary Prompts8.4 Team Handoff Documentation9 Document Organization & Naming Conventions9.1 AI-Suggested Naming Conventions9.2 Folder Structure Optimization9.3 File Cleanup Workflows9.4 Version Control Best Practices10 Best Practices & Practical Exercises10.1 Exercise 1: Set Up Your First GPT with Prioritization10.2 Exercise 2: Create a Matter Briefing Template10.3 Exercise 3: Organize Documents Using Naming Conventions10.4 Exercise 4: Design In-House Legal Department Organization10.5 Exercise 5: Implement Priority & Resource Allocation11 Managing GPTs Over Time11.1 Updating Custom Instructions11.2 GPT Lifecycle12 Team Collaboration with ChatGPT12.1 ChatGPT Team Features12.2 Collaboration Best Practices13 Comparing to Enterprise Features13.1 Custom GPTs vs. Harvey Vault13.2 When Enterprise Tools Make Sense14 Homework Before Tutorial 0515 Quick Reference: Custom Instruction Elements16 Do This Now17 Related family pages18 Sources19 Additional Reading