Automating Demand Letter Generation: 91% Faster Drafting for Preferred Legal Group

Preferred Legal's paralegals spent up to 120 minutes per demand letter — manually parsing case files, identifying applicable claims, and populating templates. RTS Labs built an AI-powered Co-Pilot that cut drafting time to ~10 minutes, a 91% reduction, without adding headcount.

See How We Built It
Have a Similar Challenge?
logistics supply chain header
Case Study at a Glance
Client

Preferred Legal Group

Industry

Use Case

AI-Powered Demand Letter Automation

Tech Stack

OpenAI GPT-4o

AWS

React

Python

Time to Production
From brief to live deployment
0 weeks

Case Study

Jump To

Dealing with a similar challenge?

Our engineers will map your workflow and define a ship date in a 2-week Discovery Sprint.

Start a Conversation

Share

1. The Challenge

Preferred Legal Group handles thousands of personal injury and employment law cases annually across multiple states. Central to each case is a demand letter — a complex legal document that synthesizes case facts, applicable statutes, damage calculations, and legal arguments into a single, formatted deliverable. For years, this was entirely manual work.

Paralegals spent between 30 minutes and two hours on each letter, depending on experience level. With 500+ cases processed monthly, the firm was burning thousands of staff-hours on a task that followed predictable, repeatable patterns. As caseload grew, so did the pressure — either hire more paralegals or find a smarter way to work.

Time-Intensive Drafting

Paralegals spent up to 120 minutes per demand letter, manually copying case data from ActionStep into Word templates and identifying which legal claims applied to each case.

Per letter, manually
0 min

Caseload Pressure

500+ cases processed monthly with no proportional increase in attorney or paralegal capacity, creating a bottleneck that threatened the firm’s ability to scale.

Cases per month
0 +

Inconsistent Outputs

Newer associates took 2-3x longer than experienced paralegals and produced more variation in claim selection, damage calculations, and document formatting — introducing quality and compliance risk at scale.

Output variance by experience
0 x

2. The Engineer Approach

RTS Labs designed a web-based AI Co-Pilot that integrates directly into PLG’s existing workflow. Rather than replacing the paralegal, the system acts as an intelligent assistant — parsing the Matter Analysis PDF, surfacing applicable claims with confidence scores, auto-calculating damages, and populating the demand letter template in real time. The human stays in the loop for review and final edits before export.

  • Document Ingestion & Parsing

    Paralegals upload a Matter Analysis (MA) PDF. The system converts it to structured JSON using OpenAI GPT-4o, extracting plaintiff/defendant details, employment dates, claim categories, and damage-relevant facts with high consistency.

  • AI Claim Suggestion & Selection

    The AI analyzes the extracted case data against a library of California employment law claims, generating a ranked list of applicable claims — each with a confidence score trained on thousands of prior PLG cases. Paralegals review and confirm selections.

  • Damage Calculation & Template Auto-Fill

    Upon claim selection, the system auto-calculates economic and non-economic damages (back pay, meal/rest break penalties, waiting time penalties, mileage) and populates the official demand letter template — including narrative sections — in real time.

  • Human-in-the-Loop Review & Export

    Paralegals make final edits in a live preview panel before generating the formatted Word document on official letterhead. Compliance safeguards flag missing information, outdated references, or risky language before submission.

The key was building the claim suggestion model around how PLG's experienced attorneys actually think about liability — not just pattern-matching on document text. We trained it on thousands of prior cases so the confidence scores it surfaces are genuinely actionable. That trust layer was what made paralegal adoption immediate, not gradual.
Alex Hogancamp
Director of AI, RTS Labs

3. Results & Impact

Faster Drafting
0 %
Est. Annual Savings
0 k
Throughput Increase
0 x
Time to Production
0 wks

Before RTS Labs

  • Labor-Intensive Processes

    Up to 120 minutes per demand letter, fully manual

  • Fragmented Data Copying

    Copy/paste from ActionStep into Word templates for every case

  • Variable Output Quality

    Inconsistent claim selection and damage calculations across staff

  • Exposure to Compliance Risks

    No automated compliance checks before submission

After RTS Labs

  • Rapid AI-Assisted Turnaround

    ~10 minutes per demand letter with AI-assisted drafting

  • Automated Data Integration

    AI auto-populates templates from structured case data

  • Data-Driven Claim Selection

    Consistent, confidence-scored claim suggestions on every letter

  • Automated Compliance Safeguards

    Built-in compliance flagging before every export

More Case Studies:

Landstar Case Study
Landstar horz logo transparent background

Unifying the Agent Portal: 90% Less Time Searching for Landstar

Overview:
Landstar agents jumped between SOPs, shipment systems, and the capacity portal to answer a single customer question. RTS Labs built an AI copilot directly into the Agent Portal — RAG...
AdobeStock 132567138 768x444
rts logo

Unlocking Enterprise Data: 25% Lower Spend for a Global Sports Equipment Manufacturer

Overview:
A global sports equipment manufacturer — 1,000+ employees designing custom golf gear and apparel across retail and ecommerce — had outgrown a patchwork data architecture that couldn't support the advanced...
Blue Haven Pools Case Study
BlueHaven scaled

1-Day Quotes to 5 Minutes: Blue Haven Pools Case Study

Overview:
Blue Haven Pools' sales process couldn't keep up. Generating a quote required multiple systems and manual calculations — taking up to a full day. By the time proposals reached homeowners,...
Have a Similar Challenge?

Every AI Idea Deserves a Ship Date

Stop strategizing. Start building. Let’s map your workflow and get your AI integration into production in 90 days.

Bring Us Your Brief