New Local AI Simplifies Contracts (Work In Progress)

Problem

Existing user research reveals that customers often sign contracts without understanding their implications.

• An Adobe Acrobat Contract Survey from January, 2025 reveals that 70% of customers admit to signing contracts without knowing what’s in them. 32% of workers have faced negative consequences due to misunderstandings in contracts. The key factors behind this data point are that contracts are too long to read and the negative emotions surrounding contracts.
• Another survey from the UK’s College of Law also reveals that 68% of participants admitted they either don’t read or don’t understand the contracts they sign. More than half of survey participants admitted they read their contracts to an extent but don’t always understand what they’re agreeing to. More than one in ten said they “hardly” or “never” read their contracts at all.

Additionally, there are concerns with AI violating one’s privacy.

• A 2023 study by KPMG and the University of Queensland found three in four customers globally feel concerned about the potential risks of AI.
• KPMG also found 63% of consumers were concerned about the potential for AI to compromise one’s privacy.
• A recent Pew Research Center also found that 81% of consumers think the information collected by AI will be used in ways people are uncomfortable with, as well as in ways that were not originally intended.

In summary, the data reveals that AI can be a tool for analyzing contracts. However, there’s also the potential for AI to be a privacy concern as data may be sent to a company’s servers without a person’s knowledge. This suggests that there is a potential for the creation of a product that both

1. Allows for users to summarize and interact with their documents
2. Also honors their privacy and promises to never send any confidential data to a company’s servers.

Target Audience

• Users’ age between 20 and 60
  • Younger users aged 20 – 24 who are enrolled in an institution of higher ed
  • Middle-aged users from 30 – 40 are high-collar professionals in the industries of User Experience (UX), Graphic Design, Copywriting, Engineering, K-12 Education, and Government
  • Older users from 50 – 60 working in Office Management, Finance & Accounting, Recreational Services, Psychology, and Social Work
• Monthly budget is between $2000 – $8,000
• Internet Speeds
  • Mid-Tier: 500 Mbps Download, 10Mbps Upload
  • High-Tier: 1000 Mbps Download, 20 Mbps Upload

Requirements

• The app should be able to run on as many Mid to High range machines:
  • Mid-Range Machines:
    • 4 to 8-core CPU
    • 6 GB Ram
    • 10GB available storage
    • Windows 10,11, macOS Ventura, Sonoma, Sequoia (currently supported versions), and Debian-based Linux Distributions
  • High-Range Machines:
    • 8 to 16-core CPU
    • 16 to 32 GB Ram
    • 25 GB available storage
    • Windows 10,11, macOS Ventura, Sonoma, Sequoia (currently supported versions), and Debian-based Linux Distributions

Assumptions

• To address the issue of privacy, a local Large Learning Model (LLM) that can be 2 to 4.5 GB in size will need to be downloaded to the user’s computer with full disclosure of the process and how a local LLM differs from a cloud-based LLM such as ChatGPT, Gemini, Docusign AI, Adobe, etc
• AI is changing fast — more AI models are expected to come in the near future, and the cons of each AI now will someday be addressed
• Users want to be confident that any document uploaded to an AI model will never be shared with anyone without consent
• Users expect a friendly AI experience, regardless of whether it’s open source or proprietary. Although, for conscientious users, open source will be a selling point
• Microsoft’s Copilot AI is fully integrated with the Windows 11 OS, which will make it challenging to promote the benefits of local AI and privacy to this user base

Constraints

• Limited budget for user research; this will be a side project, there will be no funding for paying participants to do un-moderated tests for the app or take surveys for a $25 – $50 gift card
• Contributions are voluntary; this will be an open source project, contributors will come and go as they please with no compensation
• Can only use free methods to attract new users and contributors; direct advertising to users will be difficult, if not impossible. For this project, other channels will need to be utilized. Potential options include Discord Chat, Facebook, X, and some Mastodon Instances that are free of charge
• Written in Node.js, a JavaScript library that comes with more limitations for desktop applications compared to ones written in C++, C#, and other compiled languages

What Early Success Looks Like

• Watching 25 – 30 people and 1.5K stars on GitHub for the new project
• The addition of 1 – 2 new contributors during the first two months to reduce the workload of one person
• 2 – 4 downloads a week

What Later Success Looks Like

• Watching 50 – 80 people and 3.5K stars on GitHub for the new project
• The addition of 3 – 5 new contributors every month
• 4 – 6 downloads a day

What Ideal Success Looks Like

• Watching 1000 – 1600 people and 8.5K stars on GitHub for the project
• The addition of 6 – 8 new contributors every one to two weeks
• 30 – 65 downloads a day
• Written recommendations for members of the open source community, in addition to positive reviews on YouTube, ZDNET, TechCrunch, and other high profile news outlets

What Failure Looks Like

• 600-800 users reporting frequent crashes and glitches
• No new contributors
• 1-2 downloads in one week, but none afterwards
• Negative reception from YouTube influencers, ZDNET, TechCrunch, and other high profile news outlets criticising its instability.

UI Diagram (Dot)

To kickstart the deepdive, I’m using Alex Pinel’s Dot on GitHub (GNU General Public License v3) for inspiration, and created a diagram for the UI in Penpot. Penpot is an open source alternative to Figma, Sketch, and InVision under the Mozilla Public Source License 2.0.

Dot v0.9.3 is still being tested in both Wine (Wine Is Not an Emulator) on Ubuntu Linux and Windows 10 within an Oracle Virtualbox VM (base package).

Up Next

• User Persona ✅
• User Flows ❌
• Lo-Fi Wireframes ❌
• Hi-Fi Mockups ❌
• Name and Identity Exploration ❌
• Coding & Testing ❌
• Write up copy for GitHub page ❌
• Promotion Stage ❌