This article will provide you with a basic overview of Jurist. This includes details on how it works, a map of the interface, and tips on how to most effectively engage with Jurist.
What is Ironclad AI Assistant?
To explain what Jurist is, we must first explain a couple of AI industry terms:
- Generative AI (GenAI): A type of artificial intelligence system that can create new content, such as text, images, music, or code, based on patterns learned from existing data. When you give it a question or topic, it can come up with original answers that look and sound like they were made by a person.
- Conversational AI: Allows machines to have human-like conversations by using natural language processing and machine learning. This technology powers chatbots, virtual assistants, and voice interfaces, enabling smooth interactions with technology. These systems can understand the context of a conversation, answer questions, provide support, and help with various tasks. This changes how we communicate with machines and access information and services.
- Large Language Model (LLM): A type of artificial intelligence designed to understand and generate human language. These models are trained on vast amounts of text data, allowing them to recognize patterns, context, and meaning. LLMs can answer questions, write essays, translate languages, and even hold conversations, making them useful for various applications like chatbots, writing assistance, and more.
Jurist is a legal AI assistant that can draft, edit, summarize and conduct research for any general counsel, lawyer, or legal team. It uses an LLM and Conversational AI to provide you with an experience similar to chatting virtually with a colleague. It is highly trained in legal terminology, processes, and contracts.
How Does it Work?
To use Jurist, you’ll simply enter a prompt, attach a relevant document, and Chat. Jurist carries out your request on the right, logging each step in the Logs panel on the left. From there, it works just like a conversation! You can ask Jurist to edit different sections of the document, simplify the language, add in different clauses, and much more.
Ironclad AI Assistant Interface
| Item | Description |
|---|---|
| New Project and Project History (1) | Click the plus sign to create a new project. Click the clock icon to view a list of your most recent projects. |
| Input Box (2) | Enter your questions and responses for the Jurist. You can also view a list of prompts, attach relevant files, and show/hide the Logs window. |
| Log (3) | A log of the actions Jurist is taking based off of your prompts and responses. |
| Jurist Chat (4) | The chat thread between you and Jurist. |
| File Editor (5) | A file editor. It can display your uploaded document or the content Jurist generated based on your prompt. You can have multiple tabs open to display various documents or output. Depending on your screen’s size, Jurist may display one or two file editor panes. Redlines are color-coded for easy identification:
|
| AI Generated Output Title (6) | The title of the content the Jurist generated. This is often a summary of your prompt. |
| Download (7) | Download a .docx file of the Jurist’s output. |
| Editor Tools (8) | Edit the document with basic functions such as text formatting, lists, indentation, and hyperlinks. You can also show/hide redlines by toggling the switch. |
Jurist Agents and Token Limits
Jurist uses multiple agents designed to automate tasks commonly done by humans, like reading, editing, analyzing, or synthesizing. Jurist uses a manager agent to delegate or sequence tasks through agents in order to achieve the best output.
When agents use Large Language Models (LLMs) to accomplish a task, they are limited by the LLM's context window, which is the amount of information that the LLM can either consume or output. These context windows vary by model and provider, and are typically measured in tokens.
Tokens can be mapped to words, paragraphs, and pages and are directionally accurate. The actual words, paragraphs, and pages a model can handle will vary based on the content itself (eg. paragraphs vs tables) as well as things like font and font size.
Use the following table to understand the token-limited operations Jurist can perform and associated limits.
| Operation | Sub Operation | Approximate Limits |
|---|---|---|
| Editing | Redlining | 70,000 words |
| Editing from a template | 70,000 words | |
| Translating | 70,000 words or 300 paragraphs, whatever is lesser | |
| Document Analysis | 70,000 words |
Tips for Using Jurist
Interacting with Jurist is as simple as engaging in a chat. Here are some tips to help you get started:
- Be specific. Clearly describe your query or task. For example, "Build a table showing the tax treatment of stock options in Mexico, including at grant, exercise and sale."
- Indicate who you are. By telling Jurist whether you are part of the company or the counterparty, it will be able to draft content and redlines with your role in mind.
- Provide context. The more details you provide, the more tailored Jurist's assistance will be. For instance, "Draft a non-disclosure agreement for a tech startup, focusing on intellectual property protection."
- Continue the conversation. If Jurist's response isn't quite what you needed, ask follow-up questions or request more specific information.
- Always review AI-generated content. While AI is a powerful tool, it's important to remember that it doesn't replace the need for human judgment and legal expertise.