Heading

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

Resource

Everytown - Building a Solution to Gun Safety Using LLMs

Download now for free

No items found.

Large-Language Models (LLMs) are revolutionizing the way organizations manage complex tasks. However, deploying LLMs effectively requires more than simply integrating them into existing systems. This was the challenge Everytown faced when they sought to use AI to support their mission of promoting gun safety across the U.S. They needed a sophisticated solution to keep their team informed about constantly changing regulations, ensuring that their efforts remained accurate and impactful.

Everytown - Enhancing Gun Safety Initiatives with AI

Large-Language Models (LLMs) are at the forefront of AI innovation, enabling organizations to significantly improve their workflows. However, challenges like hallucinations and unpredictable outputs mean that successful implementation requires more than just adding an LLM to a chatbot.

Everytown's Mission

Everytown, a nonprofit focused on gun safety, sought an AI solution to help their team stay updated on rapidly changing gun regulations across the U.S. They needed an intelligent assistant that could provide accurate, up-to-date information tailored to specific locations, functioning as an extension of their research team.

Key Challenges

Data Quality and Reliability
Accurate results depend on quality data. We had to format and clean 27 different datasets, ensuring the LLM could interpret and handle them effectively.

Handling Information Overload
We used vector databases to manage large datasets and optimize responses, ensuring accuracy without overloading the LLM’s context window.

Complex Architecture
Behind the simple chat interface, we implemented a sophisticated architecture that included multiple LLMs and agents, each handling specific tasks like data retrieval and Python script execution.

Maintaining Tone and Guardrails
We ensured the assistant matched Everytown’s communication style and stayed within content policies, critical for sensitive topics like gun safety.

The Solution

Leveraging Everytown’s Knowledge
We trained the LLM using Everytown’s existing documentation to ensure consistent tone and quality in responses.

Data Optimization
We carefully selected, processed, and chunked data to fit within the LLM’s context window, enhancing the assistant’s performance.

Advanced Retrieval and Workflow Management
Using Retrieval-Augmented Generation (RAG) and an agentic approach, we allowed the LLM to access and use Everytown’s data effectively, with a central orchestrator managing the workflow.

Python Integration
Through an API, we enabled the LLM to execute complex data queries, improving the assistant’s capabilities and reducing latency.

Validation and Results

The MVP system passed all validation tests, reducing research time from hours to seconds and achieving an 85% match with expert-written responses. It’s now in legal review for broader deployment within Everytown’s network.

Why NineTwoThree?

At NineTwoThree, we specialize in developing cutting-edge AI solutions that enhance workflows and save time. If you're looking to leverage AI for your organization, let's talk.