Innovation in Action: A Smarter AI Experience for Your Firm
Get Spoiled with AI
AI seems to be taking over and controlling the conversation no matter where you look. Every time I open social media, I see a post about how AI is replacing jobs or how someone tried to have AI replace themselves, ironically, by using AI to cheat real work. While we here at FinLegal do not support the use of AI to replace people, we do support the use of AI to improve efficiencies in your professional life. I have had the privilege of working with our AI team and will let you know how we see our AI features changing the way your law firm operates.
How did we get here?
If you have read any of my other blog posts in the last few months, you will have seen how proud we are to have been selected by Amazon as one of ten tech teams to work with their AWS team in London. Together, we (the royal “we” as I just cheer my team on in the background) have built a collaborative multi-agent system that enables LLMs to effectively utilize live data within our platform to generate the most relevant results for your customers and shorten the time taken to undertake these tasks by more than 80%.
Specialized Agents = Specialized Results
But how are we using it the most? In a different blog post, I discussed how we have built specialized agents to handle: retrieval, analysis, validation and summarization. These agents are being fed thousands of pages of medical records, directly in the FinLegal dashboard, by our customers and our agentic AI is identifying, referencing, confirming and then summarizing this health information. We are taking 3000+ pages of medical records and turning them into small, easy to read and easy to reference, evidence extractions from thousands of pages to assist firms in case validation, hearing preparation and identifying medical timelines.
Accuracy and Trust in our AI
Our agentic systems use state-of-the-art models as a judge functionality to constantly assess, and reassess, their own outputs at every stage: this is to ensure factual grounding and detect hallucinations, correcting them when they do occur before they ever reach you. Now, no LLM powered system is perfect, but through the effective use of citations our results can be verified quickly by a human reviewer, giving you the trust and confidence to proceed at speed.
From Thousands of Pages to Key Evidence Points
So, how are we currently using these agents? There are two purposes that have made me really excited. The first instance is the use of evidence extractions from thousands of pages for hearing preparation. Here, our agents are looking specifically for medical conditions that render them disabled. The agent scans 3000+ pages of medical records to look for any supporting information of medical diagnosis and the timelines and providers of medical treatment.
Mass Tort Illness Identification
Next, we are using our agent for mass tort illness identification. Our AI engineers use the published lists of ailments in each active litigation and program our agents to search specifically for the mention of any related diagnosis. While we do not “train” our AI, we do continuously work with the programming to ensure the most accurate results for our users. As someone who used to be responsible for the review and summary of medical records, I cannot explain how much time and money this feature would have saved.
Conclusion
In conclusion, FinLegal’s AI solution is based on facts. Our AI engineers have spent hours programming our agents to work with the materials provided and nothing else. Our multi-agent design handles all the work of providing the information your firm needs and our built-in safeguards ensure that the information is accurate and referenceable. While we are working specifically with medical information now, we are also prepared to work with contracts, lease agreements, financial documents and much more! Finally, unlike the general AI solutions available, you get the guaranteed protection for all your information.
Author: Kelsey Wallace Mengel
Kelsey is an experienced legal professional specializing in optimizing intake processes with a focus on client retention, conversion, and personalized communication. She is skilled in training, quality control, and onboarding new case types, with a strong interest in leveraging technology for efficiency. A dedicated military spouse, Kelsey volunteers with the J.D. Military Spouse Network, supporting military families with legal needs.
