Intelligent Digital Assistance for Contract Workflows

Presented By

Tom Debevoise (Advanced Component Research)
Denis Gagne CEO & CTO Trisotech

Description

Legal contracts often lead to intricate workflows that traditional modeling techniques, such as BPMN, struggle to represent accurately. This presentation explores the complexity of real estate sales agreements and how retrieval-augmented generation (RAG) can effectively model their dynamic nature. Real estate contracts, which encompass numerous critical elements like purchase price, property condition, financing terms, and regulatory compliance, are not static but evolve through negotiations and contingencies.

The dynamic and multifaceted nature of these contracts necessitates a sophisticated approach to workflow management for knowledge workers. Current methods fall short in capturing the detailed nuances, resulting in inefficiencies and errors as professionals manually extract essential information. By leveraging RAG, it is possible to maintain an adaptive list of activities and events, akin to a “checklist” with a closing calendar, guiding the efforts of real estate professionals more effectively.

This presentation by Tom and Denis will delve into the challenges of modeling complex contracts and demonstrate how RAG can address these issues, ultimately enhancing the workflow and efficiency of knowledge workers involved in real estate transactions.

View the slides

Videos

Recorded webinars

View all videos
Attend a live webinar

Blog

In Healthcare:
To Automate or Not to Automate, that is the Question

By Dr. John Svirbely, MD

Read Time: 3 Minutes

With modeling tools, you can define complex processes such as clinical guidelines. In theory these models can be automated. In practice it may be wise not to automate everything. The decision to automate depends on several factors, such as your goals and the problems that you need to solve. Automation is not without costs, and you need to consider the return on your investment (ROI).

The Decision to Automate

Certain processes or decisions are more attractive to automate than others. To identify these, you may ask some questions:

Is it “high” value (high frequency, repetitive, something not to be overlooked)?
Do users view automation of the process as something that would be helpful?
Does the process or decision have a certain level of stability?
Does it have reasonable data requirements?

How much data that the models require and how easy it is to obtain are key issues. If the automated process constantly interrupts the user or requires a large amount of data, then it may bring little value to the organization. One solution may be to have standing orders in place that will guarantee that the required data is always collected and available when it is needed.

The Emergency Department is an excellent example of practice setting which can be a challenge to automate. The environment can be chaotic, and some patients require dynamic care that is determined on the fly. Such tasks are a challenge to automate. However, even in the ED there are other processes where automation can relieve staff from drudgery and free them up for patient care.

One issue to consider relates to patient complexity. If most patients are straightforward while only a small subset are clinical challenges, then the complex patients can be triaged to a clinician while the remainder handled by an automated process. This improves overall efficiency and use of manpower.

Microservices

Even if a guideline is not fully automatable, it often contains elements that are. These can be encapsulated in microservices that are triggered when a certain set of conditions are met.

These are attractive since they often need a limited amount of data. They are easier to create and maintain. On the other hand, many of these services may be needed, which can introduce another set of challenges.

Figure: Example of a BPMN Process that can serve as a microservice in a patient being treated with opioids. It identifies possible gaps in the patient’s care that need to be corrected.

One challenge with microservices is the user experience. Having a lot of microservices means that a lot of messages could be generated and cause alarm fatigue. It is important to develop a strategy that will allow essential information to get through to the user.

Conclusions

The decision to automate or not can be challenging. Several things need to be considered such as cost, liability, acceptability, and care quality. However, considering the economic challenges faced in healthcare today, automation is an attractive idea. Some processes can and should be automated.