Ask a general-purpose language model to summarize a contract, and it will probably do a reasonable job. Ask it to calculate what a company owes a supplier, accounting for three amendments, a revised pricing schedule, and an internal procurement policy, and it’s a different story.
Enterprise AI agents need to know more than what’s written in a document. They need context about which contracts belong together, which terms still apply, and when a decision needs human approval.
It’s a problem Docusign is tackling as it expands beyond electronic signatures into an Intelligent Agreement Management (IAM) platform.. Introduced in April 2024 and available in the U.S. to customers that May, the IAM platform helps organizations create, commit to and manage agreements.
At the center of that effort is Docusign Iris, the contract AI engine that powers Docusign IAM and its AI features across the agreement lifecycle. It combines Docusign’s contract management expertise, agreement-centric data, and AI models to help teams surface insights and take action across contract workflows.
“General LLMs are great. It’s just that you need more around it to really unleash its full power,” Sagnik Nandy, Docusign’s chief technology officer, tells The New Stack.
“Context is one of the things that really differentiates a generic solution from a solution that speaks your language.”
“Context is one of the things that really differentiates a generic solution from a solution that speaks your language.”
In Nandy’s account, the first is relatively straightforward: following a term defined on page two and referenced again on page 20 of the same contract.
Source link
