--- title: The context problem: How Docusign built agents that... description: Docusign's CTO Sagnik Nandy explains how its Iris AI engine gives contract agents the context needed to act on agreements, not just summarize them. He breaks... canonical: https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The context problem: How Docusign built agents that understand the business behind contracts | daily.dev og:description: Docusign's CTO Sagnik Nandy explains how its Iris AI engine gives contract agents the context needed to act on agreements, not just summarize them. He breaks... og:url: https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo og:image: https://api.daily.dev/og/posts/LubDTvDwO.png og:image:alt: The context problem: How Docusign built agents that understand the business behind contracts og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The context problem: How Docusign built agents that understand the business behind contracts **[The New Stack](https://daily.dev/sources/newstack)** · 8 min read · 1 upvotes · 0 comments ## Summary Docusign's CTO Sagnik Nandy explains how its Iris AI engine gives contract agents the context needed to act on agreements, not just summarize them. He breaks context into four types: within-agreement, cross-agreement, organizational, and user. Iris combines extraction, semantic search, and agreement-specific logic to link contracts and amendments into single entities. Nandy estimates a single procurement question can involve five or six tools working together behind the scenes. Docusign reports that Experian cut contract cycle times from roughly 10 days to hours and made contract data easier to access after connecting Docusign with its CPQ solution. This is a sponsored post. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What are the four types of context an AI agent needs to understand contracts, according to Docusign? Docusign's CTO Sagnik Nandy identifies four categories: within-agreement context (tracking terms across pages of one document), cross-agreement context (linking a contract with its amendments and price changes), organizational context (internal legal and procurement policies), and user context (language preferences and prior questions). General-purpose LLMs handle the first category reasonably well but struggle with the other three. _Developers designing contract or document AI agents can track context-handling approaches like this on daily.dev._ ### Why can't a general-purpose LLM correctly answer questions about a contract that has multiple amendments? To a language model, a contract and its amendments look like three or four independent PDF files rather than one contractual relationship. Custom logic is needed to group the documents correctly and determine which terms are currently in force, since retrieval alone cannot establish which version of a clause applies after amendments or price changes. _Anyone building retrieval-based agents over linked documents can follow similar context challenges on daily.dev._ ### What results has Docusign reported from customers using its Iris contract AI engine? Docusign reported in its 2026 Customer Awards that Experian cut contract cycle times from roughly 10 days to hours after connecting Docusign with its configure-price-quote (CPQ) solution, also making contract data easier to access and understand. Docusign notes these results are not necessarily attributable to autonomous agents specifically. _Teams evaluating enterprise AI agent vendors can compare reported outcomes like this on daily.dev._ ## Similar posts on daily.dev - [Making the case for context-aware AI](https://daily.dev/posts/making-the-case-for-context-aware-ai-qtscsy5rm) · MIT Technology Review · 2 upvotes · 0 comments - [Unlocking AI’s full potential: Why context is everything](https://daily.dev/posts/unlocking-ai-s-full-potential-why-context-is-everything-tugwyh3ng) · The New Stack · 1 upvotes · 0 comments - [The Context Tax of Agentic Development](https://daily.dev/posts/the-context-tax-of-agentic-development-spfv0nbhr) · Expedia Group Tech · 0 upvotes · 0 comments - [Enterprise Context Engineering](https://daily.dev/posts/enterprise-context-engineering-a8tzc9dd5) · Materialize · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm), [#rag](https://daily.dev/tags/rag) [View this post on daily.dev](https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The context problem: How Docusign built agents that understand the business behind contracts","url":"https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo"},"datePublished":"2026-10-31T16:23:23.399Z","dateModified":"2026-10-31T16:23:51.355Z","description":"Docusign's CTO Sagnik Nandy explains how its Iris AI engine gives contract agents the context needed to act on agreements, not just summarize them. He breaks...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eb4b453d3fe138c582ec1a13bbc4356f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eb4b453d3fe138c582ec1a13bbc4356f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm,rag","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"The context problem: How Docusign built agents that understand the business behind contracts"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-context-problem-how-docusign-built-agents-that-understand-the-business-behind-contracts-lubdtvdwo#faq","mainEntity":[{"@type":"Question","name":"What are the four types of context an AI agent needs to understand contracts, according to Docusign?","acceptedAnswer":{"@type":"Answer","text":"Docusign's CTO Sagnik Nandy identifies four categories: within-agreement context (tracking terms across pages of one document), cross-agreement context (linking a contract with its amendments and price changes), organizational context (internal legal and procurement policies), and user context (language preferences and prior questions). General-purpose LLMs handle the first category reasonably well but struggle with the other three. Developers designing contract or document AI agents can track context-handling approaches like this on daily.dev."}},{"@type":"Question","name":"Why can't a general-purpose LLM correctly answer questions about a contract that has multiple amendments?","acceptedAnswer":{"@type":"Answer","text":"To a language model, a contract and its amendments look like three or four independent PDF files rather than one contractual relationship. Custom logic is needed to group the documents correctly and determine which terms are currently in force, since retrieval alone cannot establish which version of a clause applies after amendments or price changes. Anyone building retrieval-based agents over linked documents can follow similar context challenges on daily.dev."}},{"@type":"Question","name":"What results has Docusign reported from customers using its Iris contract AI engine?","acceptedAnswer":{"@type":"Answer","text":"Docusign reported in its 2026 Customer Awards that Experian cut contract cycle times from roughly 10 days to hours after connecting Docusign with its configure-price-quote (CPQ) solution, also making contract data easier to access and understand. Docusign notes these results are not necessarily attributable to autonomous agents specifically. Teams evaluating enterprise AI agent vendors can compare reported outcomes like this on daily.dev."}}]} ```