AIToday

PwC's AI-driven annotation solution on AWS reduces manual contract review time by up to 90%

Amazon AI BlogApr 29, 20262 min read
PwC's AI-driven annotation solution on AWS reduces manual contract review time by up to 90%

Summaries like this, in your inbox every morning.

Sign up free →

3 Key Points

  1. PwC built AIDA (AI-driven annotation), a solution on AWS that extracts structured insights from contracts using LLMs (large language models—AI systems that understand and generate text) combined with rule-based extraction and natural language queries. In customer implementations, AIDA has helped reduce manual contract review time by up to 90%.

  2. AIDA provides three core capabilities: template-based extraction using user-defined rules, document-level chat where users ask natural language questions about individual contracts, and global chat across multiple documents with context-specific answers linked to source citations. The solution processes contracts asynchronously across Amazon ECS using AWS Fargate and uses Retrieval Augmented Generation (RAG) to ground model responses in the underlying contract text.

  3. In the Media & Entertainment sector, one major film and TV studio used AIDA to extract and analyze rights information from license agreements and reduced rights research time by 90%. AIDA can support contract analysis across industries including Real Estate and functions like Procurement, Legal, and Compliance.

Discussion

No comments yet. Be the first to share your thoughts!

Log in to join the discussion

Related Articles

Stay ahead with AI news

Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.

Get Started Free

Free · takes 30 seconds · unsubscribe anytime

1 minute a day. The AI essentials.

200+ sources · Email / LINE / Slack

Get it free →