Contract management · Production

How Condé Nast accelerated contract processing and rights analysis with Amazon Bedrock

The problem

Rights management experts at Condé Nast spent countless hours manually identifying and matching incoming contracts to existing templates, extracting granted rights and metadata, and managing licensing agreements. The manual, rule-based approach created significant operational bottlenecks, was time-consuming and prone to human error, and caused the company to take a conservative approach to utilizing rights — resulting in missed revenue opportunities.

Workflow diagram · grounded in source
1
Contract upload triggers workflow
trigger
“A user uploads new contracts to an input S3 bucket. The addition of new contracts triggers Amazon EventBridge, which starts the main Step Functions workflow.”
2
PDF-to-text transcription
ai_action
“This step uses the visual reasoning capabilities of Anthropic's Claude 3.7 Sonnet in Amazon Bedrock to perform the transcription from a PDF (converted to an image) into a raw text file. This operation takes into account handwritten notes…”
3
Metadata field extraction
ai_action
“a second SageMaker Processing job runs, using Anthropic's Claude 3.7 Sonnet in Amazon Bedrock to extract a set of pre-specified metadata fields. The large language model (LLM) is provided a schema through a prompt template, consisting of…”
4
Template similarity and diff
ai_action
“A third SageMaker Processing job discovers similar existing templates by comparing the text of the incoming contract to the text of possible templates, stored in an Amazon Bedrock knowledge base. Additionally, Anthropic's Claude 3.7 Sonn…”
5
Human review and system load
human_review
“A human reviewer validates the results of the system. Using an AWS Lambda function, valid results are then loaded into Condé Nast's rights and royalties management system.”
6
Route low-similarity contracts
routing
“Incoming contracts with low similarity across the templates are sent to a separate S3 bucket to be used in a separate downstream process (further analysis and generation of new templates).”
7
Cluster low-similarity contracts
ai_action
“These low similarity contracts are passed into a clustering algorithm and grouped based on the similarity of their text and the rights granted by each contract.”
8
Draft and ingest new templates
feedback_loop
“A human reviewer uses these results to draft new templates to be used in future deals and runs of the solution. The solution can then be rerun for the contracts that might have new corresponding templates uploaded to the knowledge base i…”
Reported outcome

Processing time for contract analysis was reduced from weeks to hours, significantly reducing the risk of rights violations and dramatically improving access to rights management expertise across the organization.
The system handles high-volume periods without requiring additional human resources.

Reported metrics
Contract analysis processing timereduced from weeks to hours
Risk of rights violationssignificantly reduced
Access to rights management expertisedramatically improving
Handling of high-volume periodseffortlessly handles increased workloads without requiring additional human resources
Show all 5 reported metrics
contract analysis processing timereduced from weeks to hours
risk of rights violationssignificantly reduced
access to rights management expertisedramatically improving
handling of high-volume periodseffortlessly handles increased workloads without requiring additional human resources
focus of rights management expertsfocus on complex cases and strategic initiatives
Reported stack
Amazon BedrockAmazon S3AWS Step FunctionsAmazon SageMaker AIAmazon EventBridgerights and royalties management system
Source
https://aws.amazon.com/blogs/machine-learning/how-conde-nast-accelerated-contract-processing-and-rights-analysis-with-amazon-bedrock?tag=soumet-20
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Processing time for contract analysis was reduced from weeks to hours, significantly reducing the risk of rights violations and dramatically improving access to rights management expertise across the organization.

What tools did this team use?

Amazon Bedrock, Amazon S3, AWS Step Functions, Amazon SageMaker AI, Amazon EventBridge, rights and royalties management system.

What results were reported?

Contract analysis processing time: reduced from weeks to hours; Risk of rights violations: significantly reduced; Access to rights management expertise: dramatically improving; Handling of high-volume periods: effortlessly handles increased workloads without requiring additional human resources (source-reported, not independently verified).

How is this contract management AI workflow structured?

Contract upload triggers workflow → PDF-to-text transcription → Metadata field extraction → Template similarity and diff → Human review and system load → Route low-similarity contracts → Cluster low-similarity contracts → Draft and ingest new templates.

Related contract management cases