Bringing AI to Pharma’s Legal Workflows
Arionkoder helped Pharma Company’s Legal team move from manual searches to AI-powered insight. The new platform made contract reviews faster, more accurate, and set the foundation for a full Contract Lifecycle Management system.
Arionkoder helped Pharma Company’s Legal team move from manual searches to AI-powered insight. The new platform made contract reviews faster, more accurate, and set the foundation for a full Contract Lifecycle Management system.
Bringing AI to Pharma’s Legal Workflows
Arionkoder helped Pharma Company’s Legal team move from manual searches to AI-powered insight. The new platform made contract reviews faster, more accurate, and set the foundation for a full Contract Lifecycle Management system.
ALIGN
We began by deeply understanding how the Pharma Company’s Legal team managed contracts day to day.
Our UX and Product teams mapped every step of the process with the Legal Manager. They analyzed how contracts were located in SharePoint and how metadata was extracted and compared manually. This helped uncover the main bottlenecks: tedious searches, duplicated effort, and an overreliance on external attorneys.
These insights revealed a clear opportunity to bring AI into the process responsibly, without disrupting daily workflows.
ALIGN
We began by deeply understanding how the Pharma Company’s Legal team managed contracts day to day.
Our UX and Product teams mapped every step of the process with the Legal Manager. They analyzed how contracts were located in SharePoint and how metadata was extracted and compared manually. This helped uncover the main bottlenecks: tedious searches, duplicated effort, and an overreliance on external attorneys.
These insights revealed a clear opportunity to bring AI into the process responsibly, without disrupting daily workflows.
ALIGN
We began by deeply understanding how the Pharma Company’s Legal team managed contracts day to day.
Our UX and Product teams mapped every step of the process with the Legal Manager. They analyzed how contracts were located in SharePoint and how metadata was extracted and compared manually. This helped uncover the main bottlenecks: tedious searches, duplicated effort, and an overreliance on external attorneys.
These insights revealed a clear opportunity to bring AI into the process responsibly, without disrupting daily workflows.
PRIORITIZE
From our discovery work, we identified four daily tasks where AI could make the greatest impact: searching, reading, and comparing contracts.
These became the foundation of our Proof of Value:
Contract content discovery: ask natural-language questions about contract data.
Metadata extraction: automate how key contract fields are identified and stored.
Contract search: combine keyword and metadata search for faster, smarter retrieval.
Template comparison: highlight differences between a contract and its standard template.
Together, these use cases defined the PoV scope — proving how AI could reshape legal operations at scale.
PRIORITIZE
From our discovery work, we identified four daily tasks where AI could make the greatest impact: searching, reading, and comparing contracts.
These became the foundation of our Proof of Value:
Contract content discovery: ask natural-language questions about contract data.
Metadata extraction: automate how key contract fields are identified and stored.
Contract search: combine keyword and metadata search for faster, smarter retrieval.
Template comparison: highlight differences between a contract and its standard template.
Together, these use cases defined the PoV scope — proving how AI could reshape legal operations at scale.
PRIORITIZE
From our discovery work, we identified four daily tasks where AI could make the greatest impact: searching, reading, and comparing contracts.
These became the foundation of our Proof of Value:
Contract content discovery: ask natural-language questions about contract data.
Metadata extraction: automate how key contract fields are identified and stored.
Contract search: combine keyword and metadata search for faster, smarter retrieval.
Template comparison: highlight differences between a contract and its standard template.
Together, these use cases defined the PoV scope — proving how AI could reshape legal operations at scale.
Prove
We built an AI-powered platform that mirrored the familiar SharePoint interface but delivered entirely new capabilities behind the scenes.
AI-driven contract search
Implemented a dual-mode AI Agent with metadata-based (SQL) and keyword-based (Azure AI Search) tools.
Results: 95–100 % keyword-search accuracy and 71 % metadata-search accuracy.Metadata extraction automation
Deployed multimodal LLMs to parse contracts and auto-populate fields such as expiration or signature dates, achieving high reliability with exceptions flagged for legal validation.Contract chatbot (“Madra”)
Enabled users to query entire contracts conversationally without RAG pipelines, reaching ≈ 84 % answer accuracy.
Template comparison Designed AI-generated summaries highlighting key deviations, replacing manual side-by-side reviews.
Prove
We built an AI-powered platform that mirrored the familiar SharePoint interface but delivered entirely new capabilities behind the scenes.
AI-driven contract search
Implemented a dual-mode AI Agent with metadata-based (SQL) and keyword-based (Azure AI Search) tools.
Results: 95–100 % keyword-search accuracy and 71 % metadata-search accuracy.Metadata extraction automation
Deployed multimodal LLMs to parse contracts and auto-populate fields such as expiration or signature dates, achieving high reliability with exceptions flagged for legal validation.Contract chatbot (“Madra”)
Enabled users to query entire contracts conversationally without RAG pipelines, reaching ≈ 84 % answer accuracy.
Template comparison Designed AI-generated summaries highlighting key deviations, replacing manual side-by-side reviews.
Prove
We built an AI-powered platform that mirrored the familiar SharePoint interface but delivered entirely new capabilities behind the scenes.
AI-driven contract search
Implemented a dual-mode AI Agent with metadata-based (SQL) and keyword-based (Azure AI Search) tools.
Results: 95–100 % keyword-search accuracy and 71 % metadata-search accuracy.Metadata extraction automation
Deployed multimodal LLMs to parse contracts and auto-populate fields such as expiration or signature dates, achieving high reliability with exceptions flagged for legal validation.Contract chatbot (“Madra”)
Enabled users to query entire contracts conversationally without RAG pipelines, reaching ≈ 84 % answer accuracy.
Template comparison Designed AI-generated summaries highlighting key deviations, replacing manual side-by-side reviews.
Integrate
We integrated these AI components into a cohesive UX platform resembling the Legal team’s existing tools to drive adoption.Natural-language filters, guided prompts, and AI-generated summaries reduced friction and saved time, while preserving data governance within Pharma Company’s Azure and Databricks stack.Agile sprints and proof spikes allowed the team to iterate fast, validate AI behavior, and refine workflows in real time.
Integrate
We integrated these AI components into a cohesive UX platform resembling the Legal team’s existing tools to drive adoption.Natural-language filters, guided prompts, and AI-generated summaries reduced friction and saved time, while preserving data governance within Pharma Company’s Azure and Databricks stack.Agile sprints and proof spikes allowed the team to iterate fast, validate AI behavior, and refine workflows in real time.
Integrate
We integrated these AI components into a cohesive UX platform resembling the Legal team’s existing tools to drive adoption.Natural-language filters, guided prompts, and AI-generated summaries reduced friction and saved time, while preserving data governance within Pharma Company’s Azure and Databricks stack.Agile sprints and proof spikes allowed the team to iterate fast, validate AI behavior, and refine workflows in real time.
Scale
Beyond the PoV, we designed a roadmap for growth toward a production-ready CLM platform:
Cost-Benefit Analysis – Azure migration plan and cost projections.
Feature Expansion – future AI modules for clause automation, risk scoring, and compliance tracking.
User-Centric Refinement – prioritized improvements to handle metadata edge cases and ensure adoption.
Scale
Beyond the PoV, we designed a roadmap for growth toward a production-ready CLM platform:
Cost-Benefit Analysis – Azure migration plan and cost projections.
Feature Expansion – future AI modules for clause automation, risk scoring, and compliance tracking.
User-Centric Refinement – prioritized improvements to handle metadata edge cases and ensure adoption.
Scale
Beyond the PoV, we designed a roadmap for growth toward a production-ready CLM platform:
Cost-Benefit Analysis – Azure migration plan and cost projections.
Feature Expansion – future AI modules for clause automation, risk scoring, and compliance tracking.
User-Centric Refinement – prioritized improvements to handle metadata edge cases and ensure adoption.
“Commercial CMS failed at some of the things our PoV does, and lack some features we love about it.”
AI Director
@
Pharma Company
How we helped:
1.
Explored Legal Workflows in Depth
Mapped the contract search and review process, identifying inefficiencies and automation opportunities.
2.
Designed a Familiar Yet Powerful UX
Built an intuitive interface inspired by SharePoint to minimize disruption.
3.
Developed Hybrid AI Agents
Combined LLM reasoning with metadata and keyword search for smarter contract discovery.
4.
Automated Metadata Extraction
Implemented multimodal LLMs to parse and classify key contract fields.
5.
Built “Madra” Contract Chatbot
Enabled conversational understanding of contracts with 84 % accuracy.
6.
Optimized Template Comparison
Used prompt engineering to summarize deviations efficiently.
7.
Delivered a Growth Roadmap
Outlined the path from PoV to full CLM platform with cost and feature projections.
Team
Product Owner Project Manager ML Engineer Data Scientist Back-End Engineer QA Engineer UX/UI Designer
Delivery
UX/UI Design Functional Web App GitHub Repository Product Documentation
GET STARTED
Ready to make AI useful?
Ready to make AI useful?
Ready to make AI useful?
Turning bold ambition into lasting impact starts with a conversation.
Turning bold ambition into lasting impact starts with a conversation.
© 2025 Arionkoder.
All rights reserved.
Quick Actions
Jump to Value
The Foundry
Email: hello@arionkoder.com
Offices: Americas · EMEA (5 offices)
This site respects your device’s accessibility settings, including Reduce Motion, and reduces animations when that option is enabled.