Case Study
Optimizing Investigational New Drug Application Processes
Case Study
Optimizing Investigational New Drug Application Processes
Client
A Top Provider of New Drug Application Services
Industry
Healthcare & Life Sciences
Services
Analysis & Design Source Document Vectorization Prompt Engineering Retrieval Augmented Generation (RAG)
Project Duration
3 months
Client
A Top Provider of New Drug Application Services
Industry
Healthcare & Life Sciences
Services
Analysis & Design Source Document Vectorization Prompt Engineering Retrieval Augmented Generation (RAG)
Project Duration
3 months
Client
A Top Provider of New Drug Application Services
Industry
Healthcare & Life Sciences
Services
Analysis & Design Source Document Vectorization Prompt Engineering Retrieval Augmented Generation (RAG)
Project Duration
3 months
Problem
A top firm that helps new drug developers submit extensive applications for investigational new drugs (INDs), was looking to streamline their operations. Specializing in cell and gene therapy (CGT), the client offers a comprehensive range of services tailored to the unique challenges of this sector and IND (Investigational New Drug) application projects. The process is currently manual, labor-intensive, and requires processing massive amounts of supportive documentation and materials consuming substantial resources for each new application. The client was seeking ways to streamline their internal processes and amount of time required from staff to stay competitive.
Our Vision
Roko Labs was selected to create an AI-powered solution that streamlines the creation of IND application documents based on various available materials (video meetings, contracts, source documents, etc.) the system would employ a fine-tuned AI model, extract relevant contextual information and meta-data, anonymize and validate the data, to have the final pre-IND documents (Statement of Work, Analytical Procedures, and Validation of Analytical Procedures) generated automatically.
Problem
A top firm that helps new drug developers submit extensive applications for investigational new drugs (INDs), was looking to streamline their operations. Specializing in cell and gene therapy (CGT), the client offers a comprehensive range of services tailored to the unique challenges of this sector and IND (Investigational New Drug) application projects. The process is currently manual, labor-intensive, and requires processing massive amounts of supportive documentation and materials consuming substantial resources for each new application. The client was seeking ways to streamline their internal processes and amount of time required from staff to stay competitive.
Our Vision
Roko Labs was selected to create an AI-powered solution that streamlines the creation of IND application documents based on various available materials (video meetings, contracts, source documents, etc.) the system would employ a fine-tuned AI model, extract relevant contextual information and meta-data, anonymize and validate the data, to have the final pre-IND documents (Statement of Work, Analytical Procedures, and Validation of Analytical Procedures) generated automatically.
Problem
A top firm that helps new drug developers submit extensive applications for investigational new drugs (INDs), was looking to streamline their operations. Specializing in cell and gene therapy (CGT), the client offers a comprehensive range of services tailored to the unique challenges of this sector and IND (Investigational New Drug) application projects. The process is currently manual, labor-intensive, and requires processing massive amounts of supportive documentation and materials consuming substantial resources for each new application. The client was seeking ways to streamline their internal processes and amount of time required from staff to stay competitive.
Our Vision
Roko Labs was selected to create an AI-powered solution that streamlines the creation of IND application documents based on various available materials (video meetings, contracts, source documents, etc.) the system would employ a fine-tuned AI model, extract relevant contextual information and meta-data, anonymize and validate the data, to have the final pre-IND documents (Statement of Work, Analytical Procedures, and Validation of Analytical Procedures) generated automatically.
Scroll Full Timeline
Solution
Roko Labs collaborated closely with the client subject matter experts to define project requirements and business logic. Through in-depth discovery sessions, the team identified key workflows and obtained source documents essential for training AI models and refining prompts.
Solution
Roko Labs collaborated closely with the client subject matter experts to define project requirements and business logic. Through in-depth discovery sessions, the team identified key workflows and obtained source documents essential for training AI models and refining prompts.
Scroll Full Timeline
Roko’s AI engineers designed a robust system architecture centered around a fine-tuned single model, incorporating Retrieval Augmented Generation (RAG). This approach enabled the system to effectively process domain-specific knowledge, ensuring precise extraction of key information from complex medical and regulatory documents. The system was developed and rigorously trained through iterative review cycles with the client’s experts, refining outputs until an optimal accuracy threshold was achieved. A custom-built UI was implemented to facilitate seamless document uploading, AI processing, and expert review—ensuring a streamlined workflow for generating high-quality pre-IND documents.
Roko’s AI engineers designed a robust system architecture centered around a fine-tuned single model, incorporating Retrieval Augmented Generation (RAG). This approach enabled the system to effectively process domain-specific knowledge, ensuring precise extraction of key information from complex medical and regulatory documents. The system was developed and rigorously trained through iterative review cycles with the client’s experts, refining outputs until an optimal accuracy threshold was achieved. A custom-built UI was implemented to facilitate seamless document uploading, AI processing, and expert review—ensuring a streamlined workflow for generating high-quality pre-IND documents.
Roko Labs developed the Synthesis App for the client, a custom UI that enables the client to securely upload emails, text, and even video conversations for processing. These materials are stored using scalable solutions like AWS S3, with robust encryption to protect highly confidential data. During processing, the system first retrieves relevant data needed for generating a sub-section of an investigational new drug (IND) application by extracting key methods, procedures, and equipment details, including keywords, summaries, and structured data. Next, the system retrieves validation parameters such as accuracy, precision, and robustness, along with related testing data. Finally, the system compiles the retrieved information into a clear and structured document, ensuring a well-organized output that meets regulatory and industry standards.
Roko Labs developed the Synthesis App for the client, a custom UI that enables the client to securely upload emails, text, and even video conversations for processing. These materials are stored using scalable solutions like AWS S3, with robust encryption to protect highly confidential data. During processing, the system first retrieves relevant data needed for generating a sub-section of an investigational new drug (IND) application by extracting key methods, procedures, and equipment details, including keywords, summaries, and structured data. Next, the system retrieves validation parameters such as accuracy, precision, and robustness, along with related testing data. Finally, the system compiles the retrieved information into a clear and structured document, ensuring a well-organized output that meets regulatory and industry standards.
Result
80%
accuracy score of generated documents from proof of concept focusing on two key IND sections.
50%
Reduction in time required per IND, creating a scalable framework for the client.
Result
80%
accuracy score of generated documents from proof of concept focusing on two key IND sections.
50%
Reduction in time required per IND, creating a scalable framework for the client.
Have a similar project or AI initiative? Let’s talk about it.
More Case Studies
Copyright © 2026 Roko Labs Inc.
All rights reserved.
1250 Broadway, 36th Floor, New York, NY, 10001
Copyright © 2026 Roko Labs Inc.
All rights reserved.
1250 Broadway, 36th Floor, New York, NY, 10001
Copyright © 2026 Roko Labs Inc.
All rights reserved.
1250 Broadway, 36th Floor, New York, NY, 10001
Copyright © 2026 Roko Labs Inc.
All rights reserved.
1250 Broadway, 36th Floor, New York, NY, 10001