Techathon 6.0

About the business: 

A leading multinational generic pharmaceutical company, with significant business in the US and a broad product portfolio, seeks to diversify beyond the highly competitive, low-margin generics market. The company aims to develop value-added, innovative products by repurposing approved molecules for new indications, alternative dosage forms, or different patient populations—targeting unmet medical needs.

Problem statement: 

Identifying such opportunities requires extensive literature reviews, often taking two to three months and involving multiple iterations to uncover viable product concepts. To accelerate this process, the company plans to adopt an Agentic AI solution that integrates with various online sources and subscription-based databases.

This AI-driven tool will enable users to interactively explore potential innovation cases, significantly reducing research time and increasing throughput. By enhancing the speed and quality of early-stage product evaluations, the company aims to strengthen its pipeline with differentiated offerings that deliver greater clinical and commercial value.

Goal:

Teams must design an Agentic AI solution where the Master Agent:

• Can be linked to various regulatory websites, clinical trial websites, scientific journals and paid databases (subscriptions provided by the client), along with any internal databases of the client
• Features a user interface that allows users to input prompts for finding information from the web, analyzing market data and summarize scientific journals
• Generates a summary report of the searches and save the report in an archival system

Key deliverable:

A live demo or recorded video (maximum four minutes) showcasing the end-to-end journey from the initial prompt of finding a molecule, identifying its unmet needs, checking for ongoing clinical trials, exploring its probable use in other diseases, and determining if any patents have been filed, leading to the development of an innovative product story.

Agentic AI roles

1. Master Agent (Conversation orchestrator)

• Interprets user queries and breaks them into modular research tasks.
• Delegates tasks to domain-specific Worker Agents.
• Synthesizes responses from Worker Agents into coherent summaries with references.
• Responds with formatted text, tables, charts or PDF reports as needed

2. Worker Agents

• IQVIA Insights Agent
  • Queries IQVIA datasets for sales trends, volume shifts and therapy area dynamics.
  • Outputs: Market size tables, CAGR trends, therapy-level competition summaries.
• EXIM Trends Agent
  • Extracts export-import data for APIs/formulations across countries.
  • Outputs: Trade volume charts, sourcing insights, import dependency tables.
• Patent Landscape Agent
  • Searches USPTO and other IP databases for active patents, expiry timelines and FTO flags
  • Outputs: Patent status tables, competitive filing heatmaps, PDF extracts of relevant patents.
• Clinical Trials Agent
  • Fetches trial pipeline data from ClinicalTrials.gov or WHO ICTRP.
  • Outputs: Tables of active trials, sponsor profiles, trial phase distributions.
• Internal Knowledge Agent
  • Retrieves and summarizes internal documents (e.g., MINS, strategy decks, field insights).
  • Outputs: Key takeaways, comparative tables or downloadable briefing PDFs
• Web Intelligence Agent
  • Performs real-time web search for guidelines, scientific publications, news and patient forums
  • Outputs: Hyperlinked summaries, quotations from credible sources, guideline extracts
• Report Generator Agent
  • Formats the synthesized response into a polished PDF or Excel report.
  • Outputs: PDF summaries with charts/tables, downloadable links in-chat.
  • ClinicalTrials.gov