Tech
How we built Formation Bio’s clinical trial prediction model
How Formation Bio is designing a resilient research engine using durable execution
How Formation Bio uses Pareto frontiers to analyze the high-water marks for drug development
How Formation Bio designs systems for sublinear scaling and compounding memory
How Formation Bio built a human-in-the-loop pipeline to make genetic insights operational at scale
How we built ARK – an MCP gateway that connects models, tools, and permissions to enable the next generation of AI-powered work at Formation Bio
How LLM-assisted processing transformed 260,000 unstructured clinical trials into 6.5 million structured components and embeddings
How Formation looks for “dark assets”– silently deprioritized candidates that may reveal hidden opportunity
Technical Architecture: Muse AI Recruitment Tool
In this post, we’ll explore the high-level architecture and key components that power Muse, offering a behind-the-scenes look at how we leverage OpenAI’s LLMs to create an efficient and effective tool for crafting recruitment strategies and content.
Formation Bio's AI Vision Statement
We envision a future where drug development is faster, more cost-effective, and significantly more likely to succeed, ultimately allowing us to achieve that mission - and AI is a key part of that vision.