"The scarcest resource in clinical trials is the time of the highly qualified people running the clinical trials. We need to free up their time to bring more meaningful innovation to patients." - David Hyman, Chief Medical Officer, Eli Lilly

Since the year 2000, the pace of drug approvals has remained stubbornly slow, with the FDA approving roughly 50 new treatments per year. This pace is in spite of massive increases in R&D investment. It’s well known that clinical trials take 10-12 years on average to complete all four phases. But what if clinical trials didn’t take weeks to start, months to enroll, and years to complete?

At Medable, our mission has always been to use technology to bring more effective therapies to patients faster. We call this vision 1:1:1.

Defining 1:1:1

At its core, 1:1:1 is simple but transformative:

  • 1 day study startup
  • 1 day patient enrollment
  • 1 year study conduct

Achieving this requires more than incremental improvements. It demands a shift from fragmented tools to intelligent, integrated, and autonomous systems, moving from systems of record to systems of outcome.

Today, highly trained clinical experts spend too much of their time navigating systems, assembling information, and reconciling signals rather than applying their expertise to what matters most: patient safety, therapy effectiveness, and scientific progress. Eliminating this structural friction is where agentic AI becomes transformative.

Tangible progress toward 1:1:1

In 2017, Tufts CSDD found it took an average of 8.1 days to enter patient visit data into site EDCs. That gap exemplifies the "operational whitespace" that has plagued trials since technology first entered them.

AI-enabled eCOA can compress startup and improve data capture, but much of the remaining delay lives in cross-system workflows and inter-phase decisions. Agentic workflows address this whitespace by aggregating information across systems, surfacing trends and risks, and recommending next best actions, all while preserving governance and credentialed control.

Current examples include:

  • TMF-focused agents that classify and route artifacts into the correct TMF locations with minimal human handling
  • Clinical monitoring support agents that summarize recent study activity, flag deviations and emerging risks, and reduce the need to log into numerous systems
  • App-building frameworks that let ecosystem partners build validated, compliant workflows on top of agent capabilities using pre-configured clinical trial components

The operational value is time recapture. If a CRA no longer spends hours compiling study status across systems, that time returns to higher-value work: patient safety, deviation detection, and decision-making.

In the past two years, with AI and agentic capabilities, we’ve seen real progress and promise in working toward our 1:1:1 vision. In some instances with top customers, we’ve turned around a study build in just 1 day (CASE STUDY LINK), cut translation time in half (CS LINK), all while maintaining and improving patient and site adherence (CS LINK). Based on internal research we forecast that most remote clinical monitoring task time can be cut by 80%.

Further opportunities for agentic application

Site activation. Traditionally sequential, involving site selection, contracting, regulatory submissions, training, and deployment, with handoffs that create delays. Agentic AI enables parallel execution by preparing site packages during contract negotiation, scheduling training dynamically, and flagging risks before they delay activation. These systems also learn from past activations, improving over time across sites, regions, and study types.

Data management and monitoring. Manual review across systems creates bottlenecks that delay database lock. Agentic AI replaces reactive review with continuous, automated oversight, ingesting data in real time, detecting anomalies, generating and prioritizing queries, and coordinating resolution with sites. CRAs are freed from fragmented, periodic reviews.

Integrated decision-making. By unifying data across systems and functions, agentic AI provides a single view of trial performance and can accelerate work like protocol drafting by synthesizing regulatory and scientific inputs.

Across all of these, agentic AI replaces idle time with continuous progress, ensuring that the gaps between milestones actively advance the study rather than delay it.

The path forward

The path to 1:1:1 won't be defined by a single breakthrough, but by the steady removal of friction across every stage of clinical development. What look like isolated inefficiencies are really systemic gaps between people, data, and decisions. AI and Agentic AI help close those gaps, not by replacing human expertise, but by amplifying it.

The future of clinical development will be measured not only by speed, but by how effectively we use that speed to expand access, increase quality, and deliver more therapies to more patients. 1:1:1 is not just an aspiration. It is a direction of travel, and the work to realize it has already begun.

‍