.svg){kind=icon}
2× Faster Screening. 9 Months Saved. 45% Fewer Protocol Deviations.
Outcomes
What we did
2x
Faster screening
9 Months
Recruitment cycle reduction
45%
Fewer protocol deviations
55%
Better forecast accuracy
About Company
This regional site network was anchored in Chicago, Illinois, with sites spanning the broader Midwest supporting a Phase III cardiometabolic study experienced uneven recruitment despite strong patient access.
Leadership implemented agentic AI to strengthen site operations and improve enrollment predictability.
The issue was not site commitment; it was limited visibility into early performance drift. Approximately 25–30% of sites were trending toward low enrollment with no early-warning mechanism in place.
Leadership implemented agentic AI to strengthen site operations and improve enrollment predictability.
The issue was not site commitment; it was limited visibility into early performance drift. Approximately 25–30% of sites were trending toward low enrollment with no early-warning mechanism in place.
Challenges
Key Barriers
to Trial Execution
Manual Screening
%201.svg){kind=icon}
Manual patient record evaluation
Slow and inconsistent screening
High coordinator dependency
Coordinator Workload
High workload across 3–5 studies
No AI support for eligibility checks
Late Deviation Detection
Deviations identified during monitoring
Too late to prevent impact on quality/timelines
Poor Forecasting
Reliance on historical averages
No real-time site performance signals
Core platform
Operational Solution
Maxis AI Agentic Workflows — Under Human Oversight Throughout
AI Patient Screening
Continuous eligibility evaluation
Pre-qualified candidates for coordinators
2× screening throughput
2× screening throughput
Real-Time Monitoring
Continuous enrollment tracking
Early alerts for deviation risks
45% fewer deviations
45% fewer deviations
Predictive Site Oversight
Early identification of at-risk sites
Proactive intervention enabled
Unified cross-study dashboards
55% better forecast accuracy
55% better forecast accuracy
Maxis AI operated as a governed and supervised execution layer within existing systems throughout.
Core platform
Measured Impact
Quantified Outcomes After Deploying Maxis AI’sAgentic Workflows
| Metric | Before Agentic AI | After Agentic AI |
|---|---|---|
| Screening Efficiency | Manual pace; coordinators evaluating full records per candidate | ~2× faster; recruitment cycle cut by up to 9 months |
| Protocol Deviations | Identified post-monitoring | Reduced by ~45% |
| Low-Performing Sites | ~25–30% of sites trending below target | <12% |
| Forecast Accuracy | Limited; leadership hesitant to expand beyond pilot programs | Improved by ~55% |
| Rescue Site Need | Likely — activation was being planned | Avoided entirely |
Outcomes
Leadership reported fewer escalations and more stable recruitment projections. Rescue-site activation avoided entirely.
Screening throughput doubled — recruitment cycle cut by up to 9 months
Protocol deviations reduced ~45%
Low-performing sites dropped from ~25–30% to <12%
Forecast accuracy improved ~55% — leadership expanded deployment
Looking for Agentic AI for clinical trials?
Explore our Agentic AI Platform to see how AI agents are transforming study startup, data management, oversight, and regulatory submissions.
