[AI]AWS and Bluesight build AI for hospital 340B compliance

[ChatGPT 0]

This is the hidden content, please

• Sign In
• or
• Sign Up

(

This is the hidden content, please

• Sign In
• or
• Sign Up

Web Services) has explained how

This is the hidden content, please

• Sign In
• or
• Sign Up

developed Prism, an AI layer that connects hospital pharmacy and compliance data across its product suite.

Prism Assistant for ControlCheck has reached general availability and operates across 20 health systems, according to AWS vendor statements. Meanwhile, a multi-product agent for 340B Group Purchasing Organisation (GPO) compliance remains scheduled for release later in 2026.

The project addresses a data-intensive process that hospital pharmacy teams often conduct manually. AWS says a single 340B covered entity can spend more than 4,000 staff hours each year reviewing whether GPO drug purchases qualify for an exception. Staff must compare purchase data with US Food and Drug Administration shortage notices, American Society of Health-System Pharmacists records, days-on-hand inventory, machine learning shortage forecasts, and back-order reports from other hospitals.

ControlCheck agent reaches 20 hospital health systems

Bluesight started with ControlCheck, its controlled-substance monitoring product. Hospital diversion teams use ControlCheck to identify unusual medication transaction patterns, but compliance staff still needed to assemble reports, review dashboards, and correlate findings manually.

Prism Assistant gives users a conversational interface that can query ControlCheck data, produce charts, and generate report material. AWS claims Bluesight built the first version during a three-day Experience-Based Acceleration engagement in September 2025, with eight Bluesight engineers working alongside seven AWS specialists. TechForge Media notes that while these rapid development timelines highlight the agility of the tools, they remain vendor-reported metrics pending independent verification from the active health systems themselves.

The team used Strands Agents with

This is the hidden content, please

• Sign In
• or
• Sign Up

Bedrock and hosted the application through

This is the hidden content, please

• Sign In
• or
• Sign Up

Bedrock AgentCore Runtime. AgentCore Gateway exposed more than 10 ControlCheck APIs as MCP tools, allowing the agent to discover and call them during a user request.

Crucially, Bluesight avoided direct database access for the language model. Its engineers wrapped existing ControlCheck API endpoints in AWS Lambda functions that return structured data suited to agent processing. The company kept business logic inside its application layer, while the agent interpreted questions, selected tools, gathered records, and presented results.

AWS reports that design reduced query latency from five minutes to 10 seconds. The deployment also included a frontend with chart generation, observability controls, cost attribution, encryption, authentication, and infrastructure-as-code.

“This is exactly what diversion program leaders have been waiting for—it gets them to answers faster and takes the manual grind out of every investigation,” said Samir Neyazi, Director of Product Management at Bluesight.

Bluesight deployed the service within a virtual private cloud and reached general availability in under nine months, according to AWS. The 20 health systems using Prism Assistant represent the active deployment evidence in the AWS account; the larger GPO agent has not yet reached that stage.

Multi-agent 340B compliance targets GPO purchases

Federal 340B rules prohibit Disproportionate Share, Children’s, and Free-Standing ******* hospitals from buying outpatient drugs through GPO contracts when non-GPO channels can supply the drug. Compliance teams must document the exception when supply conditions prevent that purchase route.

Bluesight’s planned GPO agent brings together records from CostCheck, ShortageCheck, and 340BCheck. CostCheck provides purchase information, ShortageCheck contributes drug availability evidence, and 340BCheck validates eligibility data.

The proposed architecture uses Anthropic Claude Sonnet 4.6 as the primary model and Claude Haiku 4.5 for lower-latency operations through

This is the hidden content, please

• Sign In
• or
• Sign Up

Bedrock. AgentCore Runtime executes the agents in a VPC with private subnets. AgentCore Gateway connects Lambda-backed tools to the three Bluesight product systems.

A coordinating GPO agent directs specialist data workers. One worker retrieves purchase records, another gathers supply evidence, and another checks 340B eligibility. The coordinator assembles the evidence and produces an audit-oriented report.

March 2026 brought a second AWS acceleration engagement focused on that architecture. AWS says the team connected the system by the end of its first day and completed every planned feature by the end of day two. The company tested the agent against synthetic data, where it reported a 100 percent invoice discovery rate and 93 percent evidence justification accuracy, above its 85 percent target.

However, enterprise buyers must exercise caution: those figures do not represent production performance across hospital customers. Synthetic testing can demonstrate whether tool calls, matching logic, and report generation work against prepared scenarios, but it cannot establish how the system handles local data gaps, delayed shortage updates, unusual drug identifiers, or disputed purchasing cases.

Keeping compliance scoring outside the language model

Bluesight assigns the language model a constrained role in the GPO workflow. The model gathers records, calls product tools, and drafts the explanation. A deterministic scoring service calculates the compliance determination.

That service evaluates 13 evidence inputs, applies priority-based matching, and uses configurable time windows. The design gives compliance teams a repeatable scoring process rather than an LLM-generated judgement and allows an auditor to inspect the source records, the rules applied, and the sequence of tool calls behind each determination.

Despite the automated assistance, hospital pharmacy, legal, and compliance teams still need absolute ownership of those policy settings. A supplier shortage threshold, acceptable inventory *******, or purchase-date window can alter a compliance outcome. Bluesight’s approach gives customers a technical mechanism to configure those decisions, but each organisation must set and approve its own policy rules.

HIPAA controls and audit traces shape the deployment

This is the hidden content, please

• Sign In
• or
• Sign Up

Bedrock holds HIPAA eligibility, and Bluesight operates under a Business Associate Agreement with AWS. AWS says it does not train foundation models on customer data processed through

This is the hidden content, please

• Sign In
• or
• Sign Up

Bedrock.

Bluesight uses

This is the hidden content, please

• Sign In
• or
• Sign Up

Cognito for OAuth2 client-credential authentication and JSON Web Token validation. AgentCore Runtime provides session isolation for concurrent customer requests. AWS Key Management Service encrypts data at rest and in transit, while AWS Secrets Manager manages credentials for downstream services.

This is the hidden content, please

• Sign In
• or
• Sign Up

CloudWatch records agent decisions, tool invocations, data-access events, alarms, and performance metrics. That audit trail matters when a hospital needs to explain why it permitted a GPO purchase or escalated a drug-diversion pattern.

Bluesight’s internal measurements across 20 health systems report up to 97 percent faster report generation and analysis in ControlCheck workflows. Recurring reports reportedly dropped from about six hours of manual assembly to 15 minutes, a 96 percent reduction. Pre-investigation triage dropped from three hours to about 10 minutes, while controlled-substance variance analysis fell from 30 minutes to less than one minute.

Teams should strictly run historical purchasing cases in parallel with existing review processes before allowing an agent-assisted result to affect compliance decisions. Local testing should rigorously examine data completeness, drug-code matching, shortage timing, exception rules, and cases where human reviewers previously disagreed. Each production finding should retain the scoring-rule version, source evidence, and tool trace that produced it.

See also:

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

Want to learn more about AI and big data from industry leaders? Check out

This is the hidden content, please

• Sign In
• or
• Sign Up

taking place in Amsterdam, California, and London. The comprehensive event is part of

This is the hidden content, please

• Sign In
• or
• Sign Up

and is co-located with other leading technology events including the

This is the hidden content, please

• Sign In
• or
• Sign Up

. Click

This is the hidden content, please

• Sign In
• or
• Sign Up

for more information.

AI News is powered by

This is the hidden content, please

• Sign In
• or
• Sign Up

. Explore other upcoming enterprise technology events and webinars

This is the hidden content, please

• Sign In
• or
• Sign Up

.

The post

This is the hidden content, please

• Sign In
• or
• Sign Up

appeared first on

This is the hidden content, please

• Sign In
• or
• Sign Up

.

This is the hidden content, please

• Sign In
• or
• Sign Up