How One Medicare Org Cut Broker Lookups From 8 to 2 Min

A Medicare team piped provider, formulary, and cost data into broker and clinician AI assistants — cutting lookups from 8 to 2 minutes and freeing 40K broker hours a year.

75%

Cut broker lookup time to 2 min

4–8 weeks

Implementation Time

Jordan Gurrieri

Co-founder & CEO

BlueLabel

Connect ↓

The Challenge

The client needed to make Medicare decision-making faster, clearer, and more personalized across the full member, broker, and clinician journey. Before the engagement, critical information about providers, medications, formularies, coverage, and out-of-pocket costs was fragmented across complex workflows, making it difficult for seniors to compare plans, brokers to answer enrollment questions quickly, and clinicians to discuss cost-aware care options at the point of care. BlueLabel was brought in to help the partner safely embed AI into its Medicare Advantage ecosystem through rapid conversational AI experiments, a broker assistant prototype, and a clinician-facing copilot inside its core care platform. The work also created a repeatable AI experimentation lane, helping the organization test, validate, and scale high-value AI use cases with lower risk.

What They Built

BlueLabel helped a national Medicare Advantage organization design and implement a connected portfolio of AI-powered healthcare tools that made complex coverage, cost, and care information easier to access and act on. The work began with conversational AI experiments that explored how seniors could compare doctors, medications, plan options, and out-of-pocket costs through a simpler, more natural experience. From those learnings, BlueLabel built a broker-facing AI assistant that brings fragmented provider, formulary, plan, and coverage data into a single natural-language workflow, helping brokers answer questions like whether a doctor is in-network, whether a medication is covered, and what a member may pay under a specific plan. BlueLabel also supported clinician-facing AI workflows that surface formulary tiers, drug cost information, and lower-cost alternatives at the point of care, helping providers have more transparent, cost-aware conversations with patients. In parallel, BlueLabel helped the organization establish a repeatable AI experimentation and implementation process, including rapid prototyping, user feedback loops, compliance-aware design, and integration planning for embedding AI assistants into core operational systems. Together, the work moved AI from isolated pilots toward practical, workflow-ready tools for members, brokers, clinicians, and care teams.

The solution created value by turning scattered provider, formulary, plan, and cost information into fast, searchable answers inside the workflows people already used. Instead of brokers or clinicians manually checking multiple systems to resolve complex coverage and medication questions, the AI assistant could retrieve the relevant information, synthesize it, and present a clear answer in natural language. That reduced lookup time, improved consistency, and made it easier for teams to help members make informed decisions.

BlueLabel implemented the program through its SPRINT framework, using rapid two-week cycles to move from strategy to working AI prototypes and embedded workflow design. The engagement began with a two-week planning and discovery sprint, where BlueLabel aligned with the client's leadership team, prioritized the highest-value Medicare workflows, reviewed technical and data considerations, and mapped the first set of user stories and success criteria.

From there, BlueLabel moved into a series of two-week rapid prototyping sprints. The first sprints focused on testing conversational AI experiences for member-facing plan guidance, including questions around providers, medications, coverage, and out-of-pocket costs. Those early experiments helped the team quickly learn which use cases were most valuable and which ideas should be refined, expanded, or stopped.

The next sprints turned those learnings into more structured workflow tools. BlueLabel built and iterated on a broker-facing assistant that unified provider, plan, and formulary data into a natural-language experience. The team validated the assistant around real enrollment questions, refined the experience through stakeholder feedback, and prepared the prototype for broader pilot and scaling decisions.

In parallel, BlueLabel extended the same cost-and-coverage intelligence into clinician-facing workflows, helping bring formulary tiers, member-specific medication costs, and lower-cost alternatives into the point-of-care experience. This required additional sprint cycles focused on technical discovery, integration planning, testing, feedback capture, and workflow fit.

The initial program moved from discovery to validated MVP direction in roughly 10–14 weeks: one two-week discovery sprint followed by approximately four to six two-week implementation sprints. As the highest-value use cases became clearer, the engagement continued through additional sprint cycles focused on validation, integration, feedback loops, and roadmap planning. This gave the client a repeatable AI experimentation lane: fast enough to learn every two weeks, structured enough to make confident go/no-go decisions, and practical enough to move promising AI concepts toward production-ready workflows.

AI Role

The AI retrieves relevant provider, plan, formulary, medication, and cost information, then synthesizes it into clear natural-language answers for brokers and clinicians. In the broker workflow, it helps answer coverage questions like whether a provider is in-network or what a medication may cost under a plan. In the clinical workflow, it surfaces formulary tiers, member-specific drug costs, and potential lower-cost alternatives for review at the point of care.

AI Model

Custom / proprietary

Infrastructure

Provider, plan, formulary, and drug-cost data sources • Client's core care platform (clinician point-of-care workflows) • Core enrollment and operational systems (broker workflows)

Integration Points

Not disclosed.

Impact

75% faster complex question resolution

Reduced estimated broker lookup time from 8 minutes to 2 minutes for complex provider, medication, and coverage questions.

Up to 40,000 broker hours saved annually

Projected annual savings if the assistant scales from a 100-broker pilot to roughly 300 active brokers.

3,000+ clinician hours saved annually

Projected annual time savings if the clinician assistant scales to 100,000+ members.

Technology Utilized

Implementation Complexity

No items found.

The hardest part was managing the complexity of a fast-evolving AI engagement inside a large healthcare organization. What started as a focused enrollment prototype quickly uncovered higher-value opportunities for brokers and clinicians, so BlueLabel had to keep the work moving while adapting to new stakeholders, shifting priorities, and real-world feedback.

Best Fit For

Organizations with complex, high-touch workflows, fragmented information, and teams that need faster, clearer decision support would benefit most from this type of AI solution.

Jordan Gurrieri

Co-founder & CEO

BlueLabel

Co-founder & CEO of BlueLabel, leading generative AI innovation and digital transformation for enterprises across healthcare, finance, travel, and real estate.

Connect with the Expert

Industry:

Healthcare & Life Sciences

Business Function:

Operations

Company Size:

251-1,000

Project Cost:

$100K – $250K

Ownership:

Public Company

Organization Type:

Public Company

AI Pattern:

Knowledge Management & Search (RAG)

Value Type:

No items found.

AI Model:

Custom / proprietary