What challenges did Promptly face before AI implementation?

Specialty medical practices relied on fragmented tools for scheduling, billing, patient messaging, insurance eligibility, and prior authorizations. Promptly's support and sales teams had to search manually across scattered documentation to answer questions. Developers lacked a shared AI assistant and consistent security posture for software development. The business needed to maintain security guardrails for protected health information while scaling AI experiences.

What was the impact of the AI solution?

Amazon Q Developer accounts for 30% to 40% of code written across the engineering team. Promptly reports about a 25% improvement in development speed and faster movement to beta. The Amazon Bedrock chat is live in production. An Amazon Bedrock AgentCore-powered version is entering beta with multiple clinic customers. Support specialists report quicker resolutions and higher satisfaction because answers from thousands of pages can be surfaced in seconds.

Source

Promptly (with DoiT): AI-first healthcare patient engagement using Amazon Bedrock and Amazon Q Developer

Use case typePatient engagementUpdated Jun 13, 2026

Promptly is a healthcare software-as-a-service company that helps specialty medical practices streamline patient engagement and automate clinical workflows. The company consolidated tens of thousands of documents from about 50 shared drives into an environment for generative AI applications and agents. Promptly integrated Amazon Bedrock into its web application to provide a conversational chat experience for patients. The chat helps patients with appointment scheduling, billing questions, and insurance questions without requiring a staff member. Promptly also uses Amazon Q Developer across its engineering sprints for code review and software development assistance. An internal assistant called the Oracle of Promptly was built for staff using AWS agent capabilities.

Organization: Promptly
Industry: Healthcare
Location: United States
Published: April 2026

Reported outcomes

40%

quantified impactOther quantified impact

30%quantified impact−25%time

Strategic outcomes

New product / capabilityLaunched patient-facing conversational supportSpeed & agilityAccelerated development and beta progressCustomer experience & trustImproved patient self-service supportBetter decisions & insightEnabled rapid knowledge retrieval for staff

Primary read

Use case focus

Showing 3 of 5

1Patient engagement
2Workflow automation
3Developer productivity

Specialty medical practices relied on fragmented tools for scheduling, billing, patient messaging, insurance eligibility, and prior authorizations.
Promptly's support and sales teams had to search manually across scattered documentation to answer questions.
Developers lacked a shared AI assistant and consistent security posture for software development.
The business needed to maintain security guardrails for protected health information while scaling AI experiences.

DoiT helped Promptly consolidate internal documentation into a centralized environment for generative AI applications and agents.
Promptly built a customer-facing conversational interface with Amazon Bedrock and embedded it in the web application.
The AI chat guides patients through scheduling, bill inquiries, and insurance questions.
Promptly adopted Amazon Q Developer for engineering productivity, using it throughout each sprint and for immediate code review before QA.
The team also built an internal assistant named the Oracle of Promptly using AWS agent capabilities for team-wide knowledge access.

Technologies

Amazon Bedrock Amazon Q Developer Amazon Bedrock AgentCore Amazon Bedrock Agents

Amazon Q Developer accounts for 30% to 40% of code written across the engineering team.
Promptly reports about a 25% improvement in development speed and faster movement to beta.
The Amazon Bedrock chat is live in production.
An Amazon Bedrock AgentCore-powered version is entering beta with multiple clinic customers.
Support specialists report quicker resolutions and higher satisfaction because answers from thousands of pages can be surfaced in seconds.

Architecture

DoiT connected tens of thousands of documents from approximately 50 shared drives into an environment for generative AI applications and agents. Promptly deployed a customer-facing chat widget in its web app using Amazon Bedrock. Engineering teams use Amazon Q Developer in sprint workflows, and an internal assistant was created using AWS agent capabilities. A version using Amazon Bedrock AgentCore is in beta.

Implementation partners1

DoiT International

Sources & evidence1

Groundedness: 5/5

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence