Skip to main content
The RoseRx Platform is made up of a set of interconnected concepts that work together to help you build, deploy, and monitor compliant AI agents. This page explains each one so you can navigate the platform with confidence.
New to RoseRx? We recommend reading through these concepts before diving into the detailed guides. It’ll make everything else much easier to follow.

​
How it all fits together

At a high level, the RoseRx workflow follows five steps:
1

Create an Agent

Choose your agent type and configure its AI model, tone, and response behavior.
2

Add Knowledge

Upload documents and URLs to build your agent’s knowledge base.
3

Configure Guardrails

Set regulatory compliance rules, prohibited terms, and off-label policies.
4

Deploy a Widget

Create an embeddable chat widget, customize its appearance, and go live.
5

Monitor & Refine

Track conversations, review adverse events, and improve your agent over time.

​
Core concepts

Agents are AI-powered conversational assistants — the heart of the RoseRx Platform. Each agent is configured to serve a specific therapy area and audience.The RoseRx Platform supports four agent types:
  • HCP Clinical Decision Support — Designed for physicians and primary care providers. Delivers jurisdiction-aware clinical information, dosing guidelines, and evidence-based recommendations grounded in approved materials.
  • Patient Navigator — Designed for patient and consumer audiences. Uses accessible, supportive language to provide health information in a way that is easy to understand.
  • Medication Navigator — A companion for patients on a prescribed medication, covering how to take it, interactions, side effects, and when to seek help.
  • Field Team Co-Pilot — A real-time support tool for pharma sales reps mid-conversation with an HCP, delivering fast, compliance-safe answers.
Each agent has its own:
  • AI model — The model tier powering the agent’s responses: Fast, Balanced, or Advanced.
  • Tone of voice — How the agent communicates (professional, empathetic, conversational, etc.).
  • Response length — How detailed or concise the agent’s replies are.
  • Compliance settings — Jurisdiction, guardrails, and regulatory configuration.
You can create multiple agents for different products, markets, or audiences — all managed from a single dashboard.
Sources are the content that forms your agent’s internal knowledge. When a user asks a question, the agent searches its knowledge base and retrieves the most relevant content to generate a grounded response.The Knowledge Base supports four source types: PDF documents, website URLs, Q&A pairs, and text snippets.How it works:
  1. You add sources to the Knowledge Base.
  2. The platform automatically processes each one — documents, URLs, and snippets are split into smaller chunks, embedded, and indexed.
  3. When a user asks a question, the agent first checks your Q&A pairs — an exact match returns your approved answer verbatim. Otherwise, it uses retrieval-augmented generation (RAG) to find and reference the most relevant chunks.
This approach means your agent’s responses are grounded in your approved materials rather than general AI knowledge, significantly reducing the risk of hallucination or off-label content.
Sources are internal to the agent. End-users never see the raw source documents — they only receive the agent’s generated responses. If you want users to access files directly, use Resources instead.
Resources are downloadable files and links that are surfaced directly to end-users through the widget’s Resources tab.Unlike Sources (which power the agent’s responses behind the scenes), Resources are visible, browsable content that users can access for reference — things like product brochures, consumer medicine information leaflets, or links to external websites.Use Resources when you want to give users something they can take away or refer to alongside the conversation.
Guardrails are the regulatory compliance settings that control what your agent can and cannot say. This is one of the most important configurations in the RoseRx Platform.Key settings include:
  • Jurisdiction — The regulatory framework your agent must comply with (e.g. TGA for Australia, FDA for the United States).
  • Product classification — Whether the product is a prescription medicine, over-the-counter medicine, medical device, supplement, or other type.
  • Prohibited terms — Specific words or phrases the agent must never use in its responses.
  • Approved claims — Statements the agent is permitted to make about the product.
  • Off-label content policies — Rules for how the agent responds to questions about unapproved uses or indications.
Properly configured guardrails are essential for regulatory compliance. Always review and test your guardrail settings before deploying an agent to a live environment.
Topics allow you to track and categorize what users are asking about. Each topic is defined by a set of keywords — when those keywords appear in a conversation, the topic is automatically detected and logged.This gives you insight into user interests and frequently discussed themes, helping you:
  • Identify trending questions or concerns
  • Spot gaps in your agent’s knowledge base
  • Report on conversation themes to stakeholders
For example, you might create a topic called “Side Effects” with keywords like adverse, reaction, side effect, and symptom to track how often users ask about safety.
The Adverse Events feature is the RoseRx Platform’s built-in pharmacovigilance system. It uses AI to automatically detect potential adverse drug reactions mentioned in conversations.When a user describes symptoms, side effects, or negative experiences that may be related to a treatment or medicine, the system flags the conversation for review. You can configure the sensitivity level to control how aggressively the system flags potential events.Flagged events are surfaced in the Adverse Events dashboard, where your team can review, assess, and take appropriate action in line with your pharmacovigilance obligations.
Adverse event detection is a support tool — it does not replace your organization’s pharmacovigilance processes. Always follow your established procedures for reporting and assessment.
Widgets are the embeddable chat interfaces that bring your agent to life on external websites. A widget is the user-facing component — it’s what your audience sees and interacts with.Each widget is linked to an agent and can be fully customized:
  • Widget type — Popup, fullscreen, or slider layout.
  • Theming — Brand colors, logos, and custom styling.
  • Tab configuration — Choose which tabs are visible (Chat, Resources, etc.).
  • Domain restrictions — Limit which websites can display the widget.
  • Status — Toggle between Active and Inactive without removing the embed code.
To deploy a widget, simply copy the embed snippet and paste it into your website’s HTML.
Initiatives are country-specific campaigns that group related deployments and widgets together. They provide an organizational layer that helps you manage multi-market rollouts.For example, if you’re launching a treatment or campaign in both Australia and New Zealand, you might create separate initiatives for each country — each with its own widgets, compliance settings, and reporting.
Batch Tests are the RoseRx Platform’s built-in quality assurance system for validating agent responses before deployment. You define a set of test questions and expected behaviors, then run them against your agent to check that it responds correctly.This is especially useful for:
  • Verifying compliance after updating guardrails
  • Checking response quality after adding new knowledge
  • Regression testing before going live with changes
Run batch tests regularly — especially after making changes to your agent’s knowledge base or guardrails — to catch issues before they reach your users.
The Audit Log is a comprehensive activity trail that records every significant action taken across the platform. This includes agent creation, configuration changes, widget deployments, user logins, and more.The audit log supports your governance and compliance requirements by providing a clear, searchable record of who did what and when.
HCP Verification is a verification gate that ensures only qualified healthcare professionals can access restricted content. When enabled on a widget, users must verify their identity before accessing gated content — through AHPRA (the Australian Health Practitioner Regulation Agency) in Australia, or their NPI (National Provider Identifier) in the United States.This is essential for HCP-facing agents that surface clinical or restricted product information that should not be accessible to the general public. Verified professionals are recorded in the HCP Contacts directory.
Workflows let patient-facing agents route users to the right care. The Appointment Finder sub-agent activates when a patient asks to see a doctor, works through your configured intake questions one at a time, and guides them to an enabled care pathway — telehealth (with a booking link) or an in-person appointment.See Workflows for configuration details.
Roleplay Training is a voice-based practice simulator for field teams. Reps make simulated calls to AI-played HCP personas, pitch a product, and receive an AI-graded scorecard with coaching notes. Admins configure the personas, product cards, compliance rules, and scoring; managers track team performance on a leaderboard.Sales Engagement is an optional module — contact your RoseRx representative to enable it. See Roleplay Training to get started.

​
What’s next?

Now that you understand the building blocks, start putting them into practice:

Quick Start

Follow the step-by-step guide to create and deploy your first agent.

Creating an Agent

Learn how to set up and configure an agent in detail.

Knowledge Base

Add documents and URLs to power your agent’s responses.

Deploying a Widget

Create and embed a chat widget on your website.