> ## Documentation Index
> Fetch the complete documentation index at: https://docs.roserx.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Guidance & Guardrails
> Configure regulatory compliance settings, prohibited terms, approved claims, and off-label content policies for your agent.
Guidance and Guardrails is where you configure the regulatory compliance framework for your agent. These settings ensure your agent stays within approved boundaries, uses appropriate terminology, and handles sensitive topics correctly — all critical requirements in pharmaceutical and healthcare communications.
Access these settings by selecting an agent from the **Agents** list and clicking the **Guidance** tab.
## Primary configuration
Start by defining the fundamental regulatory context for your agent.
### Therapy type
Select the type of therapy or treatment your agent supports:
| Product type | Description |
| --------------- | ------------------------------------------------------------------- |
| **Therapeutic** | Pharmaceutical drugs and medicines |
| **Diagnostic** | Diagnostic tests and devices |
| **Device** | Medical devices (limited configuration options currently available) |
### Jurisdiction
Choose the regulatory jurisdiction that applies to your treatment or therapy area:
| Jurisdiction | Description |
| ----------------------- | ------------------------------------------------------------------ |
| **TGA (Australia)** | Therapeutic Goods Administration — Australian regulatory framework |
| **FDA (United States)** | Food and Drug Administration — United States regulatory framework |
### Primary audience
Confirm the intended audience for this agent:
* **Patient** — General public and consumers
* **HCP** — Healthcare professionals
* **Mixed** — Both patients and healthcare professionals
The primary audience is typically set when you create the agent, but you can confirm or adjust it here. This selection influences which compliance rules and guardrails are applied — for example, the Patient Query Handling section appears for Patient and Mixed audiences.
## Therapeutic classification
The classification options depend on the jurisdiction you selected. Each classification carries specific regulatory implications that affect how your agent communicates.
For therapeutic products regulated by the TGA, select the appropriate schedule:
| Schedule | Name | Description |
| -------- | -------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| **S2** | Pharmacy Medicine | Available from pharmacies without a prescription. Can be advertised to the general public with appropriate disclaimers. |
| **S3** | Pharmacist Only Medicine | Available from pharmacies but must be handed over by a pharmacist. Advertising is permitted with restrictions. |
| **S4** | Prescription Only Medicine | Requires a prescription from a qualified practitioner. |
**Schedule 4 (Prescription Only)** medicines have significant advertising restrictions under TGA regulations. In most cases, these products cannot be promoted directly to consumers. Your agent's guardrails will be configured accordingly.
For therapeutic products regulated by the FDA, select the appropriate classification:
| Classification | Description |
| ------------------------ | ------------------------------------------------------ |
| **OTC** | Over-the-counter. Available without a prescription. |
| **Rx** | Prescription only. Requires a valid prescription. |
| **Controlled Substance** | Subject to additional DEA scheduling and restrictions. |
When you select **Controlled Substance**, additional fields become available:
* **DEA Schedule** — Select the appropriate schedule (I–V)
* **Abuse potential** — Describe the known abuse potential
* **REMS program support** — Indicate whether the medicine participates in a Risk Evaluation and Mitigation Strategy program
Controlled substances are subject to strict federal regulations. Ensure your agent's configuration accurately reflects the applicable DEA schedule and any REMS program requirements before deploying to a live environment.
## Diagnostic test classification
If your therapy type is **Diagnostic**, additional classification fields appear.
### Test type
| Type | Full name | Description |
| -------- | ------------------------- | -------------------------------------------------- |
| **IVD** | In Vitro Diagnostic | Laboratory-based diagnostic test |
| **LDT** | Laboratory Developed Test | Test developed and used within a single laboratory |
| **DTC** | Direct-to-Consumer | Test marketed directly to consumers |
| **POCT** | Point-of-Care Test | Rapid test performed at or near the patient |
### Test purpose
| Purpose | Description |
| ----------------- | ----------------------------------------------------------------------------------- |
| **Screening** | Initial testing to identify potential conditions |
| **Diagnostic** | Confirmatory testing to establish a diagnosis |
| **Monitoring** | Ongoing testing to track disease progression or treatment response |
| **Companion** | Testing linked to a specific therapeutic treatment |
| **Complementary** | Testing that provides additional clinical information to inform treatment decisions |
You can also specify whether the test **requires an HCP order** and whether **genetic counseling** is required.
## Patient query handling
For agents with a **Patient** or **Mixed** audience, you control how the agent handles each category of patient question. Six categories are available:
| Category | Covers |
| ----------------------------------- | ------------------------------------------- |
| **Product information** | General questions about the product |
| **Safety & side effects** | Questions about risks and adverse reactions |
| **Dosing & administration** | How much to take and how to take it |
| **Healthcare provider information** | Finding or contacting a healthcare provider |
| **Misuse & abuse** | Questions suggesting inappropriate use |
| **Symptom & medical advice** | Requests for diagnosis or treatment advice |
Each category can be set to one of three behaviors:
* **Block** — The agent declines with a message you can customize per category.
* **Auto-respond** — The agent answers within its compliance boundaries.
* **Escalate** — The query is forwarded to a configurable email address, and the user is told their question has been passed on.
Most patient-facing agents block or escalate **Dosing & administration** and **Symptom & medical advice** queries, directing patients back to their healthcare provider.
## Disease, indications, and terminology
This section defines the approved clinical language your agent may use.
### Approved disease references
List the diseases and conditions your agent is permitted to discuss. Only diseases listed here will be referenced in responses — the agent will avoid discussing conditions outside this list.
### Approved indications and claims
Define the specific indications and claims that have been approved for your treatment or medicine. These are the statements your agent is authorized to make — for example:
* *"Indicated for the treatment of moderate to severe plaque psoriasis in adults"*
* *"Reduces the frequency of migraine headaches in patients with episodic migraine"*
Be precise with your approved indications. Copy these directly from your approved labeling, prescribing information, or regulatory submission to ensure accuracy and avoid introducing unapproved language.
### Terminology overrides
Define custom terminology the agent should recognize and use correctly — acronyms, brand names, and context-specific terms. This helps the agent interpret domain shorthand your audience uses and respond with your preferred wording.
## Prohibited terms
The RoseRx Platform allows you to define terms and phrases that your agent must never use. Prohibited terms are organized into five categories:
Common terms that could be misleading or non-compliant in a healthcare context.
**Default examples:** *"cure", "miracle", "breakthrough", "guaranteed", "100% effective"*
Terms relating to biological processes or mechanisms that may overstate the product's action.
**Default examples:** *"kills bacteria", "destroys cancer cells", "eliminates the virus"*
Claims that compare the product to competitors or overstate its performance.
**Default examples:** *"best in class", "superior", "outperforms", "number one"*
Phrases that could be interpreted as providing direct medical advice.
**Default examples:** *"you should take", "stop taking your medication", "this will help you"*
Add any additional terms specific to your medicine, organization, or regulatory requirements.
Each category comes with sensible default terms. Review these defaults carefully and add any additional terms specific to your medicine or therapy area and the regulatory environment in which it operates.
## Approved alternatives
For each prohibited term, you can map an **approved alternative** — a compliant phrase the agent should use instead.
| Prohibited term | Approved alternative |
| ----------------- | --------------------------------------------- |
| *"cure"* | *"may help manage symptoms"* |
| *"miracle"* | *"clinically studied"* |
| *"guaranteed"* | *"has been shown in clinical trials"* |
| *"best in class"* | *"demonstrated efficacy in clinical studies"* |
When the agent encounters a situation where it might use a prohibited term, it substitutes the approved alternative automatically.
Map as many prohibited terms to approved alternatives as possible. This helps the agent maintain natural, fluent responses while staying compliant.
## Off-label content policy
Configure how your agent responds when a conversation moves into off-label territory — that is, when a user asks about uses, dosages, or populations not included in the approved labeling.
| Policy | Behavior |
| ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Block** | The agent refuses to respond to off-label queries entirely, using a block message you can customize. |
| **Allow with Disclaimer** | The agent provides a response but includes a clearly visible disclaimer (customizable) stating that the information relates to off-label use. |
| **Redirect** | The agent does not answer the off-label query directly but redirects the user to approved content instead. |
| **Escalate** | The query is forwarded to a configurable email address, and the user is informed that their query has been escalated to a qualified representative. |
You can also maintain structured lists of **on-label and off-label indications** to help the agent detect when a conversation moves into off-label territory.
Off-label content policies have significant regulatory implications. Consult your regulatory and medical affairs teams before selecting a policy. In most cases, **Block** or **Redirect** is the safest choice for patient-facing agents.
## Best practices
* **Start with stricter settings** — It's easier to loosen guardrails after review than to tighten them after a compliance issue
* **Review default prohibited terms** — The defaults are a solid starting point, but every product has unique regulatory considerations
* **Align with your MLR process** — Ensure your guardrail configuration has been reviewed by your Medical, Legal, and Regulatory (MLR) team
* **Test thoroughly** — Use the [Batch Testing](/guides/testing/batch-testing) feature to verify your guardrails work as expected before publishing