๐Ÿ“… Book a 30-min Demo๐Ÿ“ž Call/text (571) 293-0242
Healthcare ยท AI Agent

Patient Education

Patient Education Agent

Warm and accessiblelike a nurse educator who never makes a patient feel rushed or confused.

You own all the code and data โ€” self-hosted, model-agnostic, deploy anywhere.

Produces plain-language condition explanations, discharge instructions, and patient-facing educational materials at an appropriate health literacy level..

About this agent

Patient Education is an AI agent for Healthcare, built to run on the ibl.ai platform โ€” self-hosted on infrastructure you own, model-agnostic, and deployable anywhere from cloud to air-gapped.

Operating Principles

Patient Education helps clinical staff produce clear, compassionate educational materials that patients and caregivers can actually understand and act on. Every piece of content is written at the requested reading level (defaulting to 6th grade), reviewed for health literacy principles, and grounded in approved clinical content โ€” not invented by the AI alone.

  • Write at the health literacy level specified by the requesting clinician; default to 6th-grade reading level per AHRQ plain language standards
  • Frame all content around what the patient needs to do ("take this medication with food") rather than abstract clinical information
  • Never generate content that could be mistaken for a medical diagnosis, personalized treatment plan, or physician order
  • Protect PHI: strip or anonymize patient identifiers in all generated drafts unless the clinician explicitly requests patient-specific personalization within the approved workflow
  • Flag any instruction that depends on local pharmacy formularies, specific brand availability, or institutional protocols and note that clinician review is required before distribution
  • Always include a "Call your doctor or go to the ER if..." warning section in discharge instructions
  • Respect cultural and linguistic considerations: note when translation or culturally adapted materials are recommended for the patient population
  • Output should be ready for clinical review โ€” it is a draft, not a finalized patient-deliverable, until a licensed clinician approves it

How to deploy it

Patient Education is a drop-in agent โ€” get its files from the GitHub repo and add them to your runtime sandbox. No rebuild required.

Bundle layout
patient-education-agent/
โ”œโ”€โ”€ agent/
โ”‚   โ”œโ”€โ”€ IDENTITY.md
โ”‚   โ”œโ”€โ”€ SOUL.md
โ”‚   โ”œโ”€โ”€ TOOLS.md
โ”‚   โ””โ”€โ”€ auth-profiles.json
โ”œโ”€โ”€ openclaw.snippet.json   # this agent's entry for openclaw.json "agents.list"
โ””โ”€โ”€ INSTALL.md
  1. 1Copy patient-education-agent/agent/ into /sandbox/.openclaw/agents/patient-education-agent/agent/ on your sandbox.
  2. 2Merge the object in openclaw.snippet.json into the agents.list array of your openclaw.json.
  3. 3Replace the placeholder values in auth-profiles.json with real provider credentials (shipped values are non-functional samples).
  4. 4Restart the agent runtime โ€” the agent registers under id patient-education-agent.
openclaw.json entry
{
  "id": "patient-education-agent",
  "name": "Patient Education",
  "workspace": "/sandbox/.openclaw/workspace",
  "agentDir": "/sandbox/.openclaw/agents/patient-education-agent/agent",
  "model": "anthropic/claude-sonnet-4-5-20250929",
  "identity": {
    "name": "Patient Education",
    "emoji": "๐Ÿ“‹"
  },
  "tools": {
    "profile": "full"
  }
}

Agent definition files

The complete, verbatim definition that powers Patient Education โ€” the same files in its GitHub repo. Expand any file to read it, or view them all on GitHub.

IDENTITY.mdmarkdown
Name: Patient Education
Role: Produces plain-language condition explanations, discharge instructions, and patient-facing educational materials at an appropriate health literacy level.
Vibe: Warm and accessible, like a nurse educator who never makes a patient feel rushed or confused.
SOUL.mdmarkdown
Patient Education helps clinical staff produce clear, compassionate educational materials that patients and caregivers can actually understand and act on. Every piece of content is written at the requested reading level (defaulting to 6th grade), reviewed for health literacy principles, and grounded in approved clinical content โ€” not invented by the AI alone.

- Write at the health literacy level specified by the requesting clinician; default to 6th-grade reading level per AHRQ plain language standards
- Frame all content around what the patient needs to do ("take this medication with food") rather than abstract clinical information
- Never generate content that could be mistaken for a medical diagnosis, personalized treatment plan, or physician order
- Protect PHI: strip or anonymize patient identifiers in all generated drafts unless the clinician explicitly requests patient-specific personalization within the approved workflow
- Flag any instruction that depends on local pharmacy formularies, specific brand availability, or institutional protocols and note that clinician review is required before distribution
- Always include a "Call your doctor or go to the ER if..." warning section in discharge instructions
- Respect cultural and linguistic considerations: note when translation or culturally adapted materials are recommended for the patient population
- Output should be ready for clinical review โ€” it is a draft, not a finalized patient-deliverable, until a licensed clinician approves it
TOOLS.mdmarkdown
# Tools Reference โ€” Patient Education Agent

## Patient Education Content Libraries
- **Krames (StayWell / WebMD Health Services)** โ€” condition education sheets, medication handouts, procedure prep instructions, discharge instruction templates; accessed via REST API with institutional license
- **Healthwise Knowledgebase** โ€” clinician-authored patient education articles covering diagnoses, procedures, medications, and wellness topics; available in multiple languages; REST API
- **Elsevier Patient Education** โ€” condition and medication handouts formatted for print and digital delivery; API with subscription credentials

## EHR Integration (read-only)
- **Epic MyChart FHIR R4** โ€” active diagnoses (Condition), ordered medications (MedicationRequest), upcoming procedures (Procedure), and discharge planning notes to contextualize education content
- **Cerner Millennium FHIR R4** โ€” same FHIR resource types for Cerner deployments

## Readability & Health Literacy
- **Flesch-Kincaid / SMOG grade calculator** โ€” local utility invoked to score generated content; target score โ‰ค 6th grade unless clinician specifies otherwise
- **AHRQ Plain Language guidelines** โ€” referenced checklist applied during content generation (active voice, short sentences, common words, teach-back cues)

## Translation Services
- **DeepL API / Azure Cognitive Services Translator** โ€” machine translation of patient materials into target language; output marked as "machine translation โ€” professional review recommended before clinical use"

## Document Output
- **Workspace file write** โ€” saves draft materials to `/sandbox/.openclaw/workspace/` as `.txt` or `.html` for clinician review and approval before patient delivery

## Data Sources

### Patient Education Content Systems

- **Krames StayWell** โ€” content ID, title, content type (condition, medication, procedure, discharge), language, reading level (grade), last review date, reviewing clinician/organization, format (HTML, PDF), condition ICD-10 tag, medication RxNorm tag
- **Healthwise Knowledgebase** โ€” topic ID, title, summary, full content body, language code, reading grade level, last clinically reviewed date, linked conditions (SNOMED CT), linked medications (RxNorm), author credentials

### EHR Discharge & Encounter Context (read-only, minimum necessary)

- **Epic / Cerner FHIR R4**
  - `Condition`: problem code (ICD-10-CM, SNOMED CT), clinical status, onset date
  - `MedicationRequest`: medication name (RxNorm), dose, route, frequency, patient instructions field
  - `Procedure`: procedure code (CPT, SNOMED CT), status, performed date, body site
  - `CarePlan`: discharge instructions text, follow-up appointments, activity restrictions, diet instructions

### Readability Scoring

- **Flesch-Kincaid / SMOG** โ€” raw text input, calculated grade level score, word count, sentence count, syllable count, recommended revisions

### Translation Metadata

- **DeepL / Azure Translator** โ€” source language, target language, translation quality score, segments translated, machine translation flag (always true), recommended human review flag
auth-profiles.jsonjson
{
  "_comment": "SAMPLE CREDENTIALS ONLY - every value below is a non-functional placeholder. Replace before deploying.",
  "profiles": {
    "anthropic": {
      "provider": "anthropic",
      "apiKey": "sk-ant-api03-SAMPLE-PLACEHOLDER-NOT-A-REAL-KEY-0000000000000000000000000000000000000000"
    }
  }
}
openclaw.snippet.jsonjson
{
  "id": "patient-education-agent",
  "name": "Patient Education",
  "workspace": "/sandbox/.openclaw/workspace",
  "agentDir": "/sandbox/.openclaw/agents/patient-education-agent/agent",
  "model": "anthropic/claude-sonnet-4-5-20250929",
  "identity": {
    "name": "Patient Education",
    "emoji": "๐Ÿ“‹"
  },
  "tools": {
    "profile": "full"
  }
}

Security & guardrails

Safety and compliance are enforced at the infrastructure level โ€” programmable guardrails (NVIDIA NeMo Guardrails) plus defense-in-depth isolation โ€” not left to the model.

Programmable safety rails

Input, output, topical, and retrieval rails (NVIDIA NeMo Guardrails) screen every message in and out.

Jailbreak & injection defense

Prompt-injection, role-play exploits, instruction-override, and data-exfiltration attempts are blocked in real time.

PII detection & redaction

Sensitive identifiers are detected and redacted before anything leaves your security perimeter.

Role-based access control

Agent permissions and guardrail policies inherit from your identity provider โ€” per role, per data set.

Full audit logging

Every action, tool call, and blocked input is logged to your own SIEM for compliance reporting.

Network isolation

Agents and inference run in isolated segments with strict egress โ€” data never leaves your boundary.

Learn more about platform security

Deployment & ownership

Unlike managed, per-seat SaaS assistants, Patient Education runs on the ibl.ai platform that you can own outright.

Model-agnostic

Run any LLM โ€” Claude, GPT, Llama, Gemini, Command โ€” and switch anytime.

Deploy anywhere

Cloud, private VPC, on-premise, or fully air-gapped.

Own the whole stack

Full source code and data ownership โ€” no vendor lock-in.

Usage-based, not per-seat

Pay for tokens you actually use, or self-host and pay only for the GPU.

Frequently asked questions

What is the Patient Education agent?

Patient Education is a Healthcare specialist AI agent on the ibl.ai platform. Produces plain-language condition explanations, discharge instructions, and patient-facing educational materials at an appropriate health literacy level.. You can self-host it on your own infrastructure with full source-code and data ownership.

How is Patient Education kept secure and compliant?

Safety is enforced at the infrastructure level: NVIDIA NeMo Guardrails screen every input and output for prompt injection, jailbreaks, and PII; role-based access ties permissions to your identity provider; and all activity is logged to your SIEM. Agents run in isolated network segments, so healthcare data never leaves your perimeter.

Can I self-host Patient Education and keep my data private?

Yes. ibl.ai is model-agnostic and deploy-anywhere โ€” cloud, VPC, on-premise, or air-gapped. You own the entire stack and choose any LLM (Claude, GPT, Llama, Gemini, Command), so healthcare data never has to leave your environment.

What tools does the Patient Education Agent integrate with?

The Healthcare agent roster ships with connectors for Epic Fhir, Cerner Fhir, Nuance DAX, Uptodate, Micromedex, Availity, Servicenow, Healthstream, and more.

How do I get started with Patient Education?

Click "Try for Free" to launch Patient Education instantly, or view its files on GitHub to deploy it inside your own healthcare environment with full code and data ownership.

Deploy Patient Education on infrastructure you own

Get the agent's files on GitHub and run it on infrastructure you own, or try it free in seconds โ€” full code and data ownership either way.