Your brand voice, glossary and content rules, applied to every document
Set your rules once. HealthLiteracyCopilot uses them each time it revises, translates or creates. It checks each draft against them before your reviewer signs off.
Work under your rules
What it does
- One rule set, many brands: child profiles inherit the rules and override only what differs.
- Your voice and reading level: tone, a target grade from 4 to 16, and a target per document type.
- A versioned glossary of preferred terms and acronyms, checked on every draft.
- More than 30 healthcare content types, each with a purpose, a structure and required parts.
- Approved disclaimers inserted word for word; protected terms kept exactly in English and Spanish.
- Policy packs: versioned rule sets that block or warn. A published version can't be changed.
Setup
Start from the style guide you already have
Upload it. HealthLiteracyCopilot reads it and drafts your profile. Nothing applies until your owner reviews and approves it.
1 · Upload your style guide
The one your team already uses.
2 · A drafted profile, for review
- VoiceReview
- Warm, direct, "you" and "we"
- Reading levelReview
- Grade 6 target; notices grade 5
- TermsReview
- 214 glossary terms found
- DisclaimersReview
- 3 approved blocks
- Sub-brandsReview
- Medicare, Medicaid, Commercial
- AudiencesReview
- Members and caregivers
Illustrative · synthetic values.
3 · Your owner approves
Adjust, import your glossary, mark required words as exceptions, then approve.
The rule set
Six kinds of rules, checked on every draft
Revise, Translate and Create all follow the same profile. Each draft shows which rules it was checked against.
Glossary
A versioned list of preferred terms and acronyms, checked on every draft.
Protected terms
Required words stay exactly as written in English and Spanish. Approved exceptions do not push the grade up.
Approved disclaimers
Inserted from approved text, word for word. Never generated or machine-translated.
Reading level
A target grade from 4 to 16, with a different target per document type if you need one.
Content types
More than 30 healthcare content types, each with a purpose, a structure and required parts.
Policy packs
Versioned rule sets that block or warn. Test a change first. A published version can't be changed.
Illustrative · synthetic rules and values.
How it works
Step 1: Upload your style guide
HealthLiteracyCopilot reads it and fills in voice, terms, reading level, disclaimers, sub-brands and audiences for you to review.
Step 2: Approve the settings
Adjust the profile and import your glossary. Mark required words, such as "Medicaid", as exceptions so they don't push the grade up. The owner approves them.
Step 3: Work as usual
Revise, Translate and Create apply the profile. The output lands on your brand Word template.
Step 4: See what was enforced
Each draft shows its glossary checks, policy-pack results and inserted disclaimers before a reviewer approves it.
A policy pack and a glossary (illustrative values)
Policy pack v3 · published
Grade 6 or lower (Flesch-Kincaid) · forbidden: "per your request" · required: appeal rights · block on fail
Glossary · 214 terms
"prior authorization" → "approval before care" · keep "Medicaid" · acronyms spelled out
Set it once, at the top
Organization profileSets every rule: voice, reading level, glossary and disclaimers.
Medicare brandInherits every rule. Overrides the voice.
Medicaid line of businessInherits every rule. Adds its own content types.
- Puerto Rico Spanish teamInherits the Medicaid rules. Locks Puerto Rico Spanish.
Commercial brandInherits every rule. Adds its own disclaimers.
Synthetic example
One sentence, two organizations' settings
Each organization sets its own voice, reading level, terms, content types and disclaimers in profiles. Here one source sentence runs through two made-up organizations' settings. Switch between them and watch the output change.
Source sentence · Flesch-Kincaid 12.2
Prior authorization is required prior to scheduling your MRI exam. Failure to obtain authorization may result in financial responsibility for the full cost of the service.
Profile settings · health plan
- Master ProfileHealth plan
- Line of BusinessMedicaid
- Content typePrior Authorization — Member Explainer
- Brand & VoiceVoice Tone
- Warm & Accessible. Speak to the member as "you". Say "we" for the plan.
- Setting mode: Custom
- Reading LevelReading Level Target
- Grade 6
- Setting mode: Inherit from Master Profile
- Content typeMin / Max Grade Level
- Grade 5 to 6
- Setting mode: Custom
- Content typeDefault Tone
- Empathetic, Reassuring
- Setting mode: Custom
- Content typeJargon Policy
- Define Inline (first use)
- Setting mode: Custom
- Plain LanguageBrand-Preferred Terms
- obtain -> get · financial responsibility -> pay
- Setting mode: Custom
- Glossary & TerminologyAcronyms
- MRI — Magnetic Resonance Imaging (first-mention rule)
- Setting mode: Inherit from Master Profile
- DisclaimersLanguage help
- Always-On · Footer
- Setting mode: Inherit from Master Profile
- Policy packWhen a pack rule fails
- Block · required phrase "Call 711 (TTY)"
- Setting mode: Custom
Custom: a value set on this profile. Default: the HealthLiteracyCopilot default. Inherit: the parent profile's value. Settings can be filled from an uploaded brand guide; nothing is saved until someone clicks Apply.
The same sentence, revised
Before you schedule your MRI (magnetic resonance imaging) exam, you need our approval. We call this prior authorization. If you do not get it, you may have to pay the full cost.
Approved disclaimer: You can get this letter in your language or in another format at no cost. Call 711 (TTY).
- Empathetic, Reassuring tone
- Grade 5 to 6 target
- Term defined at first use
- Acronym spelled out
- Approved disclaimer inserted verbatim
Flesch-Kincaid, this sample: grade 5.9 · target grade 5 to 6. A reviewer approves every change.
Profile settings · health system
- Master ProfileHealth system
- DepartmentImaging services
- Content typeProcedure Preparation
- Brand & VoiceVoice Tone
- Clear & Authoritative. Speak to the patient as "you". Say "your care team".
- Setting mode: Custom
- Reading LevelReading Level Target
- Grade 8
- Setting mode: Inherit from Master Profile
- Content typeMin / Max Grade Level
- Grade 6 to 8
- Setting mode: Default
- Content typeDefault Tone
- Informative, Formal
- Setting mode: Custom
- Content typeJargon Policy
- Standard Medical
- Setting mode: Custom
- Safety & AccuracyDo-Not-Replace List
- prior authorization !> pre-approval
- Setting mode: Custom
- Glossary & TerminologyAcronyms
- Common medical acronyms allowed
- Setting mode: Default
- DisclaimersLanguage help
- Always-On · Footer
- Setting mode: Custom
- Policy packWhen a pack rule fails
- Warn only · forbidden phrase "free gift"
- Setting mode: Inherit from Master Profile
Custom: a value set on this profile. Default: the HealthLiteracyCopilot default. Inherit: the parent profile's value. Settings can be filled from an uploaded brand guide; nothing is saved until someone clicks Apply.
The same sentence, revised
Your MRI exam needs prior authorization before it can be scheduled. Without prior authorization, you may have to pay the full cost of the exam.
Approved disclaimer: Free language help is available. Ask us for an interpreter.
- Informative, Formal tone
- Grade 6 to 8 target
- Protected term kept: "prior authorization"
- Standard medical terms allowed
- Approved disclaimer inserted verbatim
Flesch-Kincaid, this sample: grade 7.7 · target grade 6 to 8. A reviewer approves every change.
Synthetic example · made-up organizations and settings. Grades are the Flesch-Kincaid formula on each sentence, not product scores.
Built for healthcare, compared with general-purpose AI
| What you need | General-purpose AI out of the box | HealthLiteracyCopilot | Rung |
|---|---|---|---|
| Your brand voice, glossary and content types | Re-entered in each prompt | Set once in profiles; every team inherits them | L2 |
| Reviewer workflow and approvals | Not provided | Approve, edit or skip each change; a decision record for each document | L2 |
| Version history and audit trail | Chat history only | Locked versions and an append-only audit trail you can export | L2 |
Your brand voice, glossary and content typesRung: L2
- General-purpose AI out of the box
- Re-entered in each prompt
- HealthLiteracyCopilot
- Set once in profiles; every team inherits them
Reviewer workflow and approvalsRung: L2
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- Approve, edit or skip each change; a decision record for each document
Version history and audit trailRung: L2
- General-purpose AI out of the box
- Chat history only
- HealthLiteracyCopilot
- Locked versions and an append-only audit trail you can export
See all 16 differencesHide the full comparison
| What you need | General-purpose AI out of the box | HealthLiteracyCopilot | Rung |
|---|---|---|---|
| Scoring against health-literacy standards | Can simplify on request; no built-in N-PLAT or PEMAT scoring | N-PLAT and PEMAT scores, item by item | L2 |
| Spanish measured as Spanish | No built-in Spanish readability measures | SOL, Fernández-Huerta and INFLESZ, with targets per document type | L1 |
| Meaning kept after a rewrite | Depends on the prompt; no automatic check | Meaning check and clinical integrity check on every revision | L2 |
| Your brand voice, glossary and content types | Re-entered in each prompt | Set once in profiles; every team inherits them | L2 |
| Answers grounded in your sources | General knowledge unless you add files | Your knowledge base, with citations; strict mode refuses rather than guess | L2 |
| Reviewer workflow and approvals | Not provided | Approve, edit or skip each change; a decision record for each document | L2 |
| Version history and audit trail | Chat history only | Locked versions and an append-only audit trail you can export | L2 |
| Accessibility review with evidence | Not provided | WCAG 2.1 AA review; a qualified reviewer decides; an attested record is kept | L2 |
| Accreditation evidence | Not provided | Evidence organized against the requirements you track, with binders and share links | L2 |
| Testing with simulated readers | Not provided as a method | Persona testing: cloze, teach-back, action and numeracy probes, with confidence bands | L3 |
| Journeys and channel previews | Not provided | Touchpoint matrix and channel previews for email, text, letter, web and more | L4 |
| Channel limits checked | Not checked | Text message segments and opt-out; email subject and preview text lengths | L2 |
| Numbers flagged for checking | Not flagged | A "Numbers to verify" card for every dose, date and dollar amount | L2 |
| Workforce training | Not provided | ClearComm Academy and the Teach-Back simulator | L3–L4 |
| Security and access | Varies by vendor and plan | HealthcareGPS is SOC 2 Type II audited and HIPAA compliant; separate tenant per organization; role-based access | Enable |
| An independent grade | Grades its own draft if you ask | The scorer never grades its own revisions; what it can't score with confidence goes to a person | L2 |
Scoring against health-literacy standardsRung: L2
- General-purpose AI out of the box
- Can simplify on request; no built-in N-PLAT or PEMAT scoring
- HealthLiteracyCopilot
- N-PLAT and PEMAT scores, item by item
Spanish measured as SpanishRung: L1
- General-purpose AI out of the box
- No built-in Spanish readability measures
- HealthLiteracyCopilot
- SOL, Fernández-Huerta and INFLESZ, with targets per document type
Meaning kept after a rewriteRung: L2
- General-purpose AI out of the box
- Depends on the prompt; no automatic check
- HealthLiteracyCopilot
- Meaning check and clinical integrity check on every revision
Your brand voice, glossary and content typesRung: L2
- General-purpose AI out of the box
- Re-entered in each prompt
- HealthLiteracyCopilot
- Set once in profiles; every team inherits them
Answers grounded in your sourcesRung: L2
- General-purpose AI out of the box
- General knowledge unless you add files
- HealthLiteracyCopilot
- Your knowledge base, with citations; strict mode refuses rather than guess
Reviewer workflow and approvalsRung: L2
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- Approve, edit or skip each change; a decision record for each document
Version history and audit trailRung: L2
- General-purpose AI out of the box
- Chat history only
- HealthLiteracyCopilot
- Locked versions and an append-only audit trail you can export
Accessibility review with evidenceRung: L2
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- WCAG 2.1 AA review; a qualified reviewer decides; an attested record is kept
Accreditation evidenceRung: L2
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- Evidence organized against the requirements you track, with binders and share links
Testing with simulated readersRung: L3
- General-purpose AI out of the box
- Not provided as a method
- HealthLiteracyCopilot
- Persona testing: cloze, teach-back, action and numeracy probes, with confidence bands
Journeys and channel previewsRung: L4
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- Touchpoint matrix and channel previews for email, text, letter, web and more
Channel limits checkedRung: L2
- General-purpose AI out of the box
- Not checked
- HealthLiteracyCopilot
- Text message segments and opt-out; email subject and preview text lengths
Numbers flagged for checkingRung: L2
- General-purpose AI out of the box
- Not flagged
- HealthLiteracyCopilot
- A "Numbers to verify" card for every dose, date and dollar amount
Workforce trainingRung: L3–L4
- General-purpose AI out of the box
- Not provided
- HealthLiteracyCopilot
- ClearComm Academy and the Teach-Back simulator
Security and accessRung: Enable
- General-purpose AI out of the box
- Varies by vendor and plan
- HealthLiteracyCopilot
- HealthcareGPS is SOC 2 Type II audited and HIPAA compliant; separate tenant per organization; role-based access
An independent gradeRung: L2
- General-purpose AI out of the box
- Grades its own draft if you ask
- HealthLiteracyCopilot
- The scorer never grades its own revisions; what it can't score with confidence goes to a person
Your style rules, enforced on every edit
Try it · synthetic notice · nothing to paste. It runs in your browser. Nothing is saved or sent.
Turn on JavaScript to try other choices.
Original synthetic notice
Your Medi-Cal eligibility must be redetermined on an annual basis. Failure to return the enclosed renewal documentation by June 30 may result in the termination of your coverage. Certain services may require prior authorization from your health plan prior to the provision of care.
Flesch-Kincaid grade 12.7
Revised to: renewal notice · warm · 2 terms
Please renew your Medi-Cal by June 30 so you can keep your coverage. Fill out the form in this letter and mail it back to us. If we do not get it in time, your coverage may stop. Some care needs prior authorization prior approval before you get it. Call us if you have questions, and we will gladly help.
- Warm voice
- Grade 6 target
- Deadline first (required element)
- Protected term kept
- Glossary term
Flesch-Kincaid, this sample: before grade 12.7 · after grade 3.6. Revision works toward your target grade; a reviewer approves every change.
Illustrative mockup on a synthetic notice. Every variant was produced in HealthLiteracyCopilot and approved by a reviewer.
That's our voice and our terms
The review request's optional questions accept a public link to your style guide. It's optional.
Who uses it
Next step
HealthcareGPS is SOC 2 Type II audited and HIPAA compliant. How we protect your documents
Questions
Can each line of business have its own rules?
Yes. A child profile inherits the organization's rules and overrides only what differs.
Will AI rewrite our disclaimers?
No. Approved disclaimers are inserted from approved text. They are never generated or machine-translated.
Do drug names and other required words hurt the score?
Not if you approve them. Owners can mark required words as exceptions. Then they don't push the grade up.
Can we test a rule change before it goes live?
Yes. Policy packs are versioned and testable. Once published, a version can't be changed.