Skip to content

Demo content Everything on this site is sample data shipped with the template. Configure it or follow the launch guide (opens in a new tab).

Big Cities Health Coalition AI Use Case Catalog

In production · Prairie Ridge County Health Department

Playbook or write-up Featured

Plain-language rewrites for public notices

Result in one line: Median reading level of published notices dropped from grade 14 to grade 7

A prompt kit and review checklist staff use to rewrite public notices at a sixth-grade reading level without changing what the notice requires.

Published July 8, 2026 Verified August 10, 2026

Documentation or write-up
Skills needed to set it up
Anyone on staff
Readiness
Ready to deploy Human review built in
Data it touches
Public data only
Who sees the output
Public-facing
License
Creative Commons (CC BY / CC0)
Cost to stand up
No new spend
Portable to other platforms
Yes — platform-agnostic
Use case category
Communications, media & writing
Reviews it went through
Legal or contracts review Community or advisory review Equity impact assessment
What do these mean?
Anyone on staff
No technical skills — follow the instructions.
Ready to deploy
Can be used as-is with minimal configuration.
Human review built in
A person checks the AI's output before it is used.
Public data only
Only data that is already public.
Public-facing
Residents or the general public interact with it.
Creative Commons (CC BY / CC0)
For documents, prompts, datasets and training material.
No new spend
Built with licences, staff and infrastructure the organization already had.
Yes — platform-agnostic
Runs on any comparable stack with configuration changes only.
Communications, media & writing
Drafting, translating, summarising and publishing.

Problem

Our public notices were written to satisfy a regulation, not to be read. A boil water advisory opened with “Pursuant to the applicable state drinking water regulations” and buried the instruction — boil your water for one minute — in the fourth line of a 68-word sentence. Residents called to ask what they were supposed to do. Staff read the notice back to them over the phone, in plain language, which told us the problem was the writing and not the reader.

What we built

A prompt kit and a review checklist. That is the whole thing.

The kit is a shared document with four prompts: rewrite at a sixth-grade level, produce a two-line version for social media, produce a translation request package, and check a draft against the plain-language rules. Staff paste the notice, pick the audience, and get a draft. No accounts to create, no tool to install — it uses the AI workspace the organization already licenses.

The checklist is what makes it safe. Before anything is published, the drafter confirms that the required action is in the first line, that the specifics (times, temperatures, dates, area) are unchanged, that no instruction was invented, and that any legally required wording still appears in the full notice.

How it works

The rewrite is always a draft. Communications staff edit it, the program lead approves it, and legally required wording is reinstated verbatim where the regulation demands it. For translated versions, the kit produces a package for a bilingual staff member or contracted translator to review — we do not publish a machine translation that no person has read.

Everything the kit touches is already public information, so there is nothing sensitive in the workflow at all. That is a large part of why this was easy to approve.

Results

Median reading level across notices published in the first six months fell from grade 14 to grade 7. Call volume to the main line after an advisory dropped noticeably, though we have not measured it carefully enough to claim a number.

The unexpected result was internal: staff started writing the first draft in plainer language themselves, because the checklist made the standard concrete.

Lessons learned

The checklist matters more than the prompts. Early drafts softened things — an advisory that said water “may not be safe” became water that was “generally fine” — and only a review step catches that reliably.

How to reuse

Copy the kit, replace our examples with your own notices, and keep the checklist as written. Anyone on staff can use it on day one; the only setup is agreeing internally on who approves a rewritten notice.

About

Area of work
  • Communications & outreach
  • Emergency preparedness
Review status
Reviewed & approved

How it's built

How AI is involved
AI is part of the solution
Types of AI
  • Generative text (LLM)
  • Translation
AI tools & models
  • ChatGPT Enterprise
  • Claude
Where it runs
  • Enterprise AI workspace
  • Desktop or local

Sharing & licensing

Portability notes
A prompt kit and a style guide; they work in any generative text tool.
Adapted from

What it took

Cost to keep running
Under $10k/yr
How it was bought
  • Existing enterprise licence
Who it affects
The whole point is the residents the old notices lost: we measure reading level before and after, and the community review panel reads the rewrite before it ships. Translation is where it can quietly go wrong — a rewrite that gets simpler in English can get less precise in Spanish and Vietnamese, so both translations are reviewed by a human, never machine-translated from the rewrite.

Data & access

No PII/PHI in the shared material
Yes
Data sources
  • Published notice archive
  • Required regulatory wording list
Data-governance caveats
Only already-published notices are used; nothing internal or personal is involved.

Printed from AI Use Case Catalog
https://crypticpy.github.io/bchc-ai-use-case-catalog/catalog/plain-language-notices/