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).

Idea / exploring · Sunrise Plains Regional Health Coalition

Playbook or write-up

Extreme-heat outreach targeting brief

A worked plan for using the county's existing heat-vulnerability index plus forecast data to decide, two days ahead of a heat event, which neighborhoods get door-knocking, which get robocalls, and which cooling centers to extend — written up for other jurisdictions to adapt before we build anything.

Published August 26, 2026

Documentation or write-up (opens in a new tab)
Skills needed to set it up
Anyone on staff
Readiness
Reference only
Data it touches
Public data only
Who sees the output
Partner organizations
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
Not yet reviewed
What do these mean?
Anyone on staff
No technical skills — follow the instructions.
Reference only
Documentation and lessons — not something to deploy.
Public data only
Only data that is already public.
Partner organizations
Shared with specific partner organizations.
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.
Not yet reviewed
Shared honestly — this has not been through a formal review.

After the July 2025 heat event, our after-action review found outreach went where it always goes — the neighborhoods with the most 311 calls — not where the risk was. This brief is the plan we wish we’d had: a scoring recipe that combines the vulnerability index with the block-level forecast, thresholds for each outreach tier, and a decision timeline that starts 48 hours out.

We used an LLM to draft and pressure-test the playbook against three past events, but the operational version needs no AI at all — it’s a spreadsheet and a checklist on purpose, so a duty officer can run it at 6am. We’re sharing at the idea stage because we’d rather three coalition members poke holes in it now than after we’ve built tooling around it.

About

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

How it's built

How AI is involved
AI was used to build it
Types of AI
  • Generative text (LLM)
  • Prediction & forecasting
AI tools & models
  • Gemini
  • NWS point forecast API

What it took

Cost to keep running
No ongoing cost
How it was bought
  • No procurement needed
Who it affects
The targeting logic deliberately weights unhoused residents, older adults living alone, and homes without central air — the groups our after-action reviews say we reached last in 2025. The brief includes the equity questions a review board should ask before any jurisdiction operationalizes it.

Data & access

No PII/PHI in the shared material
Yes
Data sources
  • CDC/ATSDR Social Vulnerability Index
  • NWS forecast API
  • County cooling-center registry (public)