Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for epidemiologists

Disease Surveillance Signal Agent

Early, reliable detection of unusual disease activity

Disease Surveillance Signal Agent: what goes in, what the agent does and what you get

What it does

Surveillance data arrives every day from labs, clinics and hospitals, and staff must decide quickly whether a rise is real. This agent runs detection methods on case counts by disease, area and age group and compares them with expected counts for the season. Before calling a signal, it checks reporting delays and data quality, because a batch of late reports can look like an outbreak. If the rise traces back to a reporting change, it marks it that way and keeps watching. For signals that hold up, it summarizes the case details, such as onset dates, places and common exposures, and suggests next steps. It never starts an investigation or a public message itself. You decide on investigation and communications. Edge case: a jump caused by a new lab starting to report is flagged as a reporting change.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Daily data load 2 USES A TOOL Pull case and lab reports 3 DOES Run detection methods 4 CHECKS THE RESULT Is the signal real and not a reporting artifact? If not: mark as reporting change. Back to step 2. 5 DOES Summarize case details 6 YOU APPROVE Epidemiologist decides on investigation 7 RESULT Signal log updated
Read the steps as a list
  1. Daily data load
  2. Pull case and lab reports
  3. Run detection methods
  4. Is the signal real and not a reporting artifact?If not: mark as reporting change. Back to step 2.
  5. Summarize case details
  6. Epidemiologist decides on investigationThe agent waits here for your OK.
  7. Signal log updated

How it decides

It flags counts above the expected threshold after adjusting for reporting delays.

  • Adjust for reporting delays
  • Flag new reporting sources
  • Use seasonal baselines

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Detection method
  • Threshold
  • Diseases
  • Report time

What keeps you in control

It always asks you first

  • Starting investigations
  • Public communications

Hard limits

  • Never releases data publicly

It stops when

  • Done: log updated
  • Stop: data feed down

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensOn August 14 the agent flagged 23 salmonella cases in Clark County against an expected 8. Before calling a signal it checked reporting dates. Eleven cases came from one lab that sent two weeks of reports at once. It went back and reran detection by onset date. The excess held at 15 cases against 7, clustered in ages 20 to 34. The epidemiologist reviewed the summary and opened an investigation.

More agents for epidemiologists