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 pharmacists

Drug Recall Patient Lookup Agent

Complete recall actions quickly and completely

Drug Recall Patient Lookup Agent: what goes in, what the agent does and what you get

What it does

When a recall notice arrives, the pharmacy must pull stock quickly and, for patient-level recalls, contact every patient who got the product. This agent reads the notice and extracts product, strength and lot numbers. It searches stock and dispensing records, lists stock to pull, and lists patients who received affected lots. It drafts patient messages that fit the recall level. After staff pull the stock, it checks the counts match what the records show. It tracks patient contacts and follows up on anyone not yet reached. The pharmacist approves all patient messages and returns to the supplier. Edge case: if lot numbers were not recorded when the drug was dispensed, it lists every patient who received that product during the recall window.

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
ApprovedYes, continueNo 1 STARTS WHEN Recall notice received 2 USES A TOOL Extract product and lots 3 USES A TOOL Search stock and dispensing 4 DOES List stock to pull and patients 5 YOU APPROVE Pharmacist approves messages 6 CHECKS THE RESULT Is all stock pulled and every patient contacted? If not: follow up on gaps. Back to step 4. 7 RESULT Recall record
Read the steps as a list
  1. Recall notice received
  2. Extract product and lots
  3. Search stock and dispensing
  4. List stock to pull and patients
  5. Pharmacist approves messagesThe agent waits here for your OK.
  6. Is all stock pulled and every patient contacted?If not: follow up on gaps. Back to step 4.
  7. Recall record

How it decides

Recall level sets the action. Patients are found by lot or by product window.

  • Patient-level recalls need contact
  • Unknown lots widen the search
  • Contacts logged

Make it yours

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

  • Contact methods
  • Attempts
  • Message templates
  • Report format

What keeps you in control

It always asks you first

  • Patient messages
  • Returns

Hard limits

  • No clinical advice beyond the notice

It stops when

  • Done: all actions logged
  • Stop: patients unreachable after 3 tries

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 happensA recall notice on April 22 named levothyroxine 50 mcg, lots K2241 and K2245, at the patient level. The agent found 3 bottles in stock and 27 patients who received those lots. The pharmacist approved the messages. Two days later the check showed 4 patients not reached and one bottle still in the will-call bin. The agent went back, listed them for calls and pulled the bottle. All were reached by April 25.

More agents for pharmacists