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 librarians

Collection Weeding Review Agent

A reviewed list of items to weed

Collection Weeding Review Agent: what goes in, what the agent does and what you get

What it does

Collections need regular weeding to stay useful and fit the space, but reviewing usage, age and condition item by item is slow. This agent reads circulation data, publication dates, condition notes and holdings at other libraries, and lists weeding candidates using the library's rules for each section. It then removes items that must be kept, such as last copies in the region, items on course or curriculum lists, and local history. It checks the list again for anything protected and marks those items as keep. Librarians review the final list and decide every withdrawal. Edge case: a heavily used but damaged item is listed for replacement rather than withdrawal, so a popular title does not disappear from the shelf.

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 Section review 2 USES A TOOL Read circulation, dates and condition notes 3 USES A TOOL Check holdings at other libraries 4 DOES List candidates by usage, age and condition 5 CHECKS THE RESULT Are last copies and protected items excluded? If not: remove them from the list and mark as keep. Backto step 4. 6 DOES Prepare the list with reasons for each item 7 YOU APPROVE Librarian decides 8 RESULT Weeding list
Read the steps as a list
  1. Section review
  2. Read circulation, dates and condition notes
  3. Check holdings at other libraries
  4. List candidates by usage, age and condition
  5. Are last copies and protected items excluded?If not: remove them from the list and mark as keep. Back to step 4.
  6. Prepare the list with reasons for each item
  7. Librarian decidesThe agent waits here for your OK.
  8. Weeding list

How it decides

Rules on use and age.

  • No use in 5 years
  • Last copies kept
  • Local history excluded

Make it yours

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

  • Rules
  • Sections
  • Exclusions
  • Format

What keeps you in control

It always asks you first

  • Withdrawals

Hard limits

  • No withdrawals by agent

It stops when

  • Done: list
  • Stop: none

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 happensFor the 600s section, the agent read data for 2,100 items and listed 180 weeding candidates with no loans in 5 years. The check found 9 were the last copy in the region and 2 were local history, so it looped back and removed them. Librarian Hana Lee reviewed the 169 items and approved withdrawing 140.

More agents for librarians