Claude to check Libby before spending Audible credits
Brian Frost wanted to check library access before using Audible credits on books from his wishlist. He had Claude build a workflow that compared the wishlist with Libby, separating titles he could borrow immediately from those requiring a wait or unavailable through the library.
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Compare these Audible wishlist titles with my Libby library. Check the actual Borrow button and hold state, classify immediate access versus waits, and report results for my review.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- Brian Frost
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- An ongoing Audible versus Libby comparison separated immediate borrowing, waits and unavailable titles; the full seven hundred title list was not completed.
- Human involvement
- Frost checked Libby before purchasing and was still processing the large wishlist in batches of ten to twenty titles.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Compare Audible wishlist titles with the library's Libby catalog.
- Check the exact Borrow control and classify holds separately from immediate availability.
- Process small batches and personally verify Libby before spending a credit.
Brian Frost wanted to check library access before using Audible credits on books from his wishlist. He had Claude build a workflow that compared the wishlist with Libby, separating titles he could borrow immediately from those requiring a wait or unavailable through the library.
The difficult part was interpreting availability accurately. Frost found that badges and estimated waiting times did not always mean the same thing as an active borrowing option. The workflow needed to check for the exact Borrow button text and distinguish a pending hold from an active one.
That distinction changed the output from a broad claim that a book existed in the catalog into a decision about whether he could read or listen to it now. Frost described checking Libby himself before spending an Audible credit, retaining the final purchase choice rather than asking the agent to acquire every title automatically.
In a followup on the same primary page, he said the wishlist contained about seven hundred titles and he was processing batches of ten to twenty. The audit was still incomplete. The source does not report seven hundred completed checks, a quantified saving or automatically placed library loans. Its outcome is an ongoing availability comparison designed around the actual library controls, with human verification before a paid audiobook choice.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: app.therundown.ai · Brian Frost
Frequently asked questions
Why was an availability badge insufficient?
Badges and wait estimates could be misleading, so the workflow checked the actual Borrow button text.
How much of the wishlist was finished?
Frost described about seven hundred titles and batches of ten to twenty, with the audit still ongoing.
Were loans or purchases automatic?
The account describes the author's Libby check before spending credits, not automatic borrowing or purchases.
More details
About this account
Claude created a wishlist comparison workflow that checked library availability and distinguished borrowable titles from holds.
Firsthand source opened and read. Suggested prompt written by us from the reported workflow; no original task prompt is quoted.
Credit: Brian Frost
Source published
Added to Agents In Use
Source checked
Tools and topics
Claude Code · Claude Artifacts · Audible · Libby
Library availability · Audible wishlist · Libby holds · Borrow buttons
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.