Aaron Tay's Musings about Librarianship

Better AI Search Rubrics: Roles, Gates, and Retrieval Tests

Some suggestions on how to construct AI search evaluation frameworks

Apr 29 • Aaron Tay

9

2

1

AI academic search needs better frameworks for understanding and evaluation. These three librarian projects are a start

What it looks like when the AI search conversation and understanding gets serious

Apr 20 • Aaron Tay

26

2

3

From Fixed Search Workflows to Agentic Academic Search: Promise, Progress, and the Invisible Menu Problem

Undermind's Projects features gives a taste of the promise and challenges of managing agents by users

Apr 12 • Aaron Tay

16

2

March 2026

The Horseless Carriage of AI Search: Why Using LLMs to Generate Boolean Alone Is Likely of Little Benefit

Not exactly saying Boolean must die.....but... maybe less focus?

Mar 21 • Aaron Tay

28

6

3

February 2026

The agentic researcher - building custom, transparent and extensible workflows with Claude & MCP

Why generic LLM + academic MCP servers might be as good if not better than specalised Academic deep research

Feb 23 • Aaron Tay

29

5

2

Are AI Tools Killing Review Articles? Two Failure Modes Suggest Otherwise

arXiv recently restricted review article submissions in computer science, requiring journal or conference acceptance before deposit. They noted…

Feb 12 • Aaron Tay

15

1

2

January 2026

The Sycophancy Fallacy: Why You May be Worried About the Wrong Bias with Search

AI search tools aren't "agreeing" with users—they are retrieval systems. Confusing the two is a category error that obscures the real risks.

Jan 31 • Aaron Tay

23

6

4

Classifying the Ways LLMs Summarise in Academic Search

Understanding AI Summaries in EBSCO, ProQuest, and More

Jan 24 • Aaron Tay

20

2

4

The Blank Box Problem: Why It's Harder Than Ever to Know What to Type Into an AI Search Bar

We’ve traded keyword constraints for infinite potential, and created a massive usability crisis in the process.

Jan 10 • Aaron Tay

21

5

2

December 2025

What Do We Actually Mean by "AI-Powered Search"?

When we say "AI-powered search engine," we're conflating at least four different things—and your concerns about one may not apply to another.

Dec 27, 2025 • Aaron Tay

25

1

3

Why Ghost References Still Haunt Us in 2025—And Why It's Not Just About LLMs

Ghost references existed long before LLMs. This post examines how Google Scholar's [CITATION] mechanism and web pollution may undermine RAG…

Dec 22, 2025 • Aaron Tay

21

10

2

Deep Research, Shallow Agency: What Academic Deep Research Can and Can't Do

The Agentic Illusion: Most Academic Deep Research runs fixed workflows and stumble when given unfamiliar literature review tasks that do not fit them.

Dec 8, 2025 • Aaron Tay

22

4

3