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 professors

Research Literature Watch Agent

Deliver a short weekly list of relevant new research with extracted methods and findings

Research Literature Watch Agent: what goes in, what the agent does and what you get

What it does

A working paper on minimum wages appears and the economist finds it three months later during a seminar. This agent scans working paper series, journals and preprint sites for the topics the economist cares about. It ranks new papers by relevance to the current projects and extracts the method, data, main findings and caveats. It checks the overlap with the economist's own work, such as the same question with a different data set. It looks at which keywords found useful papers and refines the keyword list. It builds a weekly digest with a short note on why each paper matters. The economist approves the digest before it is shared. Edge case: a revised version of a paper already read is marked as updated, with the changed results.

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 Weekly scan 2 USES A TOOL Search working paper series, journals and preprints 3 DOES Remove papers already read and mark updates 4 DOES Rank papers by relevance to current projects 5 USES A TOOL Extract method, data, findings and caveats 6 CHECKS THE RESULT Are at least 5 papers above the relevance cutoff? If not: Widen or refine the keywords and rescan. Back tostep 2. 7 DOES Check overlap with the economist's own work 8 DOES Build the digest with notes on why each matters 9 YOU APPROVE Economist approves the digest 10 RESULT Weekly literature digest
Read the steps as a list
  1. Weekly scan
  2. Search working paper series, journals and preprints
  3. Remove papers already read and mark updates
  4. Rank papers by relevance to current projects
  5. Extract method, data, findings and caveats
  6. Are at least 5 papers above the relevance cutoff?If not: Widen or refine the keywords and rescan. Back to step 2.
  7. Check overlap with the economist's own work
  8. Build the digest with notes on why each matters
  9. Economist approves the digestThe agent waits here for your OK.
  10. Weekly literature digest

How it decides

It ranks papers by keyword and topic match with the projects and includes only those above the relevance cutoff.

  • Include only papers above the relevance cutoff
  • Mark revised versions as updated
  • Flag direct overlap with current projects
  • Retire keywords that return nothing useful for 4 weeks

Make it yours

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

  • Topics and keywords (default the economist's list)
  • Relevance cutoff (default top 10 papers)
  • Sources scanned (default working paper series and journals)
  • Digest day (default Monday)

What keeps you in control

It always asks you first

  • Economist approves the digest before it is shared

Hard limits

  • Never claim findings the paper does not state
  • Cite every paper with its source
  • Do not share unpublished work

It stops when

  • Done: Digest approved and delivered
  • Stop: Source access fails, so hand to the economist

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 happensThis week the scan finds 63 new papers. After removing 9 already read, 4 are above the cutoff, under the 5 wanted. The agent adds the keyword wage compression and finds 3 more. It extracts methods and flags 1 paper that uses the same data as the economist's project. The economist approves a digest of 7 papers.

More agents for professors