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 journalists

Beat Records Monitor Agent

No important item on the beat missed

MonitoringResearchWriters
See how it worksGet access
Beat Records Monitor Agent: what goes in, what the agent does and what you get

What it does

A beat reporter has to watch many sources: council agendas, court dockets, business filings, inspection reports and press releases. This agent checks your chosen sources every morning and pulls what is new since yesterday. It first checks that each source loaded and parsed correctly. If one failed or changed format, it retries and then flags it in the tip sheet instead of quietly missing items. It filters items by the keywords, people and companies you watch and ranks them by likely news value, with watched names highest. For the top items it pulls your newsroom's past coverage so you have background fast. It then checks the top items are truly new and not repeats of things you already covered. You decide what to chase. Edge case: a sealed court filing shows only as a docket line, and the agent notes it cannot see the document.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Morning run 2 USES A TOOL Pull new items from each source 3 CHECKS THE RESULT Did every source load and parse correctly? If not: retry, then flag broken sources in the tipsheet. Back to step 2. 4 DOES Filter and rank items by news value 5 USES A TOOL Pull past coverage for top items 6 CHECKS THE RESULT Are the top items new and not already covered? If not: drop repeats and promote the next items. Back tostep 4. 7 DOES Assemble the tip sheet 8 YOU APPROVE Reporter picks items to pursue 9 RESULT Morning tip sheet delivered
Read the steps as a list
  1. Morning run
  2. Pull new items from each source
  3. Did every source load and parse correctly?If not: retry, then flag broken sources in the tip sheet. Back to step 2.
  4. Filter and rank items by news value
  5. Pull past coverage for top items
  6. Are the top items new and not already covered?If not: drop repeats and promote the next items. Back to step 4.
  7. Assemble the tip sheet
  8. Reporter picks items to pursueThe agent waits here for your OK.
  9. Morning tip sheet delivered

How it decides

It ranks new items by matches with watched names and keywords and by how often similar items became stories before.

  • Rank items with watched names highest
  • Flag sources that fail or change format
  • Note documents that are sealed or behind fees

Make it yours

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

  • Sources to watch
  • Keywords and names
  • Delivery time
  • Tip sheet length

What keeps you in control

It always asks you first

  • Pursuing a story or contacting sources

Hard limits

  • Uses public sources only
  • Never contacts anyone

It stops when

  • Done: tip sheet delivered
  • Stop: most sources down; alert the reporter

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 happensOn the morning of February 12, one court docket source had changed its page layout. The load check failed, so the agent retried, then flagged it. Among 63 new items, it ranked a zoning variance for a watched developer first and pulled two past stories about the same site. The repeat check dropped an inspection already covered last week. The reporter picked the zoning story.

More agents for journalists

Quality control · Writers

Nonfiction Claim Evidence Agent

A draft where every factual claim is backed by a source passage at the right strength.

8 steps1 check6 jobs
Compliance · Risk management

Writer Source Permission Agent

Every piece of third-party material used within its permissions.

7 steps1 check4 jobs
Quality control · Writers

Interview Transcript Attribution Agent

A transcript where every attributed quote is supported.

8 steps1 check2 jobs
Research · Planning

Research Interview Question Plan Agent

Story questions answered with sourced notes, and a plan for the remaining interviews

10 steps2 checks8 jobs