NAME: Medialyst · DATE: Aug 6, 2026 · Rerun · medialyst.aiLink to this section: The grade

Can AI make a media list?

Not yet, if we pitched these journalists our client would fire us.Carly, on the baseline · Jul 20

Every Thursday we hand the same client brief to our software and to Carly, who has been building media lists by hand for fourteen years. She marks ours against hers, out of 100, and we publish whatever she gives us. This is week one. You can see how it is going.

First list free. No credit card.
Embargoed until

Fair. We will tell you when we are better.

Every Thursday Carly builds the list by hand and grades ours against hers. We send you the number, whatever it says.

Next scoreThu, Aug 13

33.7/100

next test

025507510027.933.7JANFEBMARAPRMAYJUNJULAUG
100

The marking schemeLink to this section: The marking scheme

How the media list was marked.

Carly builds the list for a real client brief by hand, the way she has for fourteen years. Hers is the answer key. Three things are measured against it, each multiplied by a public weight, and added up.

Found7/43×.406.51 pts
Emails right4/7×.3017.14 pts
Good fits7/21×.3010.00 pts
The Carly Score33.7out of 100

Weights add to 1.00 · no hidden multiplier

FoundDid we find them?
The share of the 43 journalists on Carly's hand-built list that appeared on ours at all.
Emails rightWould it even land?
Of the 7 of her journalists we did find, the share whose address matched hers.
Good fitsWhen we say strong fit, is it?
Of the names the tool itself stamped a strong fit, the share Carly would pitch. Two backups are allowed at an outlet where it also found her person — you pitch one and fall back. Everyone else it vouched for, she would cut.
First list free. No credit card.
Embargoed until

Fair. We will tell you when we are better.

Every Thursday Carly builds the list by hand and grades ours against hers. We send you the number, whatever it says.

Next scoreThu, Aug 13

The pile so farLink to this section: The pile so far

Every paper she has handed back.

One real client brief a week, marked against the list she built by hand.

  1. Same brief, rerunLink to this section: Same brief, rerun, Aug 6, 2026+5.8 vs the walkthrough

    A job site’s Stress-Free Six-Figure Careers brief

    The same brief and the same answer key, run fresh through the product two weeks later — a real list anyone could pull. It found the same number of her journalists and the same number of right addresses; what moved is that more of the names it vouched for are ones she would actually pitch.

    • 7/43found no change · was 7/43
    • 4/7emails right no change · was 4/7
    • 7/21good fits 19.3pts · was 7/50

    33.7/100

    What we changed to get here

    • When we could barely find a journalist's published work, we now go looking for more of it before judging whether they fit.
    • When we still cannot find enough of it, we say “not enough evidence” instead of inventing a confident-looking score.
    • An author's index page no longer counts as an article they wrote.
    • An email or LinkedIn profile that matches a completely different name is no longer treated as a confirmed match.
    • Articles the assistant adds to an imported list now actually get turned into journalists.
  2. A job site’s Stress-Free Six-Figure Careers brief

    The list our product built, walked through with her line by line.

    • 7/43found
    • 4/7emails right
    • 7/50good fits

    27.9/100

    Why this is the first mark

    Seven months building this, with nothing to grade it against — we genuinely did not know whether the lists were any good. Then Carly came on as our Founding Strategic Advisor and marked the first one we handed her. She is not going easy on us. That is the entire reason we asked her.

Your turnLink to this section: Grade our list

Want to grade our list?

Run your own brief. Then do the thing you would do anyway before you hit send: go down the list and cut the names you would cut. Tell us how many survived and what we got wrong.

Post it wherever you post, send us the link, and we will pin it here. We do not edit it.

  • Pros Very campaign specific Easy to use Cons - Not a replacement for MuckRack yet - Didn't see a way to compare the list that you compiled based off my pitch compared to a list I already currently had

  • Apparently, telling the AI “make no mistake” does not improve the quality of the list.

  • A lot of these are advertorial articles. Can you pick up earned coverage? I want to see more broadly stories from the restaurant and chef business world. These focus too much on delivery.

    Anonymous CapybaraMedialyst user (paraphrased)
  • can you resort the list to make it only north america? I see indonesia. And many of these emails are not deliverabke

    Anonymous QuokkaMedialyst user (paraphrased)
  • i need top tier national outlets, not regional

    Anonymous FoxMedialyst user (paraphrased)
  • this media list is only supposed to be local albany publications and reporters

    Anonymous KoalaMedialyst user (paraphrased)
  • you are surfacing a lot of national journalists based in NYC. I only want to see people from New York specific media outlets who cover NYC.

    Anonymous OtterMedialyst user (paraphrased)
  • I do not think we want people who write about Indianapolis already; that will result in local writers. We want national sports, economics, or leadership writers

    Anonymous BadgerMedialyst user (paraphrased)

Pin your note

Paper
220 left

Build a list → More options → Share table → paste it here. We check that it opens, stamp the note with what you graded, and publish the link on the note so anyone can open the list you marked. Notes without one still go up; they just do not carry the receipt.

Shows effort.— C.M.