Talk about your next project
AgentMail executive brief

The lesson

Turn a surprising result from your own benchmark into a headline, then use the data to argue a broader position your product happens to serve.

The move

The essay opens with a provocative title and a TL;DR stating that all ten Claude setups finished in the bottom eleven of the 25 combinations, then explains the eval method and shows a bar chart of scores. Question headings walk the reader through the investigation: 'How did Claude score in AgentMail Evals?', 'Did Claude fail to find the hidden emails?', and 'Which jobs caused the gap?', each answered with a table that narrows the gap down to replying to mail flagged as spam. A highlighted line, 'Claude's default is no, and everyone else's is yes,' sets up the thesis that a default is not a policy, and 'How do you set email security rules for an AI agent?' closes by pointing to AgentMail Lists and Drafts.

Why it works

  • Our readA headline about a well-known model coming last pulls in readers who would never click on an email infrastructure post.
  • Our readEach heading rules out an obvious explanation in turn, so the final claim feels earned instead of asserted.
  • Our readFraming the choice as 'a wrong no' versus 'a wrong yes' gives the reader a position they can disagree with, which leads naturally to the product as the way to set the rule yourself.

What not to copy

Don't copy the jab at a named model or the spam-reply finding, which depend on AgentMail's own eval. Keep the structure: lead with a surprising result, rule out explanations one heading at a time, name the real cause, then move to a stance on what the reader should do.

More from AgentMail

More executive briefs

Steal it for your brand.

Tell us what you want to make. We’ll talk through how to put these ideas to work for your brand.